Manfred K. Warmuth

发表

Online PCA with Optimal Regrets

Jiazhong Nie, Wojciech Kotlowski, Manfred K. Warmuth, 2013, ALT.

Matrix Exponentiated Gradient Updates for On-line Learning and Bregman Projection

Gunnar Rätsch, Manfred K. Warmuth, Koji Tsuda, 2004, J. Mach. Learn. Res..

Direct and indirect algorithms for on-line learning of disjunctions

Manfred K. Warmuth, David P. Helmbold, Sandra Panizza, 2002, Theor. Comput. Sci..

Entropy regularised LPboost

Sundar Vishwanathan, Manfred K. Warmuth, Karen A. Glocer, 2008 .

Exponentially many local minima for single neurons

Peter Auer, Mark Herbster, Manfred K. Warmuth, 1995, NIPS.

Direct and Indirect Algorithms for On-line Learning of Disjunctions

Manfred K. Warmuth, David P. Helmbold, Sandra Panizza, 1999, EuroCOLT.

Applications of Scheduling Theory to Formal Language Theory

Jakob Gonczarowski, Manfred K. Warmuth, 1985, Theor. Comput. Sci..

Boosting Algorithms for Maximizing the Soft Margin

Gunnar Rätsch, Manfred K. Warmuth, Karen A. Glocer, 2007, NIPS.

Predicting nearly as well as the best pruning of a planar decision graph

Manfred K. Warmuth, Eiji Takimoto, 2002, Theor. Comput. Sci..

Entropy Regularized LPBoost

S. V. N. Vishwanathan, Manfred K. Warmuth, Karen A. Glocer, 2008, ALT.

Learning Permutations with Exponential Weights

Manfred K. Warmuth, David P. Helmbold, D. Helmbold, 2007, COLT.

Composite geometric concepts and polynomial predictability

Philip M. Long, Manfred K. Warmuth, 1990, COLT '90.

Robust Bi-Tempered Logistic Loss Based on Bregman Divergences

Manfred K. Warmuth, Ehsan Amid, Rohan Anil, 2019, NeurIPS.

On the Worst-Case Analysis of Temporal-Difference Learning Algorithms

Manfred K. Warmuth, Robert E. Schapire, R. Schapire, 2005, Machine Learning.

Totally corrective boosting algorithms that maximize the margin

Gunnar Rätsch, Manfred K. Warmuth, Jun Liao, 2006, ICML.

Learning nested differences of intersection-closed concept classes

Manfred K. Warmuth, David P. Helmbold, Robert H. Sloan, 2004, Machine Learning.

Rank-Smoothed Pairwise Learning In Perceptual Quality Assessment

Peyman Milanfar, Manfred K. Warmuth, Ehsan Amid, 2020, 2020 IEEE International Conference on Image Processing (ICIP).

Online learning with matrix parameters

Manfred K. Warmuth, Dima Kuzmin, 2009 .

Scheduling Precedence Graphs of Bounded Height

Danny Dolev, Manfred K. Warmuth, D. Dolev, 1984, J. Algorithms.

On-line Variance Minimization in O(n2) per Trial?

Manfred K. Warmuth, Elad Hazan, Satyen Kale, 2010, COLT.

The Optimal PAC Algorithm

Manfred K. Warmuth, 2004, COLT.

Unbiased estimates for linear regression via volume sampling

Manfred K. Warmuth, Michal Derezinski, Michal Derezinski, 2017, NIPS.

Relative Expected Instantaneous Loss Bounds

Manfred K. Warmuth, Jürgen Forster, J. Forster, 2000, J. Comput. Syst. Sci..

Computational Learning Theory and Kernel Machines, 16th Annual Conference on Computational Learning Theory and 7th Kernel Workshop, COLT/Kernel 2003, Washington, DC, USA, August 24-27, 2003, Proceedings

Bernhard Schölkopf, Manfred K. Warmuth, B. Schölkopf, 2003, Annual Conference Computational Learning Theory.

On the Worst-Case Analysis of Temporal-Difference Learning Algorithms

Manfred K. Warmuth, Robert E. Schapire, R. Schapire, 2005, Machine Learning.

Can Entropic Regularization Be Replaced by Squared Euclidean Distance Plus Additional Linear Constraints

Manfred K. Warmuth, 2006, COLT.

Putting Bayes to sleep

Wouter M. Koolen, Manfred K. Warmuth, Dmitry Adamskiy, 2012, NIPS.

The minimum consistent DFA problem cannot be approximated within any polynomial

Leonard Pitt, Manfred K. Warmuth, 1993, JACM.

Occam's Razor

David Haussler, Andrzej Ehrenfeucht, Manfred K. Warmuth, 1987, Inf. Process. Lett..

Active Learning and Feature Selection in the Drug Discovery Process

Manfred K. Warmuth, 2002 .

Two-temperature logistic regression based on the Tsallis divergence

Manfred K. Warmuth, Ehsan Amid, E. Amid, 2017, AISTATS.

Reductions among prediction problems: on the difficulty of predicting automata

Leonard Pitt, Manfred K. Warmuth, L. Pitt, 1988, [1988] Proceedings. Structure in Complexity Theory Third Annual Conference.

A Bayes Rule for Density Matrices

Manfred K. Warmuth, 2005, NIPS.

