Philip M. Long

发表

Density estimation for shift-invariant multidimensional distributions pdf

Rocco A. Servedio, Anindya De, Philip M. Long, 2018, ITCS.

The Relaxed Online Maximum Margin Algorithm

Yi Li, Philip M. Long, Yi Li, 1999, Machine Learning.

Adaptive Disk Spindown via Optimal Rent-to-Buy in Probabilistic Environments

Philip M. Long, P. Krishnan, Jeffrey Scott Vitter, 1999, Algorithmica.

On the Effect of the Activation Function on the Distribution of Hidden Nodes in a Deep Network

Philip M. Long, Hanie Sedghi, Hanie Sedghi, 2019, Neural Computation.

Improved Bounds about On-line Learning of Smooth Functions of a Single Variable

Philip M. Long, 1996, ALT.

Simulating access to hidden information while learning

Philip M. Long, Peter Auer, P. Auer, 1994, STOC '94.

Composite geometric concepts and polynomial predictability

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

Discriminative learning can succeed where generative learning fails

Rocco A. Servedio, Philip M. Long, Hans Ulrich Simon, 2007, Inf. Process. Lett..

Discriminative learning can succeed where generative learning fails

Rocco A. Servedio, Philip M. Long, R. Servedio, 2006, Inf. Process. Lett..

New bounds on the price of bandit feedback for mistake-bounded online multiclass learning

Philip M. Long, 2017, ALT.

Algorithmic Learning Theory, 17th International Conference, ALT 2006, Barcelona, Spain, October 7-10, 2006, Proceedings

Philip M. Long, José L. Balcázar, Frank Stephan, 2006, ALT.

Characterizations of Learnability for Classes of {0, ..., n}-Valued Functions

Philip M. Long, David Haussler, Nicolò Cesa-Bianchi, 1995, J. Comput. Syst. Sci..

PAC Learning Axis-aligned Rectangles with Respect to Product Distributions from Multiple-Instance Examples

Philip M. Long, Lei Tan, Lei Tan, 1996, COLT '96.

On-line evaluation and prediction using linear functions

Philip M. Long, 1997, COLT '97.

Finite-sample analysis of interpolating linear classifiers in the overparameterized regime pdf

Philip M. Long, Niladri S. Chatterji, 2020, ArXiv.

Agnostic Boosting

Shai Ben-David, Philip M. Long, Yishay Mansour, 2001, COLT/EuroCOLT.

More theorems about scale-sensitive dimensions and learning

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

Guest editors' introduction: Special issue on learning theory

Philip M. Long, Peter Auer, 2008, J. Comput. Syst. Sci..

On the inductive bias of dropout pdf

Philip M. Long, David P. Helmbold, D. Helmbold, 2014, J. Mach. Learn. Res..

Learning Halfspaces with Malicious Noise

Rocco A. Servedio, Philip M. Long, Adam R. Klivans, 2009, J. Mach. Learn. Res..

On the sample complexity of learning functions with bounded variation

Philip M. Long, 1998, COLT' 98.

Rate-distortion optimizations for motion estimation in low-bit-rate video coding

Philip M. Long, Jeffrey Scott Vitter, Dzung T. Hoang, 1996, Electronic Imaging.

The one-inclusion graph algorithm is near-optimal for the prediction model of learning

Yi Li, Aravind Srinivasan, Philip M. Long, 2001, IEEE Trans. Inf. Theory.

PAC Learning Axis-Aligned Rectangles with Respect to Product Distributions from Multiple-Instance Examples

Philip M. Long, Lei Tan, Lei Tan, 1996, COLT.

Performance guarantees for hierarchical clustering

Philip M. Long, Sanjoy Dasgupta, S. Dasgupta, 2002, J. Comput. Syst. Sci..

On the Complexity of Learning from Drifting Distributions

Philip M. Long, Rakesh D. Barve, 1997, Inf. Comput..

Associative Reinforcement Learning using Linear Probabilistic Concepts

Philip M. Long, Naoki Abe, N. Abe, 1999, ICML.

Approximating hyper-rectangles: learning and pseudo-random sets

Aravind Srinivasan, Philip M. Long, Peter Auer, 1997, STOC '97.

Dictionary Selection Using Partial Matching

Philip M. Long, Jeffrey Scott Vitter, Dzung T. Hoang, 1999, Inf. Sci..

