activity
20182025
most citedA Theoretical Analysis of Contrastive Unsupervised Representation Learning

204 citations · 241 across the 9 of their papers we have counts for

collaborators

9 papers

stat.ML20224 cited

New Definitions and Evaluations for Saliency Methods: Staying Intrinsic, Complete and Sound

Arushi Gupta, Nikunj Saunshi, Dingli Yu +2

Saliency methods compute heat maps that highlight portions of an input that were most {\em important} for the label assigned to it by a deep net. Evaluations of saliency methods co…

cs.LG20221 cited

Understanding Influence Functions and Datamodels via Harmonic Analysis

Nikunj Saunshi, Arushi Gupta, Mark Braverman +1

Influence functions estimate effect of individual data points on predictions of the model on test data and were adapted to deep learning in Koh and Liang [2017]. They have been use…

cs.LG202215 cited

Understanding Contrastive Learning Requires Incorporating Inductive Biases

Nikunj Saunshi, Jordan Ash, Surbhi Goel +5

Contrastive learning is a popular form of self-supervised learning that encourages augmentations (views) of the same input to have more similar representations compared to augmenta…

cs.LG20214 cited

A Representation Learning Perspective on the Importance of Train-Validation Splitting in Meta-Learning

Nikunj Saunshi, Arushi Gupta, Wei Hu

An effective approach in meta-learning is to utilize multiple "train tasks" to learn a good initialization for model parameters that can help solve unseen "test tasks" with very fe…

cs.CL2020

A Mathematical Exploration of Why Language Models Help Solve Downstream Tasks

Nikunj Saunshi, Sadhika Malladi, Sanjeev Arora

Autoregressive language models, pretrained using large text corpora to do well on next word prediction, have been successful at solving many downstream tasks, even with zero-shot u…

cs.LG20206 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…