Continuous Experts and the Binning Algorithm

John Langford, Manfred K. Warmuth, Jacob D. Abernethy, 2006, COLT.

Online variance minimization

Manfred K. Warmuth, Dima Kuzmin, D. Kuzmin, 2011, Machine Learning.

Tracking the Best Disjunction

Peter Auer, Manfred K. Warmuth, P. Auer, 1998, Machine Learning.

Predicting {0,1}-functions on randomly drawn points

David Haussler, Manfred K. Warmuth, Nick Littlestone, 1988, COLT '88.

Relative Loss Bounds for Temporal-Difference Learning

Manfred K. Warmuth, Jürgen Forster, J. Forster, 2000, Machine Learning.

Minimax experimental design: Bridging the gap between statistical and worst-case approaches to least squares regression pdf

Kenneth L. Clarkson, Manfred K. Warmuth, Michael W. Mahoney, 2019, COLT.

Worst-case loss bounds for sigmoided linear neurons

Manfred K. Warmuth, David P. Helmbold, Jyrki Kivinen, 1995, NIPS 1995.

Unlabeled Compression Schemes for Maximum Classes,

Manfred K. Warmuth, Dima Kuzmin, D. Kuzmin, 2007, COLT.

Tracking the Best Expert

Mark Herbster, Manfred K. Warmuth, M. Herbster, 1995, Machine Learning.

Relative loss bounds for single neurons

Manfred K. Warmuth, David P. Helmbold, Jyrki Kivinen, 1999, IEEE Trans. Neural Networks.

Relating Data Compression and Learnability

Manfred K. Warmuth, Nick Littlestone, N. Littlestone, 2003 .

Efficient Learning With Virtual Threshold Gates

Manfred K. Warmuth, Wolfgang Maass, W. Maass, 1995, Inf. Comput..

Linear Hinge Loss and Average Margin

Claudio Gentile, Manfred K. Warmuth, C. Gentile, 1998, NIPS.

NxN Puzzle and Related Relocation Problem

Manfred K. Warmuth, Daniel Ratner, D. Ratner, 1990, J. Symb. Comput..

Scattered versus context-sensitive rewriting

Jakob Gonczarowski, Manfred K. Warmuth, 2004, Acta Informatica.

Prediction-Preserving Reducibility

Leonard Pitt, Manfred K. Warmuth, L. Pitt, 1990, J. Comput. Syst. Sci..

On the Worst-Case Analysis of Temporal-Difference Learning Algorithms

Manfred K. Warmuth, Robert E. Schapire, 1994, ICML.

Non-Additive Path Learning under Full and Partial Information pdf

Mehryar Mohri, Manfred K. Warmuth, Corinna Cortes, 2018 .

Optimal strategies from random walks

Jacob Abernethy, Manfred K. Warmuth, Joel Yellin, 2008, COLT 2008.

Divergence-Based Motivation for Online EM and Combining Hidden Variable Models

Manfred K. Warmuth, Ehsan Amid, E. Amid, 2019, UAI.

The Last-Step Minimax Algorithm

Manfred K. Warmuth, Eiji Takimoto, E. Takimoto, 2000, ALT.

Open Problem: Shifting Experts on Easy Data

Wouter M. Koolen, Manfred K. Warmuth, 2014, COLT.

Bayesian generalized probability calculus for density matrices

Manfred K. Warmuth, Dima Kuzmin, 2009, Machine Learning.

Membership for Growing Context Sensitive Grammars is Polynomial

Manfred K. Warmuth, Elias Dahlhaus, E. Dahlhaus, 1986, CAAP.

On-line learning of linear functions

Philip M. Long, Manfred K. Warmuth, Nick Littlestone, 2005, computational complexity.

Finding a Shortest Solution for the N × N Extension of the 15-PUZZLE Is Intractable

Manfred K. Warmuth, Daniel Ratner, D. Ratner, 1986, AAAI.

Learning Rotations

Manfred K. Warmuth, Adam M. Smith, 2008, COLT.

The Blessing and the Curse of the Multiplicative Updates

Manfred K. Warmuth, 2010, ALT.

Interpolating Between Gradient Descent and Exponentiated Gradient Using Reparameterized Gradient Descent pdf

Manfred K. Warmuth, Ehsan Amid, E. Amid, 2020, ArXiv.

Leveraged volume sampling for linear regression

Manfred K. Warmuth, Michal Derezinski, Daniel J. Hsu, 2018, NeurIPS.

Learning binary relations using weighted majority voting

Manfred K. Warmuth, Sally A. Goldman, 1993, COLT '93.

Learning of depth two neural networks with constant fan-in at the hidden nodes (extended abstract)

Stephen Kwek, Peter Auer, Manfred K. Warmuth, 1996, COLT '96.

Scheduling Flat Graphs

Danny Dolev, Manfred K. Warmuth, D. Dolev, 1985, SIAM J. Comput..

The Probably Approximately Correct (PAC) and Other Learning Models

David Haussler, Manfred K. Warmuth, D. Haussler, 1993 .

On Weak Learning

Manfred K. Warmuth, David P. Helmbold, D. Helmbold, 1995, J. Comput. Syst. Sci..

