P. Bartlett

发表

Variance Reduction Techniques for Gradient Estimates in Reinforcement Learning

Peter L. Bartlett, Jonathan Baxter, Evan Greensmith, 2001, J. Mach. Learn. Res..

Learning in Neural Networks: Theoretical Foundations

Peter L. Bartlett, Martin Anthony, P. Bartlett, 1999 .

Direct gradient-based reinforcement learning

J. Baxter, P. L. Bartlett, P. Bartlett, 2000, 2000 IEEE International Symposium on Circuits and Systems. Emerging Technologies for the 21st Century. Proceedings (IEEE Cat No.00CH36353).

Infinite-Horizon Policy-Gradient Estimation

Peter L. Bartlett, Jonathan Baxter, P. Bartlett, 2001, J. Artif. Intell. Res..

Stochastic optimization of controlled partially observable Markov decision processes

P. Bartlett, Jonathan Baxter, 2000, Proceedings of the 39th IEEE Conference on Decision and Control (Cat. No.00CH37187).

Convexity, Classification, and Risk Bounds

Michael I. Jordan, Jon D. McAuliffe, P. Bartlett, 2006 .

Empirical minimization

P. Bartlett, S. Mendelson, 2006 .

Direct Optimization of Margins Improves Generalization in Combined Classifiers

Peter L. Bartlett, Llew Mason, Jonathan Baxter, 1998, NIPS.

Local Rademacher complexities

P. Bartlett, O. Bousquet, S. Mendelson, 2005, math/0508275.

` p-Norm Multiple Kernel Learning

P. Bartlett, M. Kloft, vorgelegt von Dipl.-Math, 2008 .

Experiments with Infinite-Horizon, Policy-Gradient Estimation

Peter L. Bartlett, Lex Weaver, Jonathan Baxter, 2001, J. Artif. Intell. Res..

Estimation and Approximation Bounds for Gradient-Based Reinforcement Learning

Peter L. Bartlett, Jonathan Baxter, P. Bartlett, 2000, J. Comput. Syst. Sci..

Lower bounds on the Vapnik-Chervonenkis dimension of multi-layer threshold networks

Peter L. Bartlett, P. Bartlett, 1993, COLT '93.

Reinforcement Learning in POMDP's via Direct Gradient Ascent

Peter L. Bartlett, Jonathan Baxter, P. Bartlett, 2000, ICML.

Optimal Robust Linear Regression in Nearly Linear Time pdf

Michael I. Jordan, Peter L. Bartlett, Yeshwanth Cherapanamjeri, 2020, ArXiv.

Quantitative Central Limit Theorems for Discrete Stochastic Processes pdf

Michael I. Jordan, Peter L. Bartlett, Xiang Cheng, 2019, ArXiv.

Optimal Mean Estimation without a Variance pdf

Michael I. Jordan, Peter L. Bartlett, Yeshwanth Cherapanamjeri, 2020, COLT.

Spectrally-normalized margin bounds for neural networks

Matus Telgarsky, Peter L. Bartlett, Dylan J. Foster, 2017, NIPS.

Probabilities for SV Machines

P. Bartlett, Dale Schuurmans, B. Schölkopf, 2000 .

Boosting Algorithms as Gradient Descent

Peter L. Bartlett, Marcus R. Frean, Llew Mason, 1999, NIPS.

Structural Risk Minimization Over Data-Dependent Hierarchies

John Shawe-Taylor, Peter L. Bartlett, Martin Anthony, 1998, IEEE Trans. Inf. Theory.

Function Learning from Interpolation

P. Bartlett, M. Anthony, 2000, Combinatorics, Probability and Computing.

An inequality for uniform deviations of sample averages from their means

P. Bartlett, G. Lugosi, 1999 .

A Result Relating Convex n-Widths to Covering Numbers with some Applications to Neural Networks

Peter L. Bartlett, Jonathan Baxter, P. Bartlett, 1997, EuroCOLT.

The importance of convexity in learning with squared loss

Peter L. Bartlett, Wee Sun Lee, Robert C. Williamson, 1998, COLT '96.

Fast Mean Estimation with Sub-Gaussian Rates pdf

Peter L. Bartlett, Yeshwanth Cherapanamjeri, Nicolas Flammarion, 2019, COLT.

Efficient agnostic learning of neural networks with bounded fan-in

Peter L. Bartlett, Wee Sun Lee, Robert C. Williamson, 1996, IEEE Trans. Inf. Theory.

RL$^2$: Fast Reinforcement Learning via Slow Reinforcement Learning pdf

Peter L. Bartlett, Pieter Abbeel, Xi Chen, 2016, ArXiv.

An Introduction to Reinforcement Learning Theory: Value Function Methods

Peter L. Bartlett, P. Bartlett, 2002, Machine Learning Summer School.

Adaptive Online Gradient Descent

Peter L. Bartlett, Elad Hazan, Alexander Rakhlin, 2007, NIPS.

The Sample Complexity of Pattern Classification with Neural Networks: The Size of the Weights is More Important than the Size of the Network

Peter L. Bartlett, P. Bartlett, 1998, IEEE Trans. Inf. Theory.

Rademacher and Gaussian Complexities: Risk Bounds and Structural Results

Peter L. Bartlett, Shahar Mendelson, P. Bartlett, 2003, J. Mach. Learn. Res..

Neural Network Learning - Theoretical Foundations

Peter L. Bartlett, Martin Anthony, P. Bartlett, 1999 .

Optimal Stragies and Minimax Lower Bounds for Online Convex Games

Ambuj Tewari, Peter L. Bartlett, Jacob D. Abernethy, 2008, COLT.

Regularization Networks and Support Vector Machines

Bernhard Schölkopf, Alexander J. Smola, Dale Schuurmans, 2000 .

Improved Learning Complexity in Combinatorial Pure Exploration Bandits

Peter L. Bartlett, Alessandro Lazaric, Ronald Ortner, 2016, AISTATS.

Exchangeability Characterizes Optimality of Sequential Normalized Maximum Likelihood and Bayesian Prediction

Peter L. Bartlett, Fares Hedayati, P. Bartlett, 2012, IEEE Transactions on Information Theory.

Adaptive Averaging in Accelerated Descent Dynamics

Alexandre M. Bayen, Peter L. Bartlett, Walid Krichene, 2016, NIPS.

The Rademacher Complexity of Co-Regularized Kernel Classes

Peter L. Bartlett, David S. Rosenberg, P. Bartlett, 2007, AISTATS.

Optimistic Linear Programming gives Logarithmic Regret for Irreducible MDPs

Ambuj Tewari, Peter L. Bartlett, P. Bartlett, 2007, NIPS.

Almost Linear VC-Dimension Bounds for Piecewise Polynomial Networks

Peter L. Bartlett, Ron Meir, Vitaly Maiorov, 1998, Neural Computation.

