Philip M. Long
26 papers · 2002–2024 · 5 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+11 more ↓ Show less ↑
π£ Hot Topic Early Bird π Interdisciplinary Bridge π§ Keyword Pioneer πΊοΈ Taxonomy Completionist (12) π Conference Polyglot (5)
π
Renaissance Researcher
(5)
π§
Keyword Pioneer
π
Academic Marathon
(22)
π¬
Deep Specialist
(13)
π
Keyword Champion
π
Century Club
(26)
ποΈ
Keyword Collector
(55)
π₯
Unstoppable
(8)
π
Trend Setter
π
Conference Pioneer
β
The Questioner
(2)
Conferences
JMLR (16)
COLT (3)
ICLR (3)
ALT (2)
NIPS (2)
Top co-authors
Keywords
learning theory
(4)
gradient descent
(4)
deep network
(4)
excess risk
(4)
benign overfitting
(3)
sample complexity
(3)
logistic loss
(3)
online learning
(3)
neural network optimization
(2)
pac learning
(2)
neural network
(2)
sharpness-aware minimization
(2)
generalization bound
(2)
weight decay
(2)
mistake bound
(2)
linear regression
(2)
dropout regularization
(2)
linear classifier
(2)
gradient flow
(2)
text categorization
(1)
Papers
Sharpness-Aware Minimization and the Edge of Stability
JMLR 2024
Deep linear networks can benignly overfit when shallow ones do
JMLR 2023
The Dynamics of Sharpness-Aware Minimization: Bouncing Across Ravines and Drifting Towards Wide Minima
JMLR 2023
Foolish Crowds Support Benign Overfitting
JMLR 2022
The Interplay Between Implicit Bias and Benign Overfitting in Two-Layer Linear Networks
JMLR 2022
When Does Gradient Descent with Logistic Loss Find Interpolating Two-Layer Networks?
JMLR 2021
Failures of Model-dependent Generalization Bounds for Least-norm Interpolation
JMLR 2021
When does gradient descent with logistic loss interpolate using deep networks with smoothed ReLU activations?
COLT 2021
Finite-sample Analysis of Interpolating Linear Classifiers in the Overparameterized Regime
JMLR 2021
Generalization bounds for deep convolutional neural networks
ICLR 2020
On the Complexity of Proper Distribution-Free Learning of Linear Classifiers
ALT 2020
Learning Sums of Independent Random Variables with Sparse Collective Support
JMLR 2020
On the Global Convergence of Training Deep Linear ResNets
ICLR 2020
The Singular Values of Convolutional Layers
ICLR 2019
Surprising properties of dropout in deep networks
JMLR 2018
New bounds on the price of bandit feedback for mistake-bounded online multiclass learning
ALT 2017
Surprising properties of dropout in deep networks
COLT 2017
On the Inductive Bias of Dropout
JMLR 2015
Algorithms and Hardness Results for Parallel Large Margin Learning
JMLR 2013
On the Necessity of Irrelevant Variables
JMLR 2012
New Bounds for Learning Intervals with Implications for Semi-Supervised Learning
COLT 2012
Learning Halfspaces with Malicious Noise
JMLR 2009
Online Learning of Multiple Tasks with a Shared Loss
JMLR 2007
Attribute-efficient learning of decision lists and linear threshold functions under unconcentrated distributions
NIPS 2006
Learnability and the doubling dimension
NIPS 2006
Introduction to the Special Issue on Computational Learning Theory
JMLR 2002