Sequential Prediction of Individual Sequences Under General Loss Functions

David Haussler, Manfred K. Warmuth, Jyrki Kivinen, 1998, IEEE Trans. Inf. Theory.

Using and combining predictors that specialize

Yoram Singer, Yoav Freund, Manfred K. Warmuth, 1997, STOC '97.

Efficient Learning with Virtual Threshold Gates

Manfred K. Warmuth, Wolfgang Maass, 1995, ICML.

Exponentiated Gradient Versus Gradient Descent for Linear Predictors

Manfred K. Warmuth, Jyrki Kivinen, Jyrki Kivinen, 1997, Inf. Comput..

Equivalence of models for polynomial learnability

David Haussler, Manfred K. Warmuth, Michael Kearns, 1988, COLT '88.

A Comparison of New and Old Algorithms for a Mixture Estimation Problem

Yoram Singer, Manfred K. Warmuth, Robert E. Schapire, 1995, COLT '95.

Open Problem: Online Sabotaged Shortest Path

Wouter M. Koolen, Manfred K. Warmuth, Dmitry Adamskiy, 2015, COLT.

Online Variance Minimization

Manfred K. Warmuth, Dima Kuzmin, 2006, COLT.

Boosting as entropy projection

Manfred K. Warmuth, Jyrki Kivinen, Jyrki Kivinen, 1999, COLT '99.

Predicting nearly as well as the best pruning of a planar decision graph

Manfred K. Warmuth, Eiji Takimoto, E. Takimoto, 2002, Theor. Comput. Sci..

Inline updates for HMMs

Manfred K. Warmuth, Ashutosh Garg, 2003, INTERSPEECH.

A more globally accurate dimensionality reduction method using triplets pdf

Manfred K. Warmuth, Ehsan Amid, E. Amid, 2018, ArXiv.

Winnowing subspaces

Manfred K. Warmuth, 2007, ICML '07.

The Weighted Majority Algorithm

Manfred K. Warmuth, Nick Littlestone, N. Littlestone, 1994, Inf. Comput..

Gap theorems for distributed computing

Manfred K. Warmuth, Shlomo Moran, S. Moran, 1986, PODC '86.

Towards Representation Independence in PAC Learning

Manfred K. Warmuth, 1989, AII.

The p-norm generalization of the LMS algorithm for adaptive filtering

Babak Hassibi, Manfred K. Warmuth, Jyrki Kivinen, 2003, IEEE Transactions on Signal Processing.

How to use expert advice

David Haussler, Yoav Freund, Manfred K. Warmuth, 1993, STOC.

The minimum consistent DFA problem cannot be approximated within and polynomial

Leonard Pitt, Manfred K. Warmuth, L. Pitt, 1989, STOC '89.

Compressing to VC Dimension Many Points

Manfred K. Warmuth, 2003, COLT.

Adaptive scale-invariant online algorithms for learning linear models pdf

Wojciech Kotlowski, Manfred K. Warmuth, Michal Kempka, 2019, ICML.

Online Dynamic Programming

Manfred K. Warmuth, Holakou Rahmanian, Holakou Rahmanian, 2017, NIPS.

A Bayesian Probability Calculus for Density Matrices pdf

Manfred K. Warmuth, Dima Kuzmin, 2006, UAI.

Proceedings of the Second Annual Workshop on Computational Learning Theory : University of California, Santa Cruz, July 31-August 2, 1989

David Haussler, Ronald L. Rivest, Manfred K. Warmuth, 1989 .

Mistake bounds on the noise-free multi-armed bandit game

Atsuyoshi Nakamura, Manfred K. Warmuth, David P. Helmbold, 2019, Inf. Comput..

Correcting the bias in least squares regression with volume-rescaled sampling

Manfred K. Warmuth, Michal Derezinski, Daniel J. Hsu, 2018, AISTATS.

Minimax Algorithm for Learning Rotations

Wojciech Kotlowski, Manfred K. Warmuth, 2011, COLT.

Using experts for predicting continuous outcomes

Manfred K. Warmuth, Jyrki Kivinen, Jyrki Kivinen, 1994, European Conference on Computational Learning Theory.

Classifying learnable geometric concepts with the Vapnik-Chervonenkis dimension

David Haussler, Andrzej Ehrenfeucht, Manfred K. Warmuth, 1986, STOC '86.

Optimum Follow the Leader Algorithm

Manfred K. Warmuth, Dima Kuzmin, 2005, COLT.

Unbiased estimators for random design regression pdf

Manfred K. Warmuth, Michal Derezinski, Daniel Hsu, 2019, ArXiv.

Minimax Fixed-Design Linear Regression

Wouter M. Koolen, Peter L. Bartlett, Manfred K. Warmuth, 2015, COLT.

Polynomial learnability of probabilistic concepts with respect to the Kullback-Leibler divergence

Naoki Abe, Manfred K. Warmuth, Jun'ichi Takeuchi, 1991, COLT '91.

Learning integer lattices

Manfred K. Warmuth, David P. Helmbold, Robert H. Sloan, 1990, COLT '90.

t-Exponential Triplet Embedding pdf

Manfred K. Warmuth, Nikos Vlassis, Ehsan Amid, 2016, ArXiv.

Speech Recognition: Keyword Spotting Through Image Recognition pdf

Manfred K. Warmuth, David Harrison, Sanjay Krishna Gouda, 2018, ArXiv.