Optimal Online Prediction in Adversarial Environments

Peter L. Bartlett, P. Bartlett, 2010, Discovery Science.

Optimal strategies and minimax lower bounds for online convex games [Technical Report No. UCB/EECS-2008-19]

P. Bartlett, Ambuj Tewari, J. Abernethy, 2008 .

The minimax distortion redundancy in empirical quantizer design

Tamás Linder, Peter L. Bartlett, Gábor Lugosi, 1997, Proceedings of IEEE International Symposium on Information Theory.

Local Complexities for Empirical Risk Minimization

Peter L. Bartlett, Shahar Mendelson, Petra Philips, 2004, COLT.

The VC Dimension and Pseudodimension of Two-Layer Neural Networks with Discrete Inputs

Peter L. Bartlett, Robert C. Williamson, R. C. Williamson, 1996, Neural Computation.

Covering numbers for support vector machines

John Shawe-Taylor, Peter L. Bartlett, Ying Guo, 2002, IEEE Trans. Inf. Theory.

On the Theory of Variance Reduction for Stochastic Gradient Monte Carlo pdf

Michael I. Jordan, Peter L. Bartlett, Yi-An Ma, 2018, ICML.

Failures of model-dependent generalization bounds for least-norm interpolation pdf

Philip M. Long, Peter L. Bartlett, P. Bartlett, 2020, J. Mach. Learn. Res..

Tracking Adversarial Targets

Varun Kanade, Peter L. Bartlett, Yasin Abbasi-Yadkori, 2014, ICML.

Chapter 14 - Learning Theory

Ambuj Tewari, Peter L. Bartlett, P. Bartlett, 2014 .

Accelerated Mirror Descent in Continuous and Discrete Time

Alexandre M. Bayen, Peter L. Bartlett, Walid Krichene, 2015, NIPS.

Generalization Error of Combined Classifiers

Peter L. Bartlett, Llew Mason, Mostefa Golea, 2002, J. Comput. Syst. Sci..

Generalization in Threshold Networks , Combined Decision Trees and Combined Mask Perceptrons

P. Bartlett, L. Mason, M. Golea, 1998 .

The Pattern Classification Problem

Peter L. Bartlett, Martin Anthony, P. Bartlett, 1999 .

More theorems about scale-sensitive dimensions and learning

Philip M. Long, Peter L. Bartlett, P. Bartlett, 1995, COLT '95.

Direct Controller Adjustment by On-Line Performance Assessment

Robert R. Bitmead, Peter L. Bartlett, Leonardo C. Kammer, 1998 .

Implicit Online Learning

Peter L. Bartlett, Brian Kulis, P. Bartlett, 2010, ICML.

Sparse Greedy Gaussian Process Regression

Alexander J. Smola, Peter L. Bartlett, P. Bartlett, 2000, NIPS.

Fast-Tracking Stationary MOMDPs for Adaptive Management Problems

Peter L. Bartlett, Kai Helge Becker, Martin Péron, 2016, AAAI.

AdaBoost is Consistent

Peter L. Bartlett, Mikhail Traskin, P. Bartlett, 2006, J. Mach. Learn. Res..

Discussion of Boosting Papers

Michael I. Jordan, Jon D. McAuliffe, P. Bartlett, 2003 .

Covering numbers for real-valued function classes

Sanjeev R. Kulkarni, Peter L. Bartlett, S. E. Posner, 1997, IEEE Trans. Inf. Theory.

Oracle lower bounds for stochastic gradient sampling algorithms pdf

Philip M. Long, Peter L. Bartlett, Niladri S. Chatterji, 2020, Bernoulli.

Classification with a Reject Option using a Hinge Loss

Peter L. Bartlett, Marten H. Wegkamp, P. Bartlett, 2008, J. Mach. Learn. Res..

Bounding Embeddings of VC Classes into Maximum Classes pdf

Peter L. Bartlett, Benjamin I. P. Rubinstein, J. Hyam Rubinstein, 2014, ArXiv.

On efficient agnostic learning of linear combinations of basis functions

Peter L. Bartlett, Wee Sun Lee, Robert C. Williamson, 1995, COLT '95.

Sampling for Bayesian Mixture Models: MCMC with Polynomial-Time Mixing pdf

Martin J. Wainwright, Michael I. Jordan, Peter L. Bartlett, 2019, ArXiv.

REGAL: A Regularization based Algorithm for Reinforcement Learning in Weakly Communicating MDPs

Ambuj Tewari, Peter L. Bartlett, P. Bartlett, 2009, UAI.

Examples of learning curves from a modified VC-formalism

Peter L. Bartlett, Adam Kowalczyk, Robert C. Williamson, 1995, NIPS.

Linear Programming for Large-Scale Markov Decision Problems

Peter L. Bartlett, Yasin Abbasi-Yadkori, Alan Malek, 2014, ICML.

Prediction, Learning, Uniform Convergence, and Scale-Sensitive Dimensions

Philip M. Long, Peter L. Bartlett, P. Bartlett, 1998, J. Comput. Syst. Sci..

How to Hedge an Option Against an Adversary: Black-Scholes Pricing is Minimax Optimal

Andre Wibisono, Peter L. Bartlett, Jacob D. Abernethy, 2013, NIPS.

Bounds on Error Expectation for SVM

Bernhard Schölkopf, Alexander J. Smola, Dale Schuurmans, 2000 .

Learning with Missing Features

Peter L. Bartlett, Afshin Rostamizadeh, Alekh Agarwal, 2011, UAI.

Open problems in the security of learning

Peter L. Bartlett, Blaine Nelson, Benjamin I. P. Rubinstein, 2008, AISec '08.

Natural Regularization from Generative Models

Smola, P. Bartlett, Dale Schuurmans, 2000 .

Sharp Convergence Rates for Langevin Dynamics in the Nonconvex Setting pdf

Michael I. Jordan, Peter L. Bartlett, Yasin Abbasi-Yadkori, 2018, ArXiv.

Closing the gap between bandit and full-information online optimization : high-probability regret bound

P. Bartlett, Ambuj Tewari, A. Rakhlin, 2007 .

Model Selection and Error Estimation

Peter L. Bartlett, Gábor Lugosi, Stéphane Boucheron, 2000, Machine Learning.

The Importance of Convexity in Learning with Squared Loss

Peter L. Bartlett, Wee Sun Lee, Robert C. Williamson, 1998, IEEE Trans. Inf. Theory.

High-Probability Regret Bounds for Bandit Online Linear Optimization

Thomas P. Hayes, Ambuj Tewari, Peter L. Bartlett, 2008, COLT.