Random classification noise defeats all convex potential boosters

Rocco A. Servedio, Philip M. Long, R. Servedio, 2008, ICML '08.

Efficient algorithms for learning functions with bounded variation

Philip M. Long, 2004, Inf. Comput..

Apple Tasting

Philip M. Long, David P. Helmbold, Nick Littlestone, 2000, Inf. Comput..

Predicting Electricity Distribution Feeder Failures Using Machine Learning Susceptibility Analysis

Philip M. Long, David L. Waltz, Frank Doherty, 2006, AAAI.

Structural Results About On-line Learning Models With and Without Queries

Philip M. Long, Peter Auer, P. Auer, 1999, Machine Learning.

Proceedings of the 17th international conference on Algorithmic Learning Theory

Philip M. Long, José L. Balcázar, Frank Stephan, 2006 .

Using the doubling dimension to analyze the generalization of learning algorithms

Yi Li, Philip M. Long, Nader H. Bshouty, 2009, J. Comput. Syst. Sci..

On the Complexity of Function Learning

Gerhard J. Woeginger, Philip M. Long, Peter Auer, 1993, COLT.

Using the Pseudo-Dimension to Analyze Approximation Algorithms for Integer Programming

Philip M. Long, 2001, WADS.

Halfspace Learning, Linear Programming, and Nonmalicious Distributions

Philip M. Long, 1994, Inf. Process. Lett..

Oracle lower bounds for stochastic gradient sampling algorithms pdf

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

Characterizations of learnability for classes of {O, …, n}-valued functions

Shai Ben-David, Philip M. Long, Nicolò Cesa-Bianchi, 1992, COLT '92.

Multiple-dictionary compression using partial matching

Philip M. Long, Jeffrey Scott Vitter, Dzung T. Hoang, 1995, Proceedings DCC '95 Data Compression Conference.

On-line learning with linear loss constraints

Philip M. Long, Nick Littlestone, 1993, COLT '93.

Generalization bounds for deep convolutional neural networks

Philip M. Long, Hanie Sedghi, Hanie Sedghi, 2019, ICLR.

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

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

Random classification noise defeats all convex potential boosters

Rocco A. Servedio, Philip M. Long, 2008, ICML.

A Generalization of Sauer's Lemma

Philip M. Long, David Haussler, D. Haussler, 1995, J. Comb. Theory, Ser. A.

Surprising properties of dropout in deep networks

Philip M. Long, David P. Helmbold, 2017, COLT.

Fundamental differences between Dropout and Weight Decay in Deep Networks

Philip M. Long, David P. Helmbold, 2016 .

On the difficulty of approximately maximizing agreements

Shai Ben-David, Philip M. Long, Nadav Eiron, 2000, J. Comput. Syst. Sci..

Efficient cost measures for motion compensation at low bit rates

Philip M. Long, Jeffrey Scott Vitter, Dzung T. Hoang, 1996, Proceedings of Data Compression Conference - DCC '96.

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..

On-line learning of linear functions

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

Low-weight halfspaces for sparse boolean vectors

Rocco A. Servedio, Philip M. Long, R. Servedio, 2013, ITCS '13.

Tracking drifting concepts by minimizing disagreements

Philip M. Long, David P. Helmbold, D. Helmbold, 2004, Machine Learning.

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

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

The Singular Values of Convolutional Layers pdf

Philip M. Long, Hanie Sedghi, Vineet Gupta, 2018, ICLR.

Benign overfitting in linear regression

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

Boosting and Microarray Data

Philip M. Long, SN VinsensiusBerlianVega, SN VinsensiusBerlianVega, 2003, Machine Learning.

Reinforcement Learning with Immediate Rewards and Linear Hypotheses

Philip M. Long, Naoki Abe, Alan W. Biermann, 2003, Algorithmica.

Restricted Boltzmann Machines are Hard to Approximately Evaluate or Simulate

Rocco A. Servedio, Philip M. Long, R. Servedio, 2010, ICML.

Benchmarking large-scale Fine-Grained Categorization

Philip M. Long, Anelia Angelova, A. Angelova, 2014, IEEE Winter Conference on Applications of Computer Vision.

Learning to Make Rent-to-Buy Decisions with Systems Applications

Philip M. Long, P. Krishnan, Jeffrey Scott Vitter, 1995, ICML.

Boosting the Area under the ROC Curve

Rocco A. Servedio, Philip M. Long, 2007, NIPS.