Gap Theorems for Distributed Computation

Manfred K. Warmuth, Shlomo Moran, S. Moran, 1993, SIAM J. Comput..

Relative Loss Bounds for Multidimensional Regression Problems

Manfred K. Warmuth, Jyrki Kivinen, Jyrki Kivinen, 1997, Machine Learning.

The Distributed Bit Complexity of the Ring: From the Anonymous to the Non-anonymous Case

Manfred K. Warmuth, Shlomo Moran, Hans L. Bodlaender, 1989, Inf. Comput..

Labeled Compression Schemes for Extremal Classes pdf

Shay Moran, Manfred K. Warmuth, S. Moran, 2015, ALT.

When Is There a Free Matrix Lunch?

Manfred K. Warmuth, 2007, COLT.

Adaptive Caching by Refetching

Scott A. Brandt, Manfred K. Warmuth, Robert B. Gramacy, 2002, NIPS.

Reverse iterative volume sampling for linear regression pdf

Manfred K. Warmuth, Michal Derezinski, Michal Derezinski, 2018, J. Mach. Learn. Res..

The perceptron algorithm vs. Winnow: linear vs. logarithmic mistake bounds when few input variables are relevant

Manfred K. Warmuth, Jyrki Kivinen, Jyrki Kivinen, 1995, COLT '95.

Learning binary relations using weighted majority voting

Manfred K. Warmuth, Sally A. Goldman, S. Goldman, 2004, Machine Learning.

On the computational complexity of approximating distributions by probabilistic automata

Naoki Abe, Manfred K. Warmuth, N. Abe, 1990, Machine Learning.

On-Line Learning Algorithms for Path Experts with Non-Additive Losses

Mehryar Mohri, Manfred K. Warmuth, Corinna Cortes, 2015, COLT.

Relative Loss Bounds, the Minimum Relative Entropy Principle, and EM

Manfred K. Warmuth, 1997, NIPS.

Membership for Growing Context-Sensitive Grammars is Polynomial

Manfred K. Warmuth, Elias Dahlhaus, E. Dahlhaus, 1986, J. Comput. Syst. Sci..

Repeated Games against Budgeted Adversaries

Manfred K. Warmuth, Jacob D. Abernethy, 2010, NIPS.

On the Computational Complexity of Approximating Distributions by Probabilistic Automata

Naoki Abe, Manfred K. Warmuth, N. Abe, 1990, Annual Conference Computational Learning Theory.

Support Vector Machines for Active Learning in the Drug Discovery Process

Gunnar Rätsch, Manfred K. Warmuth, Christian Lemmen, 2002 .

Predicting (0, 1)-functions on randomly drawn points

David Haussler, Manfred K. Warmuth, Nick Littlestone, 1988, [Proceedings 1988] 29th Annual Symposium on Foundations of Computer Science.

Minimax Games with Bandits

Manfred K. Warmuth, Jacob D. Abernethy, 2009, COLT.

Tracking the Best Expert

Mark Herbster, Manfred K. Warmuth, M. Herbster, 1995, Machine-mediated learning.

Tracking the Best Linear Predictor

Mark Herbster, Manfred K. Warmuth, M. Herbster, 2001, J. Mach. Learn. Res..

The Minimax Strategy for Gaussian Density Estimation. pp

Manfred K. Warmuth, Eiji Takimoto, E. Takimoto, 2000, COLT.

When Random Play is Optimal Against an Adversary

Manfred K. Warmuth, Jacob D. Abernethy, Joel Yellin, 2008, COLT.

Worst-case quadratic loss bounds for a generalization of the Widrow-Hoff rule

Philip M. Long, Nicolò Cesa-Bianchi, Manfred K. Warmuth, 1993, COLT '93.

Tail bounds for volume sampled linear regression pdf

Manfred K. Warmuth, Michal Derezinski, Daniel Hsu, 2018, ArXiv.

Learning Nested Differences of Intersection-Closed Concept Classes

Manfred K. Warmuth, David P. Helmbold, Robert H. Sloan, 1989, COLT '89.

The Distributed Bit Complexity of the Ring: From the Anonymous to the Non-anonymous Case

Manfred K. Warmuth, Shlomo Moran, Hans L. Bodlaender, 1989, FCT.

Tracking a Small Set of Experts by Mixing Past Posteriors

Manfred K. Warmuth, Olivier Bousquet, O. Bousquet, 2003, J. Mach. Learn. Res..

Sample compression, learnability, and the Vapnik-Chervonenkis dimension

Sally Floyd, Manfred K. Warmuth, S. Floyd, 2004, Machine Learning.

A New Parameter Estimation Method for Gaussian Mixtures

Yoram Singer, Manfred K. Warmuth, Y. Singer, 1998, NIPS 1998.

Additive versus exponentiated gradient updates for linear prediction

Manfred K. Warmuth, Jyrki Kivinen, Jyrki Kivinen, 1995, STOC '95.

Path kernels and multiplicative updates

Manfred K. Warmuth, Eiji Takimoto, E. Takimoto, 2003 .

Computing on an anonymous ring

Hagit Attiya, Manfred K. Warmuth, Marc Snir, 1988, JACM.

