Philip M. Long

Publication Activity (10 Years)

Years Active: 1990-2024
Publications (10 Years): 48

Top Venues

CoRR

J. Mach. Learn. Res.

Neural Comput.

ALT

Publications

Peter L. Bartlett, Philip M. Long
Corrigendum to "Prediction, learning, uniform convergence, and scale-sensitive dimensions" [J. Comput. Syst. Sci. 56 (2) (1998) 174-190]. J. Comput. Syst. Sci. 140 (2024)
Peter L. Bartlett, Philip M. Long
Prediction, Learning, Uniform Convergence, and Scale-sensitive Dimensions. CoRR (2023)
Niladri S. Chatterji, Philip M. Long
Deep linear networks can benignly overfit when shallow ones do. J. Mach. Learn. Res. 24 (2023)
Philip M. Long, Peter L. Bartlett
Sharpness-Aware Minimization and the Edge of Stability. CoRR (2023)
Niladri S. Chatterji, Philip M. Long
Foolish Crowds Support Benign Overfitting. J. Mach. Learn. Res. 23 (2022)
Niladri S. Chatterji, Philip M. Long, Peter L. Bartlett
The Interplay Between Implicit Bias and Benign Overfitting in Two-Layer Linear Networks. J. Mach. Learn. Res. 23 (2022)
Philip M. Long, Rocco A. Servedio
The Perils of Being Unhinged: On the Accuracy of Classifiers Minimizing a Noise-Robust Convex Loss. Neural Comput. 34 (6) (2022)
Peter L. Bartlett, Philip M. Long, Olivier Bousquet
The Dynamics of Sharpness-Aware Minimization: Bouncing Across Ravines and Drifting Towards Wide Minima. CoRR (2022)
Niladri S. Chatterji, Philip M. Long
Deep Linear Networks can Benignly Overfit when Shallow Ones Do. CoRR (2022)
Peter L. Bartlett, Philip M. Long
Failures of Model-dependent Generalization Bounds for Least-norm Interpolation. J. Mach. Learn. Res. 22 (2021)
Niladri S. Chatterji, Philip M. Long, Peter L. Bartlett
When does gradient descent with logistic loss interpolate using deep networks with smoothed ReLU activations? CoRR (2021)
Niladri S. Chatterji, Philip M. Long
Finite-sample Analysis of Interpolating Linear Classifiers in the Overparameterized Regime. J. Mach. Learn. Res. 22 (2021)
Philip M. Long
Superlinear Integrality Gaps for the Minimum Majority Problem. SIAM J. Discret. Math. 35 (4) (2021)
Philip M. Long
Properties of the After Kernel. CoRR (2021)
Niladri S. Chatterji, Philip M. Long
Foolish Crowds Support Benign Overfitting. CoRR (2021)
Philip M. Long, Rocco A. Servedio
The perils of being unhinged: On the accuracy of classifiers minimizing a noise-robust convex loss. CoRR (2021)
Niladri S. Chatterji, Philip M. Long, Peter L. Bartlett
The Interplay Between Implicit Bias and Benign Overfitting in Two-Layer Linear Networks. CoRR (2021)
Niladri S. Chatterji, Philip M. Long, Peter L. Bartlett
When Does Gradient Descent with Logistic Loss Find Interpolating Two-Layer Networks? J. Mach. Learn. Res. 22 (2021)
Niladri S. Chatterji, Philip M. Long, Peter L. Bartlett
When does gradient descent with logistic loss interpolate using deep networks with smoothed ReLU activations? COLT (2021)
Niladri S. Chatterji, Philip M. Long, Peter L. Bartlett
When does gradient descent with logistic loss find interpolating two-layer networks? CoRR (2020)
Difan Zou, Philip M. Long, Quanquan Gu
On the Global Convergence of Training Deep Linear ResNets. ICLR (2020)
Philip M. Long, Raphael J. Long
On the Complexity of Proper Distribution-Free Learning of Linear Classifiers. ALT (2020)
Difan Zou, Philip M. Long, Quanquan Gu
On the Global Convergence of Training Deep Linear ResNets. CoRR (2020)
Niladri S. Chatterji, Peter L. Bartlett, Philip M. Long
Oracle lower bounds for stochastic gradient sampling algorithms. CoRR (2020)
Peter L. Bartlett, Philip M. Long
Failures of model-dependent generalization bounds for least-norm interpolation. CoRR (2020)
Philip M. Long
New bounds on the price of bandit feedback for mistake-bounded online multiclass learning. Theor. Comput. Sci. 808 (2020)
Philip M. Long, Hanie Sedghi
Generalization bounds for deep convolutional neural networks. ICLR (2020)
Niladri S. Chatterji, Philip M. Long
Finite-sample analysis of interpolating linear classifiers in the overparameterized regime. CoRR (2020)
Philip M. Long, Hanie Sedghi
On the effect of the activation function on the distribution of hidden nodes in a deep network. CoRR (2019)
Philip M. Long, Hanie Sedghi
Size-free generalization bounds for convolutional neural networks. CoRR (2019)
Hanie Sedghi, Vineet Gupta, Philip M. Long
