Philip M. Long

According to our database, Philip M. Long authored at least 124 papers between 1991 and 2024.

Collaborative distances:

• Dijkstra number of three.
• Erdős number of three.

2024

Corrigendum to "Prediction, learning, uniform convergence, and scale-sensitive dimensions" [J. Comput. Syst. Sci. 56 (2) (1998) 174-190].

Peter L. Bartlett, Philip M. Long

J. Comput. Syst. Sci., March, 2024

Sharpness-Aware Minimization and the Edge of Stability.

Philip M. Long, Peter L. Bartlett

J. Mach. Learn. Res., 2024

2023

Deep linear networks can benignly overfit when shallow ones do.

Niladri S. Chatterji, Philip M. Long

J. Mach. Learn. Res., 2023

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

Peter L. Bartlett, Philip M. Long, Olivier Bousquet

J. Mach. Learn. Res., 2023

2022

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

Philip M. Long, Rocco A. Servedio

Neural Comput., 2022

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

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

J. Mach. Learn. Res., 2022

Foolish Crowds Support Benign Overfitting.

Niladri S. Chatterji, Philip M. Long

J. Mach. Learn. Res., 2022

2021

Superlinear Integrality Gaps for the Minimum Majority Problem.

Philip M. Long

SIAM J. Discret. Math., 2021

When Does Gradient Descent with Logistic Loss Find Interpolating Two-Layer Networks?

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

J. Mach. Learn. Res., 2021

Finite-sample Analysis of Interpolating Linear Classifiers in the Overparameterized Regime.

Niladri S. Chatterji, Philip M. Long

J. Mach. Learn. Res., 2021

Failures of Model-dependent Generalization Bounds for Least-norm Interpolation.

Peter L. Bartlett, Philip M. Long

J. Mach. Learn. Res., 2021

Properties of the After Kernel.

Philip M. Long

CoRR, 2021

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

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

Proceedings of the Conference on Learning Theory, 2021

2020

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

Philip M. Long

Theor. Comput. Sci., 2020

Oracle lower bounds for stochastic gradient sampling algorithms.

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

CoRR, 2020

On the Global Convergence of Training Deep Linear ResNets.

Difan Zou, Philip M. Long, Quanquan Gu

Proceedings of the 8th International Conference on Learning Representations, 2020

Generalization bounds for deep convolutional neural networks.

Philip M. Long, Hanie Sedghi

Proceedings of the 8th International Conference on Learning Representations, 2020

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

Philip M. Long, Raphael J. Long

Proceedings of the Algorithmic Learning Theory, 2020

2019

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

Philip M. Long, Hanie Sedghi

Neural Comput., 2019

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

Peter L. Bartlett, David P. Helmbold, Philip M. Long

Neural Comput., 2019

Benign Overfitting in Linear Regression.

Peter L. Bartlett, Philip M. Long, Gábor Lugosi, Alexander Tsigler

CoRR, 2019

Size-free generalization bounds for convolutional neural networks.

Philip M. Long, Hanie Sedghi

CoRR, 2019

Density Estimation for Shift-Invariant Multidimensional Distributions.

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

Proceedings of the 10th Innovations in Theoretical Computer Science Conference, 2019

The Singular Values of Convolutional Layers.

Hanie Sedghi, Vineet Gupta, Philip M. Long

Proceedings of the 7th International Conference on Learning Representations, 2019

2018

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

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

CoRR, 2018

Gradient descent with identity initialization efficiently learns positive definite linear transformations.

Peter L. Bartlett, David P. Helmbold, Philip M. Long

Proceedings of the 35th International Conference on Machine Learning, 2018

Learning Sums of Independent Random Variables with Sparse Collective Support.

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

Proceedings of the 59th IEEE Annual Symposium on Foundations of Computer Science, 2018

2017

Surprising properties of dropout in deep networks.

David P. Helmbold, Philip M. Long

J. Mach. Learn. Res., 2017

The Power of Localization for Efficiently Learning Linear Separators with Noise.

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

J. ACM, 2017

How to select a winner in evolutionary optimization?

Risto Miikkulainen, Hormoz Shahrzad, Nigel Duffy, Philip M. Long

Proceedings of the 2017 IEEE Symposium Series on Computational Intelligence, 2017

2016

Dropout Versus Weight Decay for Deep Networks.

David P. Helmbold, Philip M. Long

CoRR, 2016

2015

On the inductive bias of dropout.

David P. Helmbold, Philip M. Long

J. Mach. Learn. Res., 2015

Special Issue on New Theoretical Challenges in Machine Learning.