Learnability and the Vapnik-Chervonenkis dimension

David Haussler, Andrzej Ehrenfeucht, Manfred K. Warmuth, 1989, JACM.

Unlabeled sample compression schemes and corner peelings for ample and maximum classes pdf

Shay Moran, Victor Chepoi, Manfred K. Warmuth, 2018, ICALP.

A Comparison of New and Old Algorithms for a Mixture Estimation Problem

Yoram Singer, Manfred K. Warmuth, Robert E. Schapire, 2004, Machine Learning.

Batch and On-Line Parameter Estimation of Gaussian Mixtures Based on the Joint Entropy

Yoram Singer, Manfred K. Warmuth, Y. Singer, 1998, NIPS.

Path Kernels and Multiplicative Updates

Manfred K. Warmuth, Eiji Takimoto, E. Takimoto, 2002, J. Mach. Learn. Res..

Tracking the best regressor

Mark Herbster, Manfred K. Warmuth, 1998, COLT' 98.

Learning a set of directions

Wouter M. Koolen, Jiazhong Nie, Manfred K. Warmuth, 2013, COLT.

Worst-case Loss Bounds for Single Neurons

Manfred K. Warmuth, David P. Helmbold, Jyrki Kivinen, 1995, NIPS.

Subsampling for Ridge Regression via Regularized Volume Sampling

Manfred K. Warmuth, Michal Derezinski, Michal Derezinski, 2017, AISTATS.

A case where a spindly two-layer linear network whips any neural network with a fully connected input layer pdf

Wojciech Kotlowski, Manfred K. Warmuth, Ehsan Amid, 2020, ArXiv.

Efficient Margin Maximizing with Boosting

Gunnar Rätsch, Manfred K. Warmuth, G. Rätsch, 2005, J. Mach. Learn. Res..

Boosting versus Covering

Manfred K. Warmuth, Kohei Hatano, 2003, NIPS.

The Parallel Complexity of Scheduling with Precedence Constraints

Eli Upfal, Danny Dolev, Manfred K. Warmuth, 1986, J. Parallel Distributed Comput..

Tutorial summary: Survey of boosting from an optimization perspective

S. V. N. Vishwanathan, Manfred K. Warmuth, S. Vishwanathan, 2009, ICML '09.

Online PCA with Optimal Regret

Jiazhong Nie, Wojciech Kotlowski, Manfred K. Warmuth, 2016, J. Mach. Learn. Res..

Classification with free energy at raised temperatures

Paul Lamere, Bhiksha Raj, Rita Singh, 2003, INTERSPEECH.

An Implicit Form of Krasulina's k-PCA Update without the Orthonormality Constraint pdf

Manfred K. Warmuth, Ehsan Amid, E. Amid, 2019, AAAI.

Winnowing with Gradient Descent

Manfred K. Warmuth, Ehsan Amid, E. Amid, 2020, COLT.

New combination coefficients for AdaBoost algorithms

Feng Ye, Manfred K. Warmuth, Shuisheng Zhou, 2010, 2010 Sixth International Conference on Natural Computation.

Worst-case quadratic loss bounds for prediction using linear functions and gradient descent

Philip M. Long, Manfred K. Warmuth, Nicolò Cesa-Bianchi, 1996, IEEE Trans. Neural Networks.

Open Problem: Lower bounds for Boosting with Hadamard Matrices

Xinhua Zhang, S. V. N. Vishwanathan, Jiazhong Nie, 2013, COLT.

Leaving the Span

S. V. N. Vishwanathan, Manfred K. Warmuth, S. Vishwanathan, 2005, COLT.

Noise Free Multi-armed Bandit Game

Atsuyoshi Nakamura, Manfred K. Warmuth, David P. Helmbold, 2015, LATA.

Kernelization of matrix updates, when and how?

Wojciech Kotlowski, Manfred K. Warmuth, Shuisheng Zhou, 2014, Theor. Comput. Sci..

Barrier Boosting

Gunnar Rätsch, Klaus-Robert Müller, Sebastian Mika, 2000, COLT.

On the Convergence of Leveraging

Gunnar Rätsch, Sebastian Mika, Manfred K. Warmuth, 2001, NIPS.

Bounds on approximate steepest descent for likelihood maximization in exponential families

Manfred K. Warmuth, Nicolò Cesa-Bianchi, Anders Krogh, 1994, IEEE Trans. Inf. Theory.

Learning rotations with little regret

Manfred K. Warmuth, Elad Hazan, Satyen Kale, 2010, Machine Learning.

On-line Prediction and Conversion Strategies

Nicolò Cesa-Bianchi, Yoav Freund, Manfred K. Warmuth, 1994, Machine Learning.

The limits of squared Euclidean distance regularization

Manfred K. Warmuth, Michal Derezinski, Michal Derezinski, 2014, NIPS.

Computational Power of low-resource distributed systems: • Jukka Suomela: "Survey of Local Algorithms", Journal ACM Computing Surveys, 2013.

Hagit Attiya, Masafumi Yamashita, Manfred K. Warmuth, 2013 .

The minimum consistent DFA problem cannot be approximated within any polynomial

Leonard Pitt, Manfred K. Warmuth, L. Pitt, 1989, [1989] Proceedings. Structure in Complexity Theory Fourth Annual Conference.

On-line learning of linear functions

Philip M. Long, Manfred K. Warmuth, Nick Littlestone, 1991, STOC '91.