The Singular Values of Convolutional Layers. ICLR (Poster) (2019)
Anindya De, Philip M. Long, Rocco A. Servedio
Density Estimation for Shift-Invariant Multidimensional Distributions. ITCS (2019)
Peter L. Bartlett, David P. Helmbold, Philip M. Long
Gradient Descent with Identity Initialization Efficiently Learns Positive-Definite Linear Transformations by Deep Residual Networks. Neural Comput. 31 (3) (2019)
Peter L. Bartlett, Philip M. Long, Gábor Lugosi, Alexander Tsigler
Benign Overfitting in Linear Regression. CoRR (2019)
Philip M. Long, Hanie Sedghi
On the Effect of the Activation Function on the Distribution of Hidden Nodes in a Deep Network. Neural Comput. 31 (12) (2019)
Anindya De, Philip M. Long, Rocco A. Servedio
Density estimation for shift-invariant multidimensional distributions. CoRR (2018)
Anindya De, Philip M. Long, Rocco A. Servedio
Learning Sums of Independent Random Variables with Sparse Collective Support. FOCS (2018)
Peter L. Bartlett, David P. Helmbold, Philip M. Long
Gradient descent with identity initialization efficiently learns positive definite linear transformations by deep residual networks. CoRR (2018)
Peter L. Bartlett, David P. Helmbold, Philip M. Long
Gradient descent with identity initialization efficiently learns positive definite linear transformations. ICML (2018)
Anindya De, Philip M. Long, Rocco A. Servedio
Learning Sums of Independent Random Variables with Sparse Collective Support. CoRR (2018)
Hanie Sedghi, Vineet Gupta, Philip M. Long
The Singular Values of Convolutional Layers. CoRR (2018)
Peter L. Bartlett, Steven N. Evans, Philip M. Long
Representing smooth functions as compositions of near-identity functions with implications for deep network optimization. CoRR (2018)
David P. Helmbold, Philip M. Long
Surprising properties of dropout in deep networks. COLT (2017)
Philip M. Long
New bounds on the price of bandit feedback for mistake-bounded online multiclass learning. ALT (2017)
Risto Miikkulainen, Hormoz Shahrzad, Nigel Duffy, Philip M. Long
How to select a winner in evolutionary optimization? SSCI (2017)
David P. Helmbold, Philip M. Long
Surprising properties of dropout in deep networks. J. Mach. Learn. Res. 18 (2017)
Pranjal Awasthi, Maria-Florina Balcan, Philip M. Long
The Power of Localization for Efficiently Learning Linear Separators with Noise. J. ACM 63 (6) (2017)
David P. Helmbold, Philip M. Long
Dropout Versus Weight Decay for Deep Networks. CoRR (2016)
David P. Helmbold, Philip M. Long
On the inductive bias of dropout. J. Mach. Learn. Res. 16 (2015)
Avrim Blum, Philip M. Long
Special Issue on New Theoretical Challenges in Machine Learning. Algorithmica 72 (1) (2015)
Anelia Angelova, Philip M. Long
Benchmarking large-scale Fine-Grained Categorization. WACV (2014)
David P. Helmbold, Philip M. Long
On the Inductive Bias of Dropout. CoRR (2014)
Philip M. Long, Rocco A. Servedio
On the Weight of Halfspaces over Hamming Balls. SIAM J. Discret. Math. 28 (3) (2014)
Pranjal Awasthi, Maria-Florina Balcan, Philip M. Long
The power of localization for efficiently learning linear separators with noise. STOC (2014)
Philip M. Long, Rocco A. Servedio
Consistency versus Realizable H-Consistency for Multiclass Classification. ICML (3) (2013)
Philip M. Long, Rocco A. Servedio
Low-weight halfspaces for sparse boolean vectors. ITCS (2013)
Philip M. Long, Rocco A. Servedio
Algorithms and hardness results for parallel large margin learning. J. Mach. Learn. Res. 14 (1) (2013)
Maria-Florina Balcan, Philip M. Long
Active and passive learning of linear separators under log-concave distributions. COLT (2013)
Pranjal Awasthi, Maria-Florina Balcan, Philip M. Long
The Power of Localization for Efficiently Learning Linear Separators with Malicious Noise. CoRR (2013)
David P. Helmbold, Philip M. Long
New Bounds for Learning Intervals with Implications for Semi-Supervised Learning. COLT (2012)
Nader H. Bshouty, Philip M. Long
Linear classifiers are nearly optimal when hidden variables have diverse effects. Mach. Learn. 86 (2) (2012)
David P. Helmbold, Philip M. Long
On the Necessity of Irrelevant Variables CoRR (2012)
David P. Helmbold, Philip M. Long
On the necessity of irrelevant variables. J. Mach. Learn. Res. 13 (2012)
Maria-Florina Balcan, Philip M. Long
Active and passive learning of linear separators under log-concave distributions CoRR (2012)