Hardness results for neural network approximation problems

P. Bartlett, S. Ben-David, 1999, Theor. Comput. Sci..

Boosting Algorithms as Gradient Descent in Function Space

Peter L. Bartlett, Marcus Frean, Llew Mason, 2007 .

Improved Generalization Through Explicit Optimization of Margins

Peter L. Bartlett, Llew Mason, Jonathan Baxter, 2000, Machine Learning.

The Canonical Distortion Measure in Feature Space and 1-NN Classification

Peter L. Bartlett, Jonathan Baxter, P. Bartlett, 1997, NIPS.

Oracle inequalities for computationally adaptive model selection pdf

Peter L. Bartlett, John C. Duchi, Alekh Agarwal, 2012, ArXiv.

FAST RATES FOR ESTIMATION ERROR AND ORACLE INEQUALITIES FOR MODEL SELECTION

P. Bartlett, 2008, Econometric Theory.

Boosting Algorithms as Gradient Descent in Function

P. Bartlett, Jonathan Baxter, Marcus Frean, 1999 .

The rademacher complexity of coregularized kernel classes

David S. Rosenberg, P. Bartlett, 2007 .

For Valid Generalization the Size of the Weights is More Important than the Size of the Network

Peter L. Bartlett, P. Bartlett, 1996, NIPS.

A framework for structural risk minimisation

John Shawe-Taylor, Peter L. Bartlett, Martin Anthony, 1996, COLT '96.

Dynamic Alignment Kernels

Bernhard Schölkopf, Alexander J. Smola, Dale Schuurmans, 2000 .

Entropy Numbers for Convex Combinations and MLPs

Smola, R. C. Williamson, P. Bartlett, 2000 .

Randomized Smoothing for Stochastic Optimization

Martin J. Wainwright, Peter L. Bartlett, John C. Duchi, 2011, SIAM J. Optim..

Fat-shattering and the learnability of real-valued functions

Philip M. Long, Peter L. Bartlett, Robert C. Williamson, 1994, COLT '94.

Covering numbers for support vector machines

John Shawe-Taylor, Peter L. Bartlett, Ying Guo, 1999, COLT '99.

Derivative-Free Methods for Policy Optimization: Guarantees for Linear Quadratic Systems

Martin J. Wainwright, Dhruv Malik, Peter L. Bartlett, 2018, AISTATS.

Efficient Minimax Strategies for Square Loss Games

Wouter M. Koolen, Peter L. Bartlett, Alan Malek, 2014, NIPS.

Linear Discriminant and Support Vector Classifiers

P. Bartlett, Dale Schuurmans, B. Schölkopf, 2000 .

Hebbian Synaptic Modifications in Spiking Neurons that Learn pdf

Peter L. Bartlett, Jonathan Baxter, P. Bartlett, 2019, ArXiv.

Information-Theoretic Lower Bounds on the Oracle Complexity of Stochastic Convex Optimization

Martin J. Wainwright, Pradeep Ravikumar, Peter L. Bartlett, 2010, IEEE Transactions on Information Theory.

Learning the Kernel Matrix with Semidefinite Programming

Nello Cristianini, Michael I. Jordan, Peter L. Bartlett, 2002, J. Mach. Learn. Res..

Function Learning from Interpolation

Peter L. Bartlett, Martin Anthony, P. Bartlett, 1995, Combinatorics, Probability and Computing.

On the Consistency of Multiclass Classification Methods

Ambuj Tewari, Peter L. Bartlett, P. Bartlett, 2007, J. Mach. Learn. Res..

A Stochastic View of Optimal Regret through Minimax Duality pdf

Peter L. Bartlett, Alekh Agarwal, Jacob D. Abernethy, 2009, COLT.

Localized Rademacher Complexities

Peter L. Bartlett, Shahar Mendelson, Olivier Bousquet, 2002, COLT.

Exponentiated Gradient Algorithms for Conditional Random Fields and Max-Margin Markov Networks

Peter L. Bartlett, Xavier Carreras, Michael Collins, 2008, J. Mach. Learn. Res..

ℓ1-regularized linear regression: persistence and oracle inequalities

P. Bartlett, S. Mendelson, Joe Neeman, 2012 .

New Support Vector Algorithms

Bernhard Schölkopf, Alex J Smola, Robert C Williamson, 2000, Neural Computation.

Support vector regression with automatic accuracy control.

R. C. Williamson, Alexander J. Smola, P. Bartlett, 1998 .

The Interplay Between Implicit Bias and Benign Overfitting in Two-Layer Linear Networks pdf

Philip M. Long, Peter L. Bartlett, Niladri S. Chatterji, 2021, ArXiv.

Advances in Large Margin Classifiers

Alexander J. Smola, Peter Bartlett, P. Bartlett, 2000 .

Gaussian Processes and SVM: Mean Field and Leave-One-Out

P. Bartlett, Dale Schuurmans, B. Schölkopf, 2000 .

Functional Gradient Techniques for Combining Hypotheses

Peter L. Bartlett, Marcus Frean, Llew Mason, 2000 .

Byzantine-Robust Distributed Learning: Towards Optimal Statistical Rates pdf

Kannan Ramchandran, Yudong Chen, Dong Yin, 2018, ICML.

Generalization in Decision Trees and DNF: Does Size Matter?

Peter L. Bartlett, Wee Sun Lee, Llew Mason, 1997, NIPS.

Rademacher Complexity for Adversarially Robust Generalization

Kannan Ramchandran, Dong Yin, Peter L. Bartlett, 2018, ICML.

Sample Complexity of Policy Search with Known Dynamics

Ambuj Tewari, Peter L. Bartlett, P. Bartlett, 2006, NIPS.

Randomized smoothing for (parallel) stochastic optimization

Martin J. Wainwright, Peter L. Bartlett, John C. Duchi, 2012, 2012 IEEE 51st IEEE Conference on Decision and Control (CDC).

Blackwell Approachability and No-Regret Learning are Equivalent pdf

Peter L. Bartlett, Elad Hazan, Jacob D. Abernethy, 2010, COLT.

Shifting: One-inclusion mistake bounds and sample compression

Peter L. Bartlett, Benjamin I. P. Rubinstein, J. Hyam Rubinstein, 2009, J. Comput. Syst. Sci..

Optimal Allocation Strategies for the Dark Pool Problem

Peter L. Bartlett, Alekh Agarwal, Max Dama, 2010, AISTATS.

Margin-adaptive model selection in statistical learning

P. Bartlett, Sylvain Arlot, 2008, 0804.2937.

Multitask Learning with Expert Advice

Peter L. Bartlett, Jacob D. Abernethy, Alexander Rakhlin, 2007, COLT.

Vapnik-Chervonenkis dimension of neural nets

Peter L. Bartlett, Wolfgang Maass, P. Bartlett, 2003 .

