Picture for Vaishnavh Nagarajan

Vaishnavh Nagarajan

Explaining generalization in deep learning: progress and fundamental limits

Oct 17, 2021
Vaishnavh Nagarajan

Figure 1 for Explaining generalization in deep learning: progress and fundamental limits

Figure 2 for Explaining generalization in deep learning: progress and fundamental limits

Figure 3 for Explaining generalization in deep learning: progress and fundamental limits

Figure 4 for Explaining generalization in deep learning: progress and fundamental limits

* arXiv admin note: text overlap with arXiv:1902.04742

Access Paper or Ask Questions

A Learning Theoretic Perspective on Local Explainability

Nov 02, 2020
Jeffrey Li, Vaishnavh Nagarajan, Gregory Plumb, Ameet Talwalkar

Figure 1 for A Learning Theoretic Perspective on Local Explainability

Figure 2 for A Learning Theoretic Perspective on Local Explainability

Access Paper or Ask Questions

Provably Safe PAC-MDP Exploration Using Analogies

Jul 07, 2020
Melrose Roderick, Vaishnavh Nagarajan, J. Zico Kolter

Figure 1 for Provably Safe PAC-MDP Exploration Using Analogies

Figure 2 for Provably Safe PAC-MDP Exploration Using Analogies

Figure 3 for Provably Safe PAC-MDP Exploration Using Analogies

* 9 pages, 3 figures

Access Paper or Ask Questions

Deterministic PAC-Bayesian generalization bounds for deep networks via generalizing noise-resilience

May 30, 2019
Vaishnavh Nagarajan, J. Zico Kolter

Figure 1 for Deterministic PAC-Bayesian generalization bounds for deep networks via generalizing noise-resilience

Figure 2 for Deterministic PAC-Bayesian generalization bounds for deep networks via generalizing noise-resilience

Figure 3 for Deterministic PAC-Bayesian generalization bounds for deep networks via generalizing noise-resilience

Figure 4 for Deterministic PAC-Bayesian generalization bounds for deep networks via generalizing noise-resilience

* Published as a conference paper at ICLR 2019

Access Paper or Ask Questions

Uniform convergence may be unable to explain generalization in deep learning

Apr 02, 2019
Vaishnavh Nagarajan, J. Zico Kolter

Figure 1 for Uniform convergence may be unable to explain generalization in deep learning

Figure 2 for Uniform convergence may be unable to explain generalization in deep learning

Figure 3 for Uniform convergence may be unable to explain generalization in deep learning

Figure 4 for Uniform convergence may be unable to explain generalization in deep learning

Access Paper or Ask Questions