Training Algorithms for Hidden Markov Models using Entropy Based Distance Functions

Yoram Singer, Manfred K. Warmuth, Y. Singer, 1996, NIPS.

Composite geometric concepts and polynomial predictability

Philip M. Long, Manfred K. Warmuth, 1990, COLT '90.

Reparameterizing Mirror Descent as Gradient Descent

Manfred K. Warmuth, Ehsan Amid, 2020, NeurIPS.

Learning Permutations with Exponential Weights

Manfred K. Warmuth, David P. Helmbold, D. Helmbold, 2007, COLT.

On the Complexity of Iterated Shuffle

David Haussler, Manfred K. Warmuth, D. Haussler, 1984, J. Comput. Syst. Sci..

THE WEIGHTED MAJORITY ALGORITHM (Supersedes 89-16)

Manfred K. Warmuth, Nick Littlestone, N. Littlestone, 1992 .

Low-dimensional Data Embedding via Robust Ranking

Manfred K. Warmuth, Nikos Vlassis, Ehsan Amid, 2016 .

Kernelization of Matrix Updates, When and How?

Wojciech Kotlowski, Manfred K. Warmuth, Shuisheng Zhou, 2012, ALT.

Active Learning with Support Vector Machines in the Drug Discovery Process

Gunnar Rätsch, Manfred K. Warmuth, Christian Lemmen, 2003, J. Chem. Inf. Comput. Sci..

Relative Loss Bounds for On-Line Density Estimation with the Exponential Family of Distributions

Manfred K. Warmuth, Katy S. Azoury, 1999, Machine Learning.

Online kernel PCA with entropic matrix updates

Manfred K. Warmuth, Dima Kuzmin, D. Kuzmin, 2007, ICML '07.

Learning integer lattices

Manfred K. Warmuth, David P. Helmbold, Robert H. Sloan, 1990, COLT '90.

Tight worst-case loss bounds for predicting with expert advice

David Haussler, Manfred K. Warmuth, Jyrki Kivinen, 1994, EuroCOLT.

Learning Eigenvectors for Free

Wouter M. Koolen, Wojciech Kotlowski, Manfred K. Warmuth, 2011, NIPS.

Maximizing the Margin with Boosting

Gunnar Rätsch, Manfred K. Warmuth, G. Rätsch, 2002, COLT.

Combining Initial Segments of Lists

Wouter M. Koolen, Manfred K. Warmuth, David P. Helmbold, 2011, ALT.

Active Learning in the Drug Discovery Process

Gunnar Rätsch, Manfred K. Warmuth, Christian Lemmen, 2001, NIPS.

Some weak learning results

Manfred K. Warmuth, David P. Helmbold, D. Helmbold, 1992, COLT '92.

On‐Line Portfolio Selection Using Multiplicative Updates

Yoram Singer, Manfred K. Warmuth, Robert E. Schapire, 1998, ICML.

The weighted majority algorithm

Manfred K. Warmuth, Nick Littlestone, N. Littlestone, 1989, 30th Annual Symposium on Foundations of Computer Science.

Manipulating Derivation Forests by Scheduling Techniques

Jakob Gonczarowski, Manfred K. Warmuth, 1986, Theor. Comput. Sci..

A Fast Algorithm for Multiprocessor Scheduling of Unit-Length Jobs

Manfred K. Warmuth, Barbara B. Simons, B. Simons, 1989, SIAM J. Comput..

Proceedings of the seventh annual conference on Computational learning theory

Manfred K. Warmuth, 1994, COLT 1994.

Randomized PCA Algorithms with Regret Bounds that are Logarithmic in the Dimension

Manfred K. Warmuth, Dima Kuzmin, D. Kuzmin, 2006, NIPS.

The Blessing and the Curse of the Multiplicative Updates

Manfred K. Warmuth, 2010, Discovery Science.

Averaging Expert Predictions

Manfred K. Warmuth, Jyrki Kivinen, Jyrki Kivinen, 1999, EuroCOLT.

Shifting Experts on Easy Data

Wouter M. Koolen, Manfred K. Warmuth, 2014 .

TriMap: Large-scale Dimensionality Reduction Using Triplets pdf

Manfred K. Warmuth, Ehsan Amid, 2019, ArXiv.

PCA with Gaussian perturbations pdf

Wojciech Kotlowski, Manfred K. Warmuth, Wojciech Kotlowski, 2015, ArXiv.

Exponentiated Gradient Reweighting for Robust Training Under Label Noise and Beyond pdf

Manfred K. Warmuth, Ehsan Amid, Hossein Talebi, 2021, ArXiv.

A case where a spindly two-layer linear network decisively outperforms any neural network with a fully connected input layer

Wojciech Kotlowski, Manfred K. Warmuth, Ehsan Amid, 2021, ALT.

Theory and Praxis of Machine Learning (Dagstuhl Seminar 9426)

Thomas G. Dietterich, Hans Ulrich Simon, Manfred K. Warmuth, 2021 .

LocoProp: Enhancing BackProp via Local Loss Optimization pdf

Manfred K. Warmuth, Ehsan Amid, Rohan Anil, 2021, ArXiv.

