Philip M. Long

16 catalog papers. Name-matched publications do not establish a verified researcher identity.

Publications

• Sharpness-Aware Minimization and the Edge of Stability — Journal of Machine Learning Research 2024
• The Dynamics of Sharpness-Aware Minimization: Bouncing Across Ravines and Drifting Towards Wide Minima — Journal of Machine Learning Research 2023
• Deep linear networks can benignly overfit when shallow ones do — Journal of Machine Learning Research 2023
• Foolish Crowds Support Benign Overfitting — Journal of Machine Learning Research 2022
• The Interplay Between Implicit Bias and Benign Overfitting in Two-Layer Linear Networks — Journal of Machine Learning Research 2022
• Failures of Model-dependent Generalization Bounds for Least-norm Interpolation — Journal of Machine Learning Research 2021
• When Does Gradient Descent with Logistic Loss Find Interpolating Two-Layer Networks? — Journal of Machine Learning Research 2021
• Finite-sample Analysis of Interpolating Linear Classifiers in the Overparameterized Regime — Journal of Machine Learning Research 2021
• Learning Sums of Independent Random Variables with Sparse Collective Support — Journal of Machine Learning Research 2020
• Surprising properties of dropout in deep networks — Journal of Machine Learning Research 2017
• On the Inductive Bias of Dropout — Journal of Machine Learning Research 2015
• Algorithms and Hardness Results for Parallel Large Margin Learning — Journal of Machine Learning Research 2013
• On the Necessity of Irrelevant Variables — Journal of Machine Learning Research 2012
• Learning Halfspaces with Malicious Noise — Journal of Machine Learning Research 2009
• Online Learning of Multiple Tasks with a Shared Loss — Journal of Machine Learning Research 2007
• Introduction to the Special Issue on Computational Learning Theory — Journal of Machine Learning Research 2002