Active and passive learning of linear separators under log-concave distributions

Maria-Florina Balcan, Philip M. Long, Maria-Florina Balcan, 2012, COLT.

The Complexity of Learning According to Two Models of a Drifting Environment

Philip M. Long, 1998, COLT' 98.

Apple tasting and nearly one-sided learning

Philip M. Long, David P. Helmbold, Nick Littlestone, 1992, Proceedings., 33rd Annual Symposium on Foundations of Computer Science.

Linear classifiers are nearly optimal when hidden variables have diverse effects

Philip M. Long, Nader H. Bshouty, N. Bshouty, 2012, Machine Learning.

Unsupervised evidence integration

Rocco A. Servedio, Philip M. Long, Vinay Varadan, 2005, ICML.

Special Issue on New Theoretical Challenges in Machine Learning

Philip M. Long, Avrim Blum, 2014, Algorithmica.

Guest Editor's Introduction

Philip M. Long, 1997, Machine Learning.

Learnability and the doubling dimension

Yi Li, Philip M. Long, Yi Li, 2006, NIPS.

The learning complexity of smooth functions of a single variable

Philip M. Long, Don Kimber, Don Kimber, 1992, COLT '92.

On the Weight of Halfspaces over Hamming Balls

Rocco A. Servedio, Philip M. Long, R. Servedio, 2014, SIAM J. Discret. Math..

Attribute-efficient learning of decision lists and linear threshold functions under unconcentrated distributions

Rocco A. Servedio, Philip M. Long, 2006, NIPS.

Efficient cost measures for motion estimation at low bit rates

Philip M. Long, Jeffrey Scott Vitter, Dzung T. Hoang, 1998, IEEE Trans. Circuits Syst. Video Technol..

Media-independent Error Correction using RTP

Philip M. Long, D. Budge, Ralph Mckenzie, 1997 .

On-Line Learning with Linear Loss Constraints

Philip M. Long, David P. Helmbold, Nick Littlestone, 2000, Inf. Comput..

Fat-shattering and the learnability of real-valued functions

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

On the complexity of learning from drifting distributions

Philip M. Long, Rakesh D. Barve, 1997, COLT '96.

One-Pass Boosting

Rocco A. Servedio, Philip M. Long, Zafer Barutçuoglu, 2007, NIPS.

The Complexity of Learning According to Two Models of a Drifting Environment

Philip M. Long, 2004, Machine Learning.

Martingale Boosting

Rocco A. Servedio, Philip M. Long, R. Servedio, 2005, COLT.

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.

On the sample complexity of PAC learning half-spaces against the uniform distribution

Philip M. Long, 1995, IEEE Trans. Neural Networks.

Editors' Introduction

Philip M. Long, José L. Balcázar, Frank Stephan, 2006, ALT.

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.

Learning Halfspaces with Malicious Noise

Rocco A. Servedio, Philip M. Long, Adam R. Klivans, 2009, ICALP.

An upper bound on the sample complexity of PAC-learning halfspaces with respect to the uniform distribution

Philip M. Long, 2003, Inf. Process. Lett..

The Power of Localization for Efficiently Learning Linear Separators with Malicious Noise pdf

Maria-Florina Balcan, Philip M. Long, Pranjal Awasthi, 2013, ArXiv.

Improved bounds on the sample complexity of learning

Yi Li, Aravind Srinivasan, Philip M. Long, 2000, SODA '00.

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.

On Agnostic Learning with {0, *, 1}-Valued and Real-Valued Hypotheses

Philip M. Long, 2001, COLT/EuroCOLT.

Adaptive Martingale Boosting

Rocco A. Servedio, Philip M. Long, 2008, NIPS.

How to select a winner in evolutionary optimization?

Risto Miikkulainen, Philip M. Long, Hormoz Shahrzad, 2017, SSCI.

Improved bounds about on-line learning of smooth-functions of a single variable

Philip M. Long, 2000, Theor. Comput. Sci..

On the Complexity of Proper Distribution-Free Learning of Linear Classifiers

Philip M. Long, 2020, ALT.

The Power of Localization for Efficiently Learning Linear Separators with Noise

Maria-Florina Balcan, Philip M. Long, Pranjal Awasthi, 2013, J. ACM.

Approximating Hyper-Rectangles: Learning and Pseudorandom Sets

Aravind Srinivasan, Philip M. Long, Peter Auer, 1998, J. Comput. Syst. Sci..