WORST-CASE QUADRATIC LOSS BOUNDS FOR ON-LINE PREDICTION OF LINEAR FUNCTIONS BY GRADIENT DESCENT

Philip M. Long, Manfred K. Warmuth, Nicolò Cesa-Bianchi, 1993 .

Learning nested differences of intersection-closed concept classes

Manfred K. Warmuth, D. Helmbold, R. Sloan, 2004, Machine Learning.

Combining initial segments of lists

Wouter M. Koolen, Manfred K. Warmuth, D. Helmbold, 2011, Theor. Comput. Sci..

Randomized Online PCA Algorithms with Regret Bounds that are Logarithmic in the Dimension

Manfred K. Warmuth, D. Kuzmin, 2008 .

On the Computational Complexity of Approximating Distributions by Probabilistic Automata

Manfred K. Warmuth, N. Abe, 1990, COLT '90.

The Perceptron Algorithm Versus Winnow: Linear Versus Logarithmic Mistake Bounds when Few Input Variables are Relevant (Technical Note)

Manfred K. Warmuth, P. Auer, Jyrki Kivinen, 1997, Artif. Intell..

Learning algorithms for tracking changing concepts and an investigation into the error surfaces of single artificial neurons

Manfred K. Warmuth, M. Herbster, 1998 .

Corrigendum to "Learning rotations with little regret" September 7, 2010

Manfred K. Warmuth, Elad Hazan, Satyen Kale, 2010 .

Learning Rotations Online

Manfred K. Warmuth, Adam M. Smith, 2010 .

On the worst-case analysis of temporal-difference learning algorithms

Manfred K. Warmuth, R. Schapire, 2004, Machine Learning.

Parallel Approximation Algorithms for Bin Packing

Richard J. Anderson, Manfred K. Warmuth, E. Mayr, 1988, Inf. Comput..

Learning Binary Relations Using Weighted Majority Voting

Manfred K. Warmuth, S. Goldman, 1995, Machine Learning.

Sample compression, learnability, and the Vapnik-Chervonenkis dimension

Manfred K. Warmuth, S. Floyd, Sally Floyd, 1995, Machine Learning.

Engineering proteinase K using machine learning and synthetic genes

Manfred K. Warmuth, Jun Liao, S. Govindarajan, 2007, BMC biotechnology.

Profile Scheduling of Opposing Forests and Level Orders

Manfred K. Warmuth, D. Dolev, 1985 .

Scheduling on profiles of constant breadth

Manfred K. Warmuth, 1981 .

THE CMU SPHINX-4 SPEECH RECOGNITION SYSTEM

Manfred K. Warmuth, Paul Lamere, B. Raj, 2001 .

rst-Case ratic Loss Bounds for Pre sing Linear Functions and Gra

Philip M. Long, Manfred K. Warmuth, Nicolb Cesa-Bianchi, 1996 .

Step-size Adaptation Using Exponentiated Gradient Updates

Manfred K. Warmuth, Christopher Fifty, Rohan Anil, 2022, ArXiv.

E 1 Analysing Iterative Machine Learning Algorithms with In formation Geometric Methods

Manfred K. Warmuth, 2022 .

The{dollar}p{dollar}-Norm Generalization of the LMS Algorithm for Adaptive Filtering

Manfred K. Warmuth, Jyrki Kivinen, B. Hassibi, 2022 .

RI : Small : Collaborative Research : Probabilistic Models using Generalized Exponential Families

Manfred K. Warmuth, V. S, N. Vishwanathan, 2014 .

Online Learning on Spheres

Manfred K. Warmuth, R. C. Williamson, R. Mahony, 2005 .

Deriving and Analyzing Learning Algorithms

Manfred K. Warmuth, D. Helmbold, 2022 .

Efficient Learning Algorithms.

David Haussler, Manfred K. Warmuth, 1990 .

Mar ginal Boosting 1

Gunnar Rätsch, Manfred K. Warmuth, 2001 .

The P-Norn Generalization of the LMS Algorithm for Adaptive Filtering

Babak Hassibi, Manfred K. Warmuth, Jyrki Kivinen, 2003 .

Lower bounds for Boosting with Hadamard Matrices

Manfred K. Warmuth, Xinhua Zhang, 2013 .

Learning Theory and Kernel Machines : 16th Annual Conference on Learning Theory and 7th Kernel Workshop, COLT/Kernel 2003, Washington, DC, USA, August 24-27, 2003. Proceedings

Bernhard Schölkopf, Manfred K. Warmuth, 2003 .

The Robustness of Quadratic Voting

Manfred K. Warmuth, A. Ehrenfeucht, A. Blumer, 2016 .

How to use expert advice

Manfred K. Warmuth, Y. Freund, R. Schapire, 1997, JACM.

The Binning Algorithm

Manfred K. Warmuth, J. Langford, J. Abernethy, 2022 .

A comparison of new and old algorithms for a mixture estimation problem

Manfred K. Warmuth, R. Schapire, Y. Singer, 1995, COLT '95.

CLASSIFICATION WITH FREE ENERGY A

Manfred K. Warmuth, Paul Lamere, Rita Singh, 2003 .

Unlabeled sample compression schemes and corner peelings for ample and maximum classes

Manfred K. Warmuth, V. Chepoi, S. Moran, 2018, ICALP.