Philip M. Long, Rocco A. Servedio
Learning large-margin halfspaces with more malicious noise. NIPS (2011)
David P. Helmbold, Philip M. Long
On the Necessity of Irrelevant Variables. ICML (2011)
Rocco A. Servedio, Philip M. Long
Algorithms and hardness results for parallel large margin learning. NIPS (2011)
Philip M. Long, Rocco A. Servedio
Random classification noise defeats all convex potential boosters. Mach. Learn. 78 (3) (2010)
Nader H. Bshouty, Philip M. Long
Finding Planted Partitions in Nearly Linear Time using Arrested Spectral Clustering. ICML (2010)
Philip M. Long, Rocco A. Servedio
Restricted Boltzmann Machines are Hard to Approximately Evaluate or Simulate. ICML (2010)
Adam R. Klivans, Philip M. Long, Rocco A. Servedio
Learning Halfspaces with Malicious Noise. ICALP (1) (2009)
Nader H. Bshouty, Philip M. Long
Linear Classifiers are Nearly Optimal When Hidden Variables Have Diverse Effect. COLT (2009)
Adam R. Klivans, Philip M. Long, Alex K. Tang
Baum's Algorithm Learns Intersections of Halfspaces with Respect to Log-Concave Distributions. APPROX-RANDOM (2009)
Nader H. Bshouty, Yi Li, Philip M. Long
Using the doubling dimension to analyze the generalization of learning algorithms. J. Comput. Syst. Sci. 75 (6) (2009)
Adam R. Klivans, Philip M. Long, Rocco A. Servedio
Learning Halfspaces with Malicious Noise. J. Mach. Learn. Res. 10 (2009)
Philip M. Long, Frank Stephan
Preface. Theor. Comput. Sci. 405 (3) (2008)
Peter Auer, Philip M. Long
Guest editors' introduction: Special issue on learning theory. J. Comput. Syst. Sci. 74 (8) (2008)
Philip M. Long, Rocco A. Servedio
Adaptive Martingale Boosting. NIPS (2008)
Philip M. Long, Rocco A. Servedio
Random classification noise defeats all convex potential boosters. ICML (2008)
Ofer Dekel, Philip M. Long, Yoram Singer
Online Learning of Multiple Tasks with a Shared Loss. J. Mach. Learn. Res. 8 (2007)
Zafer Barutçuoglu, Philip M. Long, Rocco A. Servedio
One-Pass Boosting. NIPS (2007)
Philip M. Long, Rocco A. Servedio, Hans Ulrich Simon
Discriminative learning can succeed where generative learning fails. Inf. Process. Lett. 103 (4) (2007)
Philip M. Long, Rocco A. Servedio
Boosting the Area under the ROC Curve. NIPS (2007)
Ofer Dekel, Philip M. Long, Yoram Singer
Online Multitask Learning. COLT (2006)
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
Predicting Electricity Distribution Feeder Failures Using Machine Learning Susceptibility Analysis. AAAI (2006)
Philip M. Long, Rocco A. Servedio
Discriminative Learning Can Succeed Where Generative Learning Fails. COLT (2006)
José L. Balcázar, Philip M. Long, Frank Stephan
Editors' Introduction. ALT (2006)
Yi Li, Philip M. Long
Learnability and the doubling dimension. NIPS (2006)
Philip M. Long, Rocco A. Servedio
Attribute-efficient learning of decision lists and linear threshold functions under unconcentrated distributions. NIPS (2006)
Philip M. Long, Vinay Varadan, Sarah Gilman, Mark Treshock, Rocco A. Servedio
Unsupervised evidence integration. ICML (2005)
Philip M. Long, Rocco A. Servedio
Martingale Boosting. COLT (2005)
Sanjoy Dasgupta, Philip M. Long
Performance guarantees for hierarchical clustering. J. Comput. Syst. Sci. 70 (4) (2005)
Philip M. Long
Efficient algorithms for learning functions with bounded variation. Inf. Comput. 188 (1) (2004)
Philip M. Long, Xinyu Wu
Mistake Bounds for Maximum Entropy Discrimination. NIPS (2004)
Naoki Abe, Alan W. Biermann, Philip M. Long
Reinforcement Learning with Immediate Rewards and Linear Hypotheses. Algorithmica 37 (4) (2003)
Sanjoy Dasgupta, Wee Sun Lee, Philip M. Long
A Theoretical Analysis of Query Selection for Collaborative Filtering. Mach. Learn. 51 (3) (2003)
Philip M. Long, Vinsensius Berlian Vega SN
Boosting and Microarray Data. Mach. Learn. 52 (1-2) (2003)
Philip M. Long
An upper bound on the sample complexity of PAC-learning halfspaces with respect to the uniform distribution. Inf. Process. Lett. 87 (5) (2003)
Shai Ben-David, Nadav Eiron, Philip M. Long
On the difficulty of approximately maximizing agreements. J. Comput. Syst. Sci. 66 (3) (2003)
Sanjoy Dasgupta, Philip M. Long
Boosting with Diverse Base Classifiers. COLT (2003)

Philip M. Long.css-eqlu8i{font-size:small;padding-left:4px;}

Publication Activity (10 Years)

Top Topics

Top Venues

Philip M. Long