activity
20172026
most citedSkill-Mix: a Flexible and Expandable Family of Evaluations for AI models

6 citations · 20 across the 7 of their papers we have counts for

collaborators
Showing cs.LGShow all

6 papers · 1 filter

cs.LG2026

RubiConv -- Efficient Boundary-Respecting Convolutions

Linda Friso, Annie Marsden, Xinyi Chen +4

Convolutional architectures have emerged as powerful alternatives to Transformers for sequence modeling. The primary advantage is that they offer improved theoretical sequence leng…

cs.LG2023

Online Nonstochastic Model-Free Reinforcement Learning

Udaya Ghai, Arushi Gupta, Wenhan Xia +2

We investigate robust model-free reinforcement learning algorithms designed for environments that may be dynamic or even adversarial. Traditional state-based policies often struggl…

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.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.LG2020

Inherent Noise in Gradient Based Methods

Arushi Gupta

Previous work has examined the ability of larger capacity neural networks to generalize better than smaller ones, even without explicit regularizers, by analyzing gradient based al…

cs.LG20195 cited

A Simple Saliency Method That Passes the Sanity Checks

Arushi Gupta, Sanjeev Arora

There is great interest in "saliency methods" (also called "attribution methods"), which give "explanations" for a deep net's decision, by assigning a "score" to each feature/pixel…