research
∙
02/03/2023
ResMem: Learn what you can and memorize the rest
The impressive generalization performance of modern neural networks is a...
share
research
∙
01/30/2023
On student-teacher deviations in distillation: does it pay to disobey?
Knowledge distillation has been widely-used to improve the performance o...
research
∙
10/17/2021
Explaining generalization in deep learning: progress and fundamental limits
This dissertation studies a fundamental open challenge in deep learning ...
research
∙
06/25/2021
Assessing Generalization of SGD via Disagreement
We empirically show that the test error of deep networks can be estimate...
research
∙
11/02/2020
A Learning Theoretic Perspective on Local Explainability
In this paper, we explore connections between interpretable machine lear...
research
∙
10/29/2020
Understanding the Failure Modes of Out-of-Distribution Generalization
Empirical studies suggest that machine learning models often rely on fea...
research
∙
07/07/2020
Provably Safe PAC-MDP Exploration Using Analogies
A key challenge in applying reinforcement learning to safety-critical do...
research
∙
05/30/2019
Deterministic PAC-Bayesian generalization bounds for deep networks via generalizing noise-resilience
The ability of overparameterized deep networks to generalize well has be...
research
∙
02/13/2019
Uniform convergence may be unable to explain generalization in deep learning
We cast doubt on the power of uniform convergence-based generalization b...
research
∙
01/07/2019
Generalization in Deep Networks: The Role of Distance from Initialization
Why does training deep neural networks using stochastic gradient descent...
research
∙
06/07/2018
On Adversarial Risk and Training
In this work we formally define the notions of adversarial perturbations...
research
∙
06/13/2017
Gradient descent GAN optimization is locally stable
Despite the growing prominence of generative adversarial networks (GANs)...
research
∙
11/14/2016