The weighted majority algorithm

Manfred K. Warmuth, Nick Littlestone, N. Littlestone, 1989, 30th Annual Symposium on Foundations of Computer Science.

Tracking the Best Disjunction

Manfred K. Warmuth, P. Auer, 1995, Proceedings of IEEE 36th Annual Foundations of Computer Science.

Sample Compression, Learnability, and the Vapnik-Chervonenkis Dimension

Manfred K. Warmuth, 1995, Machine Learning.

On-line Prediction and Conversion Strategies

Manfred K. Warmuth, Y. Freund, N. Cesa-Bianchi, 1994, Machine Learning.

Computing on an anonymous ring

Manfred K. Warmuth, H. Attiya, M. Snir, 1985, PODC '85.

Layerwise Bregman Representation Learning with Applications to Knowledge Distillation

Manfred K. Warmuth, Christopher Fifty, Rohan Anil, 2022, ArXiv.

Hedging Structured Concepts

Wouter M. Koolen, Manfred K. Warmuth, Jyrki Kivinen, 2010, COLT.

Clustering above Exponential Families with Tempered Exponential Measures

Manfred K. Warmuth, R. Nock, E. Amid, 2022, AISTATS.

Online variance minimization

Manfred K. Warmuth, D. Kuzmin, 2006, Machine Learning.

Learning from Randomly Initialized Neural Network Features

Manfred K. Warmuth, Rohan Anil, E. Amid, 2022, ArXiv.

LocoProp: Enhancing BackProp via Local Loss Optimization

Manfred K. Warmuth, Rohan Anil, E. Amid, 2021, AISTATS.

TriMap: Large-scale Dimensionality Reduction Using Triplets

Manfred K. Warmuth, E. Amid, 2019, ArXiv.

Reparameterizing Mirror Descent as Gradient Descent

Manfred K. Warmuth, E. Amid, Ehsan Amid, 2020, NeurIPS.

A Mechanism for Sample-Efficient In-Context Learning for Sparse Retrieval Tasks

Manfred K. Warmuth, Jacob D. Abernethy, Alekh Agarwal, 2023, ArXiv.

Optimal strategies from random walks

Manfred K. Warmuth, Jacob D. Abernethy, J. Abernethy, 2008, COLT 2008.

Active Learning with Support Vector Machines in the Drug Discovery Process.

Manfred K. Warmuth, C. Lemmen, Jun Liao, 2003 .

Finding a Shortest Solution for the N × N Extension of the 15-PUZZLE Is Intractable

Manfred K. Warmuth, D. Ratner, 1986, AAAI.

Learning rotations with little regret

Manfred K. Warmuth, Elad Hazan, Satyen Kale, 2010, Machine Learning.

Hedging Structured Concepts

Wouter M. Koolen, Manfred K. Warmuth, Jyrki Kivinen, 2010, COLT 2010.

Optimal Transport with Tempered Exponential Measures

Manfred K. Warmuth, R. Nock, E. Amid, 2023, ArXiv.

Boosting with Tempered Exponential Measures

Manfred K. Warmuth, R. Nock, E. Amid, 2023, ArXiv.

Online Non-Additive Path Learning under Full and Partial Information

Manfred K. Warmuth, M. Mohri, Corinna Cortes, 2018, ALT.

Hedging Structured Concepts

Wouter M. Koolen, Manfred K. Warmuth, Jyrki Kivinen, 2010, COLT 2010.

Learning Rotations Online

Manfred K. Warmuth, Adam M. Smith, 2010 .

Layerwise Bregman Representation Learning of Neural Networks with Applications to Knowledge Distillation

Manfred K. Warmuth, Christopher Fifty, Rohan Anil, 2023, Trans. Mach. Learn. Res..

Efficient Margin Maximizing with Boosting * Gunnar Rätsch

Manfred K. Warmuth, De, John Shawe-Taylor, 2003 .

Proceedings of the seventh annual conference on Computational learning theory

Manfred K. Warmuth, 1994, COLT 1994.

Relative Loss Bounds for Temporal-Difference Learning

Manfred K. Warmuth, J. Forster, 2000, Machine Learning.

Relative Loss Bounds for Temporal-difference Learning

Manfred K. Warmuth, Urgen Forster, Peter Bartlett, 2022 .

On-line prediction and conversion strategies

Manfred K. Warmuth, Y. Freund, N. Cesa-Bianchi, 2004, Machine Learning.

Computing on an anonymous ring

Manfred K. Warmuth, H. Attiya, M. Snir, 1988, JACM.

The Tempered Hilbert Simplex Distance and Its Application To Non-linear Embeddings of TEMs

Manfred K. Warmuth, R. Nock, Frank Nielsen, 2023, ArXiv.

Open Problem: Learning sparse linear concepts by priming the features

Manfred K. Warmuth, Ehsan Amid, 2023, COLT.

Unbiased estimators for random design regression

Manfred K. Warmuth, Daniel J. Hsu, Michal Derezinski, 2019, J. Mach. Learn. Res..

Tempered Calculus for ML: Application to Hyperbolic Model Embedding

Manfred K. Warmuth, R. Nock, Alexander Soen, 2024, 2402.04163.

Optimal Transport with Tempered Exponential Measures

Manfred K. Warmuth, R. Nock, Frank Nielsen, 2023, AAAI.