Avrim Blum, Philip M. Long

Algorithmica, 2015

2014

On the Weight of Halfspaces over Hamming Balls.

Philip M. Long, Rocco A. Servedio

SIAM J. Discret. Math., 2014

Benchmarking large-scale Fine-Grained Categorization.

Anelia Angelova, Philip M. Long

Proceedings of the IEEE Winter Conference on Applications of Computer Vision, 2014

2013

Algorithms and hardness results for parallel large margin learning.

Philip M. Long, Rocco A. Servedio

J. Mach. Learn. Res., 2013

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

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

CoRR, 2013

Low-weight halfspaces for sparse boolean vectors.

Philip M. Long, Rocco A. Servedio

Proceedings of the Innovations in Theoretical Computer Science, 2013

Consistency versus Realizable H-Consistency for Multiclass Classification.

Philip M. Long, Rocco A. Servedio

Proceedings of the 30th International Conference on Machine Learning, 2013

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

Maria-Florina Balcan, Philip M. Long

Proceedings of the COLT 2013, 2013

2012

Linear classifiers are nearly optimal when hidden variables have diverse effects.

Nader H. Bshouty, Philip M. Long

Mach. Learn., 2012

On the necessity of irrelevant variables.

David P. Helmbold, Philip M. Long

J. Mach. Learn. Res., 2012

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

David P. Helmbold, Philip M. Long

Proceedings of the COLT 2012, 2012

2011

Learning large-margin halfspaces with more malicious noise.

Philip M. Long, Rocco A. Servedio

Proceedings of the Advances in Neural Information Processing Systems 24: 25th Annual Conference on Neural Information Processing Systems 2011. Proceedings of a meeting held 12-14 December 2011, 2011

2010

Random classification noise defeats all convex potential boosters.

Philip M. Long, Rocco A. Servedio

Mach. Learn., 2010

Restricted Boltzmann Machines are Hard to Approximately Evaluate or Simulate.

Philip M. Long, Rocco A. Servedio

Proceedings of the 27th International Conference on Machine Learning (ICML-10), 2010

Finding Planted Partitions in Nearly Linear Time using Arrested Spectral Clustering.

Nader H. Bshouty, Philip M. Long

Proceedings of the 27th International Conference on Machine Learning (ICML-10), 2010

2009

Learning Halfspaces with Malicious Noise.

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

J. Mach. Learn. Res., 2009

Using the doubling dimension to analyze the generalization of learning algorithms.

Nader H. Bshouty, Yi Li, Philip M. Long

J. Comput. Syst. Sci., 2009

Linear Classifiers are Nearly Optimal When Hidden Variables Have Diverse Effect.

Nader H. Bshouty, Philip M. Long

Proceedings of the COLT 2009, 2009

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

Adam R. Klivans, Philip M. Long, Alex K. Tang

Proceedings of the Approximation, 2009

2008

Preface.

Philip M. Long, Frank Stephan

Theor. Comput. Sci., 2008

Guest editors' introduction: Special issue on learning theory.

Peter Auer, Philip M. Long

J. Comput. Syst. Sci., 2008

Adaptive Martingale Boosting.

Philip M. Long, Rocco A. Servedio

Proceedings of the Advances in Neural Information Processing Systems 21, 2008

2007

Online Learning of Multiple Tasks with a Shared Loss.

Ofer Dekel, Philip M. Long, Yoram Singer

J. Mach. Learn. Res., 2007

Discriminative learning can succeed where generative learning fails.

Philip M. Long, Rocco A. Servedio, Hans Ulrich Simon

Inf. Process. Lett., 2007

Boosting the Area under the ROC Curve.

Philip M. Long, Rocco A. Servedio

Proceedings of the Advances in Neural Information Processing Systems 20, 2007

One-Pass Boosting.

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

Proceedings of the Advances in Neural Information Processing Systems 20, 2007

2006

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

Philip M. Long, Rocco A. Servedio

Proceedings of the Advances in Neural Information Processing Systems 19, 2006

Learnability and the doubling dimension.

Yi Li, Philip M. Long

Proceedings of the Advances in Neural Information Processing Systems 19, 2006

Discriminative Learning Can Succeed Where Generative Learning Fails.

Philip M. Long, Rocco A. Servedio

Proceedings of the Learning Theory, 19th Annual Conference on Learning Theory, 2006

Online Multitask Learning.

Ofer Dekel, Philip M. Long, Yoram Singer

Proceedings of the Learning Theory, 19th Annual Conference on Learning Theory, 2006

Editors' Introduction.