Gradient Diversity Empowers Distributed Learning pdf

Dimitris S. Papailiopoulos, Kannan Ramchandran, Ashwin Pananjady, 2017, ArXiv.

Exponentiated Gradient Algorithms for Large-margin Structured Classification

Ben Taskar, Peter L. Bartlett, Michael Collins, 2004, NIPS.

Benign overfitting in linear regression

Philip M. Long, Peter L. Bartlett, Alexander Tsigler, 2019, Proceedings of the National Academy of Sciences.

A Diffusion Process Perspective on Posterior Contraction Rates for Parameters

Michael I. Jordan, P. Bartlett, M. Wainwright, 2019, 1909.00966.

On Thompson Sampling with Langevin Algorithms pdf

Michael I. Jordan, Peter L. Bartlett, Aldo Pacchiano, 2020, ICML 2020.

High-Order Langevin Diffusion Yields an Accelerated MCMC Algorithm pdf

Martin J. Wainwright, Michael I. Jordan, Peter L. Bartlett, 2019, J. Mach. Learn. Res..

Optimal controller properties from closed-loop experiments

Leonardo C. Kammer, Robert R. Bitmead, Peter L. Bartlett, 1998, Autom..

Local Rademacher Complexities and Empirical Minimization

P. Bartlett, 2006 .

Direct iterative tuning via spectral analysis

P. Bartlett, R. Bitmead, L. Kammer, 1998, Proceedings of the 37th IEEE Conference on Decision and Control (Cat. No.98CH36171).

Is There an Analog of Nesterov Acceleration for MCMC? pdf

Michael I. Jordan, Yi-An Ma, Xiang Cheng, 2019, ArXiv.

GACV for Support Vector Machines

Bernhard Schölkopf, Alexander J. Smola, Dale Schuurmans, 2000 .

Near Minimax Optimal Players for the Finite-Time 3-Expert Prediction Problem

Peter L. Bartlett, Yasin Abbasi-Yadkori, Victor Gabillon, 2017, NIPS.

Two Approximate Dynamic Programming Algorithms for Managing Complete SIS Networks

Peter L. Bartlett, Kai Helge Becker, Martin Péron, 2018, COMPASS.

Alternating minimization for dictionary learning with random initialization

Peter L. Bartlett, Niladri S. Chatterji, P. Bartlett, 2017, NIPS.

Valid Generalisation from Approximate Interpolation

Yuval Ishai, John Shawe-Taylor, Peter L. Bartlett, 1996, Combinatorics, Probability and Computing.

Application of machine learning in the fault diagnostics of air handling units

David M. Auslander, Philip Haves, Michael D. Sohn, 2012 .

A Learning-Based Approach to Reactive Security

Dawn Xiaodong Song, John C. Mitchell, Peter L. Bartlett, 2009, IEEE Transactions on Dependable and Secure Computing.

Large margin methods for structured classification : Exponentiated gradient algorithms and PAC-Bayesian generalization bounds

Ben Taskar, Peter L. Bartlett, Michael Collins, 2004 .

Underdamped Langevin MCMC: A non-asymptotic analysis pdf

Michael I. Jordan, Peter L. Bartlett, Xiang Cheng, 2017, COLT.

An Efficient Sampling Algorithm for Non-smooth Composite Potentials pdf

Martin J. Wainwright, Peter L. Bartlett, Nicolas Flammarion, 2019, J. Mach. Learn. Res..

Large Margin Classifiers: Convex Loss, Low Noise, and Convergence Rates

Michael I. Jordan, Peter L. Bartlett, Jon D. McAuliffe, 2003, NIPS.

Minimax Time Series Prediction

Wouter M. Koolen, Peter L. Bartlett, Yasin Abbasi-Yadkori, 2015, NIPS.

Langevin Monte Carlo without Smoothness

Michael I. Jordan, Peter L. Bartlett, Jelena Diakonikolas, 2019, AISTATS.

Gradient Descent with Identity Initialization Efficiently Learns Positive-Definite Linear Transformations by Deep Residual Networks

Philip M. Long, Peter L. Bartlett, David P. Helmbold, 2018, Neural Computation.

Gradient descent efficiently learns positive definite deep linear residual networks

Philip M. Long, P. Bartlett, D. Helmbold, 2018 .

A simple parameter-free and adaptive approach to optimization under a minimal local smoothness assumption pdf

Peter L. Bartlett, Michal Valko, Victor Gabillon, 2018, ALT.

On Linear Stochastic Approximation: Fine-grained Polyak-Ruppert and Non-Asymptotic Concentration pdf

Martin J. Wainwright, Michael I. Jordan, Peter L. Bartlett, 2020, COLT.

Sparseness vs Estimating Conditional Probabilities: Some Asymptotic Results

Ambuj Tewari, Peter L. Bartlett, P. Bartlett, 2007, J. Mach. Learn. Res..

Acceleration and Averaging in Stochastic Descent Dynamics

Peter L. Bartlett, Walid Krichene, P. Bartlett, 2017, NIPS.

Exponential convergence of a gradient descent algorithm for a class of recurrent neural networks

P. Bartlett, S. Dasgupta, 1995, 38th Midwest Symposium on Circuits and Systems. Proceedings.

Testing Markov Chains without Hitting pdf

Peter L. Bartlett, Yeshwanth Cherapanamjeri, P. Bartlett, 2019, ArXiv.

Quantitative W1 Convergence of Langevin-Like Stochastic Processes with Non-Convex Potential State-Dependent Noise pdf

Michael I. Jordan, Peter L. Bartlett, Dong Yin, 2019, ArXiv.

Beyond the Margin

Bernhard Schölkopf, Alexander J. Smola, Dale Schuurmans, 2000 .

Exploiting Random Walks for Learning

Peter L. Bartlett, Klaus-Uwe Höffgen, Paul Fischer, 2002, Inf. Comput..

Shrinking the Tube: A New Support Vector Regression Algorithm

Bernhard Schölkopf, Alexander J. Smola, Peter L. Bartlett, 1998, NIPS.

A Unifying View of Multiple Kernel Learning

Peter L. Bartlett, Marius Kloft, Ulrich Rückert, 2010, ECML/PKDD.

Hit-and-Run for Sampling and Planning in Non-Convex Spaces pdf

Peter L. Bartlett, Yasin Abbasi-Yadkori, Alan Malek, 2016, AISTATS.

Bayesian Robustness: A Nonasymptotic Viewpoint pdf

Anca D. Dragan, Michael I. Jordan, Peter L. Bartlett, 2019, Journal of the American Statistical Association.

Horizon-Independent Optimal Prediction with Log-Loss in Exponential Families

Peter L. Bartlett, Wojciech Kotlowski, Fares Hedayati, 2013, COLT.

Testing Symmetric Markov Chains Without Hitting

Peter L. Bartlett, Yeshwanth Cherapanamjeri, P. Bartlett, 2019, COLT.