A Theoretical Analysis of Query Selection for Collaborative Filtering

Philip M. Long, Wee Sun Lee, 2001, COLT/EuroCOLT.

On the Necessity of Irrelevant Variables

Philip M. Long, David P. Helmbold, D. Helmbold, 2011, ICML.

Boosting with Diverse Base Classifiers

Philip M. Long, Sanjoy Dasgupta, S. Dasgupta, 2003, COLT.

Text compression via alphabet re-representation

Philip M. Long, Jeffrey Scott Vitter, Apostol Natsev, 1997, Proceedings DCC '97. Data Compression Conference.

Finding Planted Partitions in Nearly Linear Time using Arrested Spectral Clustering

Philip M. Long, Nader H. Bshouty, N. Bshouty, 2010, ICML.

The power of localization for efficiently learning linear separators with noise

Maria-Florina Balcan, Philip M. Long, Pranjal Awasthi, 2014, STOC.

Size-free generalization bounds for convolutional neural networks pdf

Philip M. Long, Hanie Sedghi, Hanie Sedghi, 2019, ICLR 2020.

Online Learning of Multiple Tasks with a Shared Loss

Philip M. Long, Yoram Singer, Ofer Dekel, 2007, J. Mach. Learn. Res..

Explicit bit minimization for motion-compensated video coding

Philip M. Long, Jeffrey Scott Vitter, Dzung T. Hoang, 1994, Proceedings of IEEE Data Compression Conference (DCC'94).

Learning Sums of Independent Random Variables with Sparse Collective Support

Rocco A. Servedio, Anindya De, Philip M. Long, 2018, 2018 IEEE 59th Annual Symposium on Foundations of Computer Science (FOCS).

Text compression via alphabet re-representation

Philip M. Long, Jeffrey Scott Vitter, Apostol Natsev, 1999, Neural Networks.

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.

Minimum majority classification and boosting

Philip M. Long, 2002, AAAI/IAAI.

New Bounds for Learning Intervals with Implications for Semi-Supervised Learning

Philip M. Long, David P. Helmbold, D. Helmbold, 2012, COLT.

Learning large-margin halfspaces with more malicious noise

Rocco A. Servedio, Philip M. Long, R. Servedio, 2011, NIPS.

Boostinq, support vector machines and reinforcement learning in computer-aided lean management

Philip M. Long, David L. Waltz, Roger N. Anderson, 2005 .

On-Line Learning of Smooth Functions of a Single Variable

Philip M. Long, Don Kimber, 1995, Theor. Comput. Sci..

Introduction to the special issue on computational learning theory

Philip M. Long, 2003 .

On-line learning of linear functions

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

Composite geometric concepts and polynomial predictability

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

Tree Dependent Identically Distributed Learning

Philip M. Long, Tony Jebara, T. Jebara, 2005 .

Online Multitask Learning

Philip M. Long, Yoram Singer, Ofer Dekel, 2006, COLT.

Tracking drifting concepts using random examples

Philip M. Long, David P. Helmbold, D. Helmbold, 1991, Annual Conference Computational Learning Theory.

Fat-shattering and the learnability of real-valued functions

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

A Theoretical Analysis of Query Selection for Collaborative Filtering

Philip M. Long, Sanjoy Dasgupta, Wee Sun Lee, 2001, Machine Learning.

Multiple-Dictionary Coding Using Partial Matching.

Philip M. Long, Jeffrey Scott Vitter, Dzung T. Hoang, 1995, DCC 1995.

Dropout Versus Weight Decay for Deep Networks pdf

Philip M. Long, David P. Helmbold, 2016, ArXiv.

Mistake Bounds for Maximum Entropy Discrimination

Philip M. Long, Xinyu Wu, 2004, NIPS.

Baum's Algorithm Learns Intersections of Halfspaces with Respect to Log-Concave Distributions

Philip M. Long, Adam R. Klivans, Alex K. Tang, 2009, APPROX-RANDOM.

On the Global Convergence of Training Deep Linear ResNets pdf

Philip M. Long, Quanquan Gu, Difan Zou, 2020, ICLR.

On the complexity of function learning

Gerhard J. Woeginger, Philip M. Long, Peter Auer, 1993, COLT '93.

The perils of being unhinged: On the accuracy of classifiers minimizing a noise-robust convex loss pdf

Rocco A. Servedio, Philip M. Long, 2021, ArXiv.

Properties of the After Kernel pdf

Philip M. Long, 2021, ArXiv.