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

Proceedings of the Algorithmic Learning Theory, 17th International Conference, 2006

Predicting Electricity Distribution Feeder Failures Using Machine Learning Susceptibility Analysis.

Philip Gross, Albert Boulanger, Marta Arias, David L. Waltz, Philip M. Long, Charles Lawson, Roger Anderson, Matthew Koenig, Mark Mastrocinque, William Fairechio, John A. Johnson, Serena Lee, Frank Doherty, Arthur Kressner

Proceedings of the Proceedings, 2006

2005

Performance guarantees for hierarchical clustering.

Sanjoy Dasgupta, Philip M. Long

J. Comput. Syst. Sci., 2005

Unsupervised evidence integration.

Philip M. Long, Vinay Varadan, Sarah Gilman, Mark Treshock, Rocco A. Servedio

Proceedings of the Machine Learning, 2005

Martingale Boosting.

Philip M. Long, Rocco A. Servedio

Proceedings of the Learning Theory, 18th Annual Conference on Learning Theory, 2005

2004

Efficient algorithms for learning functions with bounded variation.

Philip M. Long

Inf. Comput., 2004

Mistake Bounds for Maximum Entropy Discrimination.

Philip M. Long, Xinyu Wu

Proceedings of the Advances in Neural Information Processing Systems 17 [Neural Information Processing Systems, 2004

2003

Boosting and Microarray Data.

Philip M. Long, Vinsensius Berlian Vega SN

Mach. Learn., 2003

A Theoretical Analysis of Query Selection for Collaborative Filtering.

Sanjoy Dasgupta, Wee Sun Lee, Philip M. Long

Mach. Learn., 2003

On the difficulty of approximately maximizing agreements.

Shai Ben-David, Nadav Eiron, Philip M. Long

J. Comput. Syst. Sci., 2003

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

Philip M. Long

Inf. Process. Lett., 2003

Reinforcement Learning with Immediate Rewards and Linear Hypotheses.

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

Algorithmica, 2003

Boosting with Diverse Base Classifiers.

Sanjoy Dasgupta, Philip M. Long

Proceedings of the Computational Learning Theory and Kernel Machines, 2003

2002

The Relaxed Online Maximum Margin Algorithm.

Yi Li, Philip M. Long

Mach. Learn., 2002

Minimum Majority Classification and Boosting.

Philip M. Long

Proceedings of the Eighteenth National Conference on Artificial Intelligence and Fourteenth Conference on Innovative Applications of Artificial Intelligence, July 28, 2002

2001

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

Yi Li, Philip M. Long, Aravind Srinivasan

IEEE Trans. Inf. Theory, 2001

Improved Bounds on the Sample Complexity of Learning.

Yi Li, Philip M. Long, Aravind Srinivasan

J. Comput. Syst. Sci., 2001

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

Philip M. Long

Proceedings of the Algorithms and Data Structures, 7th International Workshop, 2001

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

Philip M. Long

Proceedings of the Computational Learning Theory, 2001

A Theoretical Analysis of Query Selection for Collaborative Filtering.

Wee Sun Lee, Philip M. Long

Proceedings of the Computational Learning Theory, 2001

Agnostic Boosting.

Shai Ben-David, Philip M. Long, Yishay Mansour

Proceedings of the Computational Learning Theory, 2001

2000

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

Philip M. Long

Theor. Comput. Sci., 2000

On-Line Learning with Linear Loss Constraints.

David P. Helmbold, Nick Littlestone, Philip M. Long

Inf. Comput., 2000

Apple Tasting.

David P. Helmbold, Nick Littlestone, Philip M. Long

Inf. Comput., 2000

Approximating Hyper-Rectangles: Learning and Pseudo-random Sets

Peter Auer, Philip M. Long, Aravind Srinivasan

Electron. Colloquium Comput. Complex., 2000

Simulating Access to Hidden Information while Learning

Peter Auer, Philip M. Long

Electron. Colloquium Comput. Complex., 2000

1999

Text compression via alphabet re-representation.

Philip M. Long, Apostol Natsev, Jeffrey Scott Vitter

Neural Networks, 1999

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

Philip M. Long

Mach. Learn., 1999

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

Peter Auer, Philip M. Long

Mach. Learn., 1999

Dictionary Selection Using Partial Matching.

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

Inf. Sci., 1999

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

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

Algorithmica, 1999

Associative Reinforcement Learning using Linear Probabilistic Concepts.