Direct iterative tuning via spectral analysis

Robert R. Bitmead, Leonardo C. Kammer, Peter L. Bartlett, 2000, Autom..

Splines, Rational Functions and Neural Networks

Peter L. Bartlett, Robert C. Williamson, R. C. Williamson, 1991, NIPS.

Semi-supervised learning with multiple views

David S. Rosenberg, P. Bartlett, 2008 .

A Kernel for Semi-Supervised Learning With MultiView Point Cloud Regularization

David S. Rosenberg, P. Bartlett, P. Niyogi, 2009 .

Adaptive Margin Support Vector Machines

Alexander J. Smola, Dale Schuurmans, Bernhard Schölkopf, 2000 .

Learning a System-ID Embedding Space for Domain Specialization with Deep Reinforcement Learning

Razvan Pascanu, Peter L. Bartlett, Pieter Abbeel, 2018 .

Rademacher Complexity for Adversarially Robust Generalization Supplementary Material

P. Bartlett, K. Ramchandran, Dong Yin, 2019 .

A Framework for Structural Risk Minimisation Produced as Part of the Esprit Working Group in Neural and Computational Learning, Neurocolt 8556

P. Bartlett, R. Holloway, 1996 .

Safe Machine Learning ( October 19-20 , 2017 ) DARPA workshop at the Simons Institute Organizers :

P. Bartlett, D. Song, S. Goldwasser, 2018 .

Advances in Large Margin Classiiers Library of Congress Cataloging-in-publication Data Advances in Large Margin Classiiers / Edited Includes Bibliographical References and Index. Isbn 0-xxx-xxxxx-x (alk. Paper) 1. Machine Learning. 2. Algorithms. 3. Kernel Functions

P. Bartlett, Dale Schuurmans, Alex Smola, 1999 .

Alternating minimization for dictionary learning: Local Convergence Guarantees

Niladri S. Chatterji, P. Bartlett, 2017 .

Multi-View Point Cloud Kernels for Semi-Supervised Learning

David S. Rosenberg, P. Bartlett, P. Niyogi, 2009 .

Comment on "Support Vector Machines with Applications"

Michael I. Jordan, Jon D. McAuliffe, P. Bartlett, 2006, math/0612821.

Learning in a Large Function Space: Privacy-Preserving Mechanisms for SVM Learning pdf

Ling Huang, Peter L. Bartlett, Benjamin I. P. Rubinstein, 2009, J. Priv. Confidentiality.

The complexity of model classes, and smoothing noisy data 1 1 An earlier version of this paper was p

P. Bartlett, S. Kulkarni, 1998 .

The complexity of model classes and smoothing noisy data

P. Bartlett, S. Kulkarni, 1996, Proceedings of 35th IEEE Conference on Decision and Control.

2 7 Ju l 2 01 9 Bayesian Robustness : A Nonasymptotic Viewpoint

Michael I. Jordan, P. Bartlett, K. Bhatia, 2019 .

RobULA: Efficient Sampling for Robust Bayesian Inference

Michael I. Jordan, P. Bartlett, A. Dragan, 2019 .

Author and Co-author Contact Information

P. Bartlett, Ambuj Tewari, 2013 .

Stochastic Gradient and Langevin Processes

Michael I. Jordan, P. Bartlett, Xiang Cheng, 2019, ICML.

Efficient neural network learning

P. Bartlett, 1999 .

Learning Hedonic Games

P. Bartlett, M. Anthony, M. Anthony, 2017 .

Prediction Algorithms: Complexity, Concentration and Convexity

Peter L. Bartlett, P. Bartlett, 2003 .

Convergence Rates for Langevin Monte Carlo in the Nonconvex Setting

Michael I. Jordan, Niladri S. Chatterji, P. Bartlett, 2020 .

Social Influence Based Clustering of Heterogeneous Information Networks

Andrei Broder, Christos Faloutsos, Jiawei Han, 2013 .

Acceleration and Averaging in Stochastic Mirror Descent Dynamics

Peter L. Bartlett, Walid Krichene, P. Bartlett, 2017, 1707.06219.

Function Learning from Interpolation 1 Produced as Part of the Esprit Working Group in Neural and Computational Learning, Neurocolt 8556

P. Bartlett, 1994 .

Signal-based testing of LQ-optimality of controllers

P. Bartlett, R. Bitmead, L. Kammer, 1996, Proceedings of 35th IEEE Conference on Decision and Control.

Sample Complexity versus Approximation Error

R. C. Williamson, P. Bartlett, 2005 .

Online Prediction

P. Bartlett, 2011 .

Quantitative Weak Convergence for Discrete Stochastic Processes

Michael I. Jordan, P. Bartlett, Xiang Cheng, 2019 .

Book Review: Neural Networks for Pattern Recognition. Christopher M. Bishop, Oxford University Press, New York, 1995. No. of pages: xvii+512. Price: £55. ISBN 0‐19‐853864‐2

Peter L. Bartlett, P. Bartlett, 1997 .

Direct Gradient-Based Reinforcement Learning: II. Gradient Ascent Algorithms and Experiments

P. Bartlett, Jonathan Baxter, Lex Weaver, 1999 .

Proceedings of the Eleventh Annual Conference on Computational Learning Theory, COLT 1998, Madison, Wisconsin, USA, July 24-26, 1998

Yishay Mansour, Peter L. Bartlett, Y. Mansour, 1998, COLT.

Neural Network Learning: The Dimensions of Neural Networks

Peter L. Bartlett, Martin Anthony, P. Bartlett, 1999 .

Neural Network Learning: Efficient Learning

Peter L. Bartlett, Martin Anthony, P. Bartlett, 1999 .

Constructive Learning Algorithms for Two-Layer Networks

Peter L. Bartlett, Martin Anthony, P. Bartlett, 1999 .

Neural Network Learning: Other Learning Problems

Peter L. Bartlett, Martin Anthony, P. Bartlett, 1999 .

Greedy Convex Ensemble

Peter L. Bartlett, Nan Ye, Thanh Tan Nguyen, 2020, IJCAI.

Learning as Optimization

Peter L. Bartlett, Martin Anthony, P. Bartlett, 1999 .

Introduction to the special issue on learning theory

Peter L. Bartlett, M. Vidyasagar, P. Bartlett, 1998 .

nostic Learnin ral

Peter L. Bartlett, Wee Sun Lee, Robert C. Williamson, 1996 .

Proceedings of the Nineteenth International Conference on Artificial Intelligence and Statistics, AISTATS 2016

Peter L. Bartlett, Alessandro Lazaric, Ronald Ortner, 2016 .

The Boolean Perceptron

Peter L. Bartlett, Martin Anthony, P. Bartlett, 1999 .