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.

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.

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 .

Consistency versus Realizable H-Consistency for Multiclass Classification

Philip M. Long, R. Servedio, 2013, ICML.

Comment on " 'Stemness': Transcriptional Profiling of Embryonic and Adult Stem Cells" and "A Stem Cell Molecular Signature" (I)

Philip M. Long, H. Otu, T. Libermann, 2003, Science.

Tracking Drifting Concepts By Minimizing Disagreements

Philip M. Long, D. Helmbold, 2004, Machine Learning.

Gradient descent efficiently learns positive definite deep linear residual networks

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

Optimal gene expression analysis by microarrays.

Philip M. Long, Sayan Mukherjee, L. Wong, 2002, Cancer cell.

Breast cancer classification and prognosis based on gene expression profiles from a population-based study

Philip M. Long, S. Fox, C. Sotiriou, 2003, Proceedings of the National Academy of Sciences of the United States of America.

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

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

SORTING AND SEARCHING WITH A FAULTY COMPARISON ORACLE

Philip M. Long, 1992 .

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

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

Text Compression via Alphabet Re-representation Extended Abstract

Philip M. Long, J. Vitter, A. Natsev, 1997 .

Rate-Distortion Optimizations for MotionEstimation in Low-Bitrate Video

Philip M. Long, J. Vitter, CodingDzung, 1995 .

The power of localization for efficiently learning linear separators with noise

Philip M. Long, Maria-Florina Balcan, Pranjal Awasthi, 2014, STOC.

Finite-sample analysis of interpolating linear classifiers in the overparameterized regime

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

On the complexity of function learning

Philip M. Long, P. Auer, W. Maass, 1993, COLT '93.

On the Complexity of Function Learning

Philip M. Long, P. Auer, W. Maass, 1993, Machine-mediated learning.

Deep Linear Networks can Benignly Overfit when Shallow Ones Do

Philip M. Long, Niladri S. Chatterji, 2022, ArXiv.

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

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

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..

Performance guarantees for hierarchical clustering

Philip M. Long, Sanjoy Dasgupta, S. Dasgupta, 2002, J. Comput. Syst. Sci..

Oracle lower bounds for stochastic gradient sampling algorithms

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

Identification of discriminators of hepatoma by gene expression profiling using a minimal dataset approach

Philip M. Long, Paul B S Lai, Edison T Liu, 2004, Hepatology.

Comparative full-length genome sequence analysis of 14 SARS coronavirus isolates and common mutations associated with putative origins of infection

Philip M. Long, Yijun Ruan, Edison T Liu, 2003, The Lancet.

Mutational dynamics of the SARS coronavirus in cell culture and human populations isolated in 2003

Tao Zhang, Philip M. Long, Jianjun Liu, 2004, BMC infectious diseases.

Generalization bounds for deep convolutional neural networks

Philip M. Long, Hanie Sedghi, 2019, ICLR.

Molecular changes from dysplastic nodule to hepatocellular carcinoma through gene expression profiling

Philip M. Long, A. Ramasamy, S. Shevade, 2005, Hepatology.

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

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

Properties of the After Kernel

Philip M. Long, 2021, ArXiv.

Deep Linear Networks can Benignly Overfit when Shallow Ones Do

Philip M. Long, Niladri S. Chatterji, 2022, J. Mach. Learn. Res..

The Perils of Being Unhinged: On the Accuracy of Classifiers Minimizing a Noise-Robust Convex Loss

Philip M. Long, R. Servedio, 2021, Neural Computation.

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

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

Foolish Crowds Support Benign Overfitting

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

How to select a winner in evolutionary optimization?

Philip M. Long, Nigel P. Duffy, R. Miikkulainen, 2017, 2017 IEEE Symposium Series on Computational Intelligence (SSCI).

Comparative full-length genome sequence analysis of 14 SARS coronavirus isolates and common mutations associated with putative origins of infection

Philip M. Long, E. Liu, Chia-Lin Wei, 2003, The Lancet.

Visual Product Discovery

Philip M. Long, Nigel P. Duffy, Olivier Francon, 2016 .

Practical learning from one-sided feedback

Philip M. Long, D. Sculley, N. Littlestone, 2007, KDD '07.

Benign overfitting in linear regression

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

Algorithms and hardness results for parallel large margin learning

Rocco A. Servedio, Philip M. Long, Phil Long, 2011, J. Mach. Learn. Res..