Naoki Abe, Philip M. Long

Proceedings of the Sixteenth International Conference on Machine Learning (ICML 1999), Bled, Slovenia, June 27, 1999

1998

Efficient cost measures for motion estimation at low bit rates.

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

IEEE Trans. Circuits Syst. Video Technol., 1998

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

Philip M. Long, Lei Tan

Mach. Learn., 1998

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

Peter L. Bartlett, Philip M. Long

J. Comput. Syst. Sci., 1998

Approximating Hyper-Rectangles: Learning and Pseudorandom Sets.

Peter Auer, Philip M. Long, Aravind Srinivasan

J. Comput. Syst. Sci., 1998

On the Sample Complexity of Learning Functions with Bounded Variation.

Philip M. Long

Proceedings of the Eleventh Annual Conference on Computational Learning Theory, 1998

1997

Guest Editor's Introduction.

Philip M. Long

Mach. Learn., 1997

On the Complexity of Learning from Drifting Distributions.

Rakesh D. Barve, Philip M. Long

Inf. Comput., 1997

On-line Evaluation and Prediction using Linear Functions.

Philip M. Long

Proceedings of the Tenth Annual Conference on Computational Learning Theory, 1997

1996

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

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

IEEE Trans. Neural Networks, 1996

Fat-Shattering and the Learnability of Real-Valued Functions.

Peter L. Bartlett, Philip M. Long, Robert C. Williamson

J. Comput. Syst. Sci., 1996

Efficient Cost Measures for Motion Compensation at Low Bit Rates (Extended Abstract).

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

Proceedings of the 6th Data Compression Conference (DCC '96), Snowbird, Utah, USA, March 31, 1996

1995

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

Philip M. Long

IEEE Trans. Neural Networks, 1995

On-Line Learning of Smooth Functions of a Single Variable.

Don Kimber, Philip M. Long

Theor. Comput. Sci., 1995

On the Complexity of Function Learning.

Peter Auer, Philip M. Long, Wolfgang Maass, Gerhard J. Woeginger

Mach. Learn., 1995

A Generalization of Sauer's Lemma.

David Haussler, Philip M. Long

J. Comb. Theory A, 1995

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

Shai Ben-David, Nicolò Cesa-Bianchi, David Haussler, Philip M. Long

J. Comput. Syst. Sci., 1995

On-line Learning of Linear Functions.

Nick Littlestone, Philip M. Long, Manfred K. Warmuth

Comput. Complex., 1995

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

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

Proceedings of the Machine Learning, 1995

Multiple-Dictionary Coding Using Partial Matching.

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

Proceedings of the IEEE Data Compression Conference, 1995

More Theorems about Scale-sensitive Dimensions and Learning.

Peter L. Bartlett, Philip M. Long

Proceedings of the Eigth Annual Conference on Computational Learning Theory, 1995

1994

Composite Geometric Concepts and Polynomial Predictability

Philip M. Long, Manfred K. Warmuth

Inf. Comput., September, 1994

Tracking Drifting Concepts By Minimizing Disagreements.

David P. Helmbold, Philip M. Long

Mach. Learn., 1994

Halfspace Learning, Linear Programming, and Nonmalicious Distributions.

Philip M. Long

Inf. Process. Lett., 1994

Explicit Bit Minimization for Motion-Compensated Video Coding.

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

Proceedings of the IEEE Data Compression Conference, 1994

1993

On-Line Learning with Linear Loss Constraints.

Nick Littlestone, Philip M. Long

Proceedings of the Sixth Annual ACM Conference on Computational Learning Theory, 1993

Worst-Case Quadratic Loss Bounds for a Generalization of the Widrow-Hoff Rule.

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

Proceedings of the Sixth Annual ACM Conference on Computational Learning Theory, 1993

1992

Apple Tasting and Nearly One-Sided Learning

David P. Helmbold, Nick Littlestone, Philip M. Long

Proceedings of the 33rd Annual Symposium on Foundations of Computer Science, 1992

The Learning Complexity of Smooth Functions of a Single Variable.

Don Kimber, Philip M. Long

Proceedings of the Fifth Annual ACM Conference on Computational Learning Theory, 1992

Characterizations of Learnability for Classes of {<i>O, ..., n</i>}-Valued Functions.

Shai Ben-David, Nicolò Cesa-Bianchi, Philip M. Long

Proceedings of the Fifth Annual ACM Conference on Computational Learning Theory, 1992

1991

Tracking Drifting Concepts Using Random Examples.

David P. Helmbold, Philip M. Long

Proceedings of the Fourth Annual Workshop on Computational Learning Theory, 1991