Fat-shattering and the learnability of real-valued functions

Philip M. Long, Peter L. Bartlett, Robert C. Williamson, 1994, COLT '94.

Computational learning theory and neural network learning

Peter L. Bartlett, P. Bartlett, 1992 .

On Approximate Thompson Sampling with Langevin Algorithms

Michael I. Jordan, Peter L. Bartlett, Yi-An Ma, 2020, ICML.

Neural Network Learning: Vapnik-Chervonenkis Dimension Bounds for Neural Networks

Peter L. Bartlett, Martin Anthony, P. Bartlett, 1999 .

Neural Network Learning: Preface

Peter L. Bartlett, Martin Anthony, P. Bartlett, 1999 .

Discussion of "2004 IMS Medallion Lecture: Local Rademacher complexities and oracle inequalities in risk minimization" by V. Koltchinskii

P. Bartlett, S. Mendelson, Peter L. Bartlett, 2007, 0708.0094.

Generalization Performance of Support Vector Machines and Other Pattern Classifiers

John Shawe-Taylor, Peter L. Bartlett, P. Bartlett, 1999 .

Some kernels for structured data

Bernhard Schölkopf, Peter L. Bartlett, P. Bartlett, 2001 .

Large Margin Bank Boundaries for Ordinal Regression

Bernhard Schölkopf, Alexander J. Smola, Dale Schuurmans, 2000 .

An Instance-Dependent Analysis for the Cooperative Multi-Player Multi-Armed Bandit pdf

Michael I. Jordan, Aldo Pacchiano, Peter Bartlett, 2021, ArXiv.

The Optimality of Jereys Prior for Online Density Estimation and the Asymptotic Normality of Maximum

P. Bartlett, F. Hedayati, 2012 .

Discussions of boosting papers, and rejoinders

Trevor Hastie, Peter J. Bickel, Robert Tibshirani, 2004 .

Local Rademacher complexities and oracle inequalities in risk minimization

Peter L. Bartlett, Shahar Mendelson, P. Bartlett, 2006 .

Fast Rates of Uniform Convergence and Oracle Inequalities for Model Selection

P. Bartlett, 2022 .

Pattern Classification with Real-Output Networks

Martin Anthony, Peter L. Bartlett, P. Bartlett, 1999 .

Learning Classes of Real Functions

Martin Anthony, Peter L. Bartlett, P. Bartlett, 1999 .

Classification with Real-Valued Functions

Martin Anthony, Peter L. Bartlett, P. Bartlett, 1999 .

Tracking Adaptive Identification: Approach Via Model Falsification

P. Bartlett, R. Bitmead, L. Kammer, 1996 .

Local Rademacher complexities

P. Bartlett, O. Bousquet, S. Mendelson, 2005, math/0508275.

Local Rademacher complexities and oracle inequalities in risk minimization

P. Bartlett, S. Mendelson, 2006 .

Direct Gradient-Based Reinforcement Learning: I. Gradient Estimation Algorithms

P. Bartlett, Jonathan Baxter, 1999 .

A Diffusion Process Perspective on Posterior Contraction Rates for Parameters

Michael I. Jordan, P. Bartlett, M. Wainwright, 2019, SIAM J. Math. Data Sci..

A Learning-Based Approach to Reactive Security

John C. Mitchell, Benjamin I. P. Rubinstein, P. Bartlett, 2009, IEEE Transactions on Dependable and Secure Computing.

Local Rademacher complexities

P. Bartlett, O. Bousquet, S. Mendelson, 2005, math/0508275.

Gen-Oja: A Two-time-scale approach for Streaming CCA

Michael I. Jordan, P. Bartlett, Nicolas Flammarion, 2018, 1811.08393.

Approximate and Stochastic Greedy Optimization

P. Bartlett, N. Ye, 2017, ArXiv.

Off-policy estimation of linear functionals: Non-asymptotic theory for semi-parametric efficiency

P. Bartlett, M. Wainwright, Wenlong Mou, 2022, ArXiv.

Benign Overfitting without Linearity: Neural Network Classifiers Trained by Gradient Descent for Noisy Linear Data

Niladri S. Chatterji, P. Bartlett, Spencer Frei, 2022, COLT.

The Dynamics of Sharpness-Aware Minimization: Bouncing Across Ravines and Drifting Towards Wide Minima

Philip M. Long, P. Bartlett, O. Bousquet, 2022, ArXiv.

On the Theory of Reinforcement Learning with Once-per-Episode Feedback

Michael I. Jordan, Niladri S. Chatterji, P. Bartlett, 2021, NeurIPS.

Implicit Bias in Leaky ReLU Networks Trained on High-Dimensional Data

P. Bartlett, Nathan Srebro, Wei Hu, 2022, ICLR.

Joint Representation Training in Sequential Tasks with Shared Structure

P. Bartlett, Ofir Nachum, Aldo Pacchiano, 2022, ArXiv.

Pattern Classification with Binary-Output Neural Networks

Martin Anthony, Peter L. Bartlett, P. Bartlett, 1999 .

Optimal variance-reduced stochastic approximation in Banach spaces

Michael I. Jordan, P. Bartlett, M. Wainwright, 2022, ArXiv.

ℓ1-regularized linear regression: persistence and oracle inequalities

P. Bartlett, S. Mendelson, Joe Neeman, 2011, Probability Theory and Related Fields.

Benign overfitting in ridge regression

P. Bartlett, Alexander Tsigler, 2020, J. Mach. Learn. Res..

Generalization Bounds for Data-Driven Numerical Linear Algebra

P. Bartlett, P. Indyk, Tal Wagner, 2022, COLT.

The Interplay Between Implicit Bias and Benign Overfitting in Two-Layer Linear Networks

Philip M. Long, Niladri S. Chatterji, P. Bartlett, 2021, J. Mach. Learn. Res..

Random Feature Amplification: Feature Learning and Generalization in Neural Networks

Niladri S. Chatterji, P. Bartlett, Spencer Frei, 2022, ArXiv.

Covering Numbers and Support Vector Machines

Ying Guo, Peter L. Bartlett, John Shawe-Taylor, 2002 .

Kernel-based off-policy estimation without overlap: Instance optimality beyond semiparametric efficiency

P. Bartlett, M. Wainwright, Wenlong Mou, 2023, 2301.06240.

Robust Ensemble Learning

Gunnar Rätsch, Bernhard Schölkopf, Dale Schuurmans, 2000 .

Oracle lower bounds for stochastic gradient sampling algorithms

Philip M. Long, Niladri S. Chatterji, P. Bartlett, 2020, Bernoulli.

Is there an analog of Nesterov acceleration for gradient-based MCMC?

Michael I. Jordan, Niladri S. Chatterji, MA YI-AN, 2021 .

