activity
20172021
most citedDo GANs actually learn the distribution? An empirical study

126 citations · 160 across the 6 of their papers we have counts for

collaborators
Showing cs.LGShow all

7 papers · 1 filter

cs.LG2021★ 2 cited

Rip van Winkle's Razor: A Simple Estimate of Overfit to Test Data

Sanjeev Arora, Yi Zhang

Traditional statistics forbids use of test data (a.k.a. holdout data) during training. Dwork et al. 2015 pointed out that current practices in machine learning, whereby researchers…

cs.LG2020★ 6 cited

A Sample Complexity Separation between Non-Convex and Convex Meta-Learning

Nikunj Saunshi, Yi Zhang, Mikhail Khodak +1

One popular trend in meta-learning is to learn from many training tasks a common initialization for a gradient-based method that can be used to solve a new task with few samples. T…

cs.LG2020★ 7 cited

Over-parameterized Adversarial Training: An Analysis Overcoming the Curse of Dimensionality

Yi Zhang, Orestis Plevrakis, Simon S. Du +3

Adversarial training is a popular method to give neural nets robustness against adversarial perturbations. In practice adversarial training leads to low robust training loss. Howev…

cs.LG2019

Explaining Landscape Connectivity of Low-cost Solutions for Multilayer Nets

Rohith Kuditipudi, Xiang Wang, Holden Lee +5

Mode connectivity is a surprising phenomenon in the loss landscape of deep nets. Optima -- at least those discovered by gradient-based optimization -- turn out to be connected by s…

cs.LG2018

Stronger generalization bounds for deep nets via a compression approach

Sanjeev Arora, Rong Ge, Behnam Neyshabur +1

Deep nets generalize well despite having more parameters than the number of training samples. Recent works try to give an explanation using PAC-Bayes and Margin-based analyses, but…

cs.LG2017★ 16 cited

Theoretical limitations of Encoder-Decoder GAN architectures

Sanjeev Arora, Andrej Risteski, Yi Zhang

Encoder-decoder GANs architectures (e.g., BiGAN and ALI) seek to add an inference mechanism to the GANs setup, consisting of a small encoder deep net that maps data-points to their…