FLAG n' FLARE: Fast Linearly-Coupled Adaptive Gradient Methods

Peter L. Bartlett, Michael W. Mahoney, Fred Roosta, 2016, AISTATS.

A ug 2 01 2 Oracle inequalities for computationally adaptive model selection

John C. Duchi, P. Bartlett, Alekh Agarwal, 2012 .

Self-Distillation Amplifies Regularization in Hilbert Space pdf

Hossein Mobahi, Peter L. Bartlett, Mehrdad Farajtabar, 2020, NeurIPS.

Bounded Parameter Markov Decision Processes with Average Reward Criterion

Ambuj Tewari, Peter L. Bartlett, P. Bartlett, 2007, COLT.

Convergence of Langevin MCMC in KL-divergence

Peter L. Bartlett, Xiang Cheng, P. Bartlett, 2017, ALT.

Representing smooth functions as compositions of near-identity functions with implications for deep network optimization pdf

Philip M. Long, Peter L. Bartlett, Steven N. Evans, 2018, ArXiv.

Preference learning along multiple criteria: A game-theoretic perspective

Martin Wainwright, Ashwin Pananjady, Kush Bhatia, 2021, NeurIPS.

Failures of model-dependent generalization bounds for least-norm interpolation

Philip M. Long, P. Bartlett, 2020, Journal of machine learning research.

Deep learning: a statistical viewpoint

Andrea Montanari, Peter L. Bartlett, Alexander Rakhlin, 2021, Acta Numerica.

Reinforcement learning in large or unknown mdps

Ambuj Tewari, Peter L. Bartlett, P. Bartlett, 2007 .

Nearly-tight VC-dimension and Pseudodimension Bounds for Piecewise Linear Neural Networks

Peter L. Bartlett, Abbas Mehrabian, Christopher Liaw, 2017, J. Mach. Learn. Res..

Shifting, One-Inclusion Mistake Bounds and Tight Multiclass Expected Risk Bounds

Peter L. Bartlett, Benjamin I. P. Rubinstein, J. Hyam Rubinstein, 2006, NIPS.

Benign Overfitting in Linear Classifiers and Leaky ReLU Networks from KKT Conditions for Margin Maximization

P. Bartlett, Nathan Srebro, Gal Vardi, 2023, COLT.

The Double-Edged Sword of Implicit Bias: Generalization vs. Robustness in ReLU Networks

P. Bartlett, Nathan Srebro, Gal Vardi, 2023, ArXiv.

Agnostic Learning with Unknown Utilities pdf

Anca D. Dragan, Peter L. Bartlett, Kush Bhatia, 2021, ITCS.

Adversarial Examples in Multi-Layer Random ReLU Networks pdf

Peter L. Bartlett, Yeshwanth Cherapanamjeri, S'ebastien Bubeck, 2021, NeurIPS.

Defending Against Saddle Point Attack in Byzantine-Robust Distributed Learning

Kannan Ramchandran, Yudong Chen, Dong Yin, 2018, ICML.

Infinite-Horizon Offline Reinforcement Learning with Linear Function Approximation: Curse of Dimensionality and Algorithm

P. Bartlett, B. Scherrer, Lin Chen, 2021, ArXiv.

Online learning with kernel losses

Peter L. Bartlett, Aldo Pacchiano, Niladri S. Chatterji, 2018, ICML.

Gradient Diversity: a Key Ingredient for Scalable Distributed Learning

Dimitris S. Papailiopoulos, Kannan Ramchandran, Ashwin Pananjady, 2017, AISTATS.

Oracle inequalities for computationally budgeted model selection

Peter L. Bartlett, John C. Duchi, Alekh Agarwal, 2011, COLT.

Information-theoretic lower bounds on the oracle complexity of convex optimization

Martin J. Wainwright, Pradeep Ravikumar, Peter L. Bartlett, 2009, NIPS.

Investigating the distribution assumptions in the Pac learning model

Peter L. Bartlett, Robert C. Williamson, R. C. Williamson, 1991, COLT '91.

Recovery Guarantees for One-hidden-layer Neural Networks

Inderjit S. Dhillon, Prateek Jain, Peter L. Bartlett, 2017, ICML.

Learning with a slowly changing distribution

Peter L. Bartlett, P. Bartlett, 1992, COLT '92.

Self-Distillation Amplifies Regularization in Hilbert Space pdf

Hossein Mobahi, Peter L. Bartlett, Mehrdad Farajtabar, 2020, NeurIPS.

Multiview point cloud kernels for semisupervised learning [Lecture Notes]

David S. Rosenberg, P. Niyogi, D. Rosenberg, 2009, IEEE Signal Processing Magazine.

Multiview point cloud kernels for semisupervised learning

Partha Niyogi, Peter L. Bartlett, Vikas Sindhwani, 2009 .

POLITEX: Regret Bounds for Policy Iteration using Expert Prediction

Peter L. Bartlett, Nevena Lazic, Csaba Szepesvári, 2019, ICML.

The Dynamics of Sharpness-Aware Minimization: Bouncing Across Ravines and Drifting Towards Wide Minima

Philip M. Long, P. Bartlett, O. Bousquet, 2022, ArXiv.

Parallelizing Contextual Linear Bandits pdf

Michael I. Jordan, Nilesh Tripuraneni, Aldo Pacchiano, 2021, ArXiv.

Accelerated Message Passing for Entropy-Regularized MAP Inference pdf

Michael I. Jordan, Aldo Pacchiano, Peter Bartlett, 2020, ICML.

Improved bounds for discretization of Langevin diffusions: Near-optimal rates without convexity

Martin J. Wainwright, Peter L. Bartlett, Nicolas Flammarion, 2019, Bernoulli.

Application of machine learning in fault diagnostics of mechanical systems

Philip Haves, Peter L. Bartlett, David M. Auslander, 2008, WCE 2008.

Regret Bound Balancing and Elimination for Model Selection in Bandits and RL pdf

Claudio Gentile, Christoph Dann, Aldo Pacchiano, 2020, ArXiv.

Dropout: Explicit Forms and Capacity Control pdf

Nathan Srebro, Raman Arora, Peter Bartlett, 2020, ICML.

Drilling Results in Ice-bound Simulated Lunar Regolith (FJS-1) as Part of the Construction and Resource Utilization Explorer Project (CRUX)

Peter L. Bartlett, Kiel Davis, Kris A. Zacny, 2006 .

Optimal Sample-Based Estimates of the Expectation of the Empirical Minimizer

Peter L. Bartlett, Shahar Mendelson, Petra Philips, 2005 .

When does gradient descent with logistic loss interpolate using deep networks with smoothed ReLU activations?

Philip M. Long, Peter L. Bartlett, Niladri S. Chatterji, 2021, COLT.

When does gradient descent with logistic loss find interpolating two-layer networks? pdf

Philip M. Long, Peter L. Bartlett, Niladri S. Chatterji, 2020, J. Mach. Learn. Res..

A Sharp Characterization of Linear Estimators for Offline Policy Evaluation

Juan C. Perdomo, S. Kakade, P. Bartlett, 2022, ArXiv.

OSOM: A Simultaneously Optimal Algorithm for Multi-Armed and Linear Contextual Bandits

Peter L. Bartlett, Niladri S. Chatterji, Vidya Muthukumar, 2019, AISTATS.

Stochastic Bandits with Linear Constraints pdf

Mohammad Ghavamzadeh, Aldo Pacchiano, Heinrich Jiang, 2020, AISTATS.

A Regularization Approach to Metrical Task Systems

Peter L. Bartlett, Niv Buchbinder, Isabelle Stanton, 2010, ALT.

Trained Transformers Learn Linear Models In-Context

P. Bartlett, Spencer Frei, Ruiqi Zhang, 2023, ArXiv.

Trained Transformers Learn Linear Models In-Context

P. Bartlett, Spencer Frei, Ruiqi Zhang, 2023, ArXiv.

Prediction with Limited Advice and Multiarmed Bandits with Paid Observations

Koby Crammer, Peter L. Bartlett, Yasin Abbasi-Yadkori, 2014, ICML.

Large-Margin Convex Polytope Machine

Ling Huang, Michael Carl Tschantz, Peter L. Bartlett, 2014, NIPS.

Optimal and instance-dependent guarantees for Markovian linear stochastic approximation pdf

Martin J. Wainwright, Peter L. Bartlett, Ashwin Pananjady, 2021, COLT.

Lower bounds on the VC-dimension of smoothly parametrized function classes

Wee Sun Lee, R. C. Williamson, P. Bartlett, 1994, COLT '94.

Best of both worlds: Stochastic & adversarial best-arm identification

Peter L. Bartlett, Michal Valko, Yasin Abbasi-Yadkori, 2018, COLT.

Gen-Oja: Simple & Efficient Algorithm for Streaming Generalized Eigenvector Computation

Michael I. Jordan, Peter L. Bartlett, Aldo Pacchiano, 2018, NeurIPS.

RL: FAST REINFORCEMENT LEARNING VIA SLOW REINFORCEMENT LEARNING

J. Schulman, P. Abbeel, P. Bartlett, 2016 .

Open Problem: Adversarial Multiarmed Bandits with Limited Advice

Koby Crammer, Peter L. Bartlett, Yevgeny Seldin, 2013, COLT.

Near Optimal Policy Optimization via REPS pdf

Ofir Nachum, Aldo Pacchiano, Jonathan Lee, 2021, NeurIPS.

Online Learning in Markov Decision Processes with Adversarially Chosen Transition Probability Distributions

Peter L. Bartlett, Yasin Abbasi-Yadkori, Csaba Szepesvari, 2013, NIPS.

Greedy Convex Ensemble

P. Bartlett, N. Ye, Thanh Tan Nguyen, 2019, IJCAI.

Scale-free adaptive planning for deterministic dynamics & discounted rewards

Jennifer Healey, Michal Valko, Victor Gabillon, 2019, ICML.

Large-Scale Markov Decision Problems via the Linear Programming Dual pdf

Xi Chen, Peter L. Bartlett, Yasin Abbasi-Yadkori, 2019, ArXiv.

Generalization Performance of Support Vector Machines and Other Pattern Classifiers

P. Bartlett, J. Shawe-Taylor, auJohn Shawe-TaylorRoyal Holloway, 1999 .

Benign Overfitting without Linearity: Neural Network Classifiers Trained by Gradient Descent for Noisy Linear Data

Niladri S. Chatterji, P. Bartlett, Spencer Frei, 2022, COLT.

Benign overfitting in linear regression

Philip M. Long, P. Bartlett, G. Lugosi, 2019, Proceedings of the National Academy of Sciences.

New Support Vector Algorithms

R. C. Williamson, P. Bartlett, Alex Smola, 2000, Neural Computation.

Vapnik-Chervonenkis Dimension Bounds for Two- and Three-Layer Networks

Peter L. Bartlett, P. Bartlett, 1993, Neural Computation.

Best of many worlds: Robust model selection for online supervised learning pdf

Anant Sahai, Vidya Muthukumar, Mitas Ray, 2018, AISTATS.

Advice-Efficient Prediction with Expert Advice pdf

Koby Crammer, Peter L. Bartlett, Yevgeny Seldin, 2013, ArXiv.

The Optimality of Jeffreys Prior for Online Density Estimation and the Asymptotic Normality of Maximum Likelihood Estimators

P. Bartlett, Fares Hedayati, 2012, COLT.

Matrix regularization techniques for online multitask learning

Peter L. Bartlett, Alekh Agarwal, Alexander Rakhlin, 2008 .

Online discovery of similarity mappings

Peter L. Bartlett, Jacob D. Abernethy, Alexander Rakhlin, 2007, ICML '07.

Trained Transformers Learn Linear Models In-Context

P. Bartlett, Spencer Frei, Ruiqi Zhang, 2023, ArXiv.

Random Feature Amplification: Feature Learning and Generalization in Neural Networks

Niladri S. Chatterji, P. Bartlett, Spencer Frei, 2022, ArXiv.

A Minimax Lower Bound for Empirical Quantizer Design

Tamás Linder, Peter L. Bartlett, Gábor Lugosi, 1997, EuroCOLT.

Sparseness vs Estimating Conditional Probabilities: Some Asymptotic Results

P. Bartlett, Ambuj Tewari, 2007, J. Mach. Learn. Res..

Defending Against Saddle Point Attack in Byzantine-Robust Distributed Learning

P. Bartlett, K. Ramchandran, Yudong Chen, 2018, ICML.

Gradient Diversity Empowers Distributed Learning

Dimitris S. Papailiopoulos, Kannan Ramchandran, Peter L. Bartlett, 2017, ArXiv.

Accelerated Mirror Descent in Continuous and Discrete Time

P. Bartlett, A. Bayen, Walid Krichene, 2015, NIPS.

FLAG: Fast Linearly-Coupled Adaptive Gradient Method pdf

Peter L. Bartlett, Michael W. Mahoney, Farbod Roosta-Khorasani, 2016, ArXiv.

Hebbian Synaptic Modifications in Spiking Neurons that Learn

P. Bartlett, Jonathan Baxter, 2019, ArXiv.

Large Margin Classifiers: Convex Loss, Low Noise, and Convergence Rates

Michael I. Jordan, Jon D. McAuliffe, P. Bartlett, 2003, NIPS.

Online and Batch Learning Algorithms for Data with Missing Features

P. Bartlett, Afshin Rostamizadeh, Alekh Agarwal, 2011, ArXiv.