activity
20192024
most citedRetouchdown: Adding Touchdown to StreetLearn as a Shareable Resource for Language Grounding Tasks in Street View

20 citations · 48 across the 8 of their papers we have counts for

collaborators
Showing cs.LGShow all

6 papers · 1 filter

cs.LG20222 cited

Differentially Private Image Classification from Features

Harsh Mehta, Walid Krichene, Abhradeep Thakurta +2

Leveraging transfer learning has recently been shown to be an effective strategy for training large models with Differential Privacy (DP). Moreover, somewhat surprisingly, recent w…

cs.LG20222 cited

Convexifying Transformers: Improving optimization and understanding of transformer networks

Tolga Ergen, Behnam Neyshabur, Harsh Mehta

Understanding the fundamental mechanism behind the success of transformer networks is still an open problem in the deep learning literature. Although their remarkable performance h…

cs.LG20225 cited

Large Scale Transfer Learning for Differentially Private Image Classification

Harsh Mehta, Abhradeep Thakurta, Alexey Kurakin +1

Differential Privacy (DP) provides a formal framework for training machine learning models with individual example level privacy. In the field of deep learning, Differentially Priv…

cs.LG20213 cited

High-probability Bounds for Non-Convex Stochastic Optimization with Heavy Tails

Ashok Cutkosky, Harsh Mehta

We consider non-convex stochastic optimization using first-order algorithms for which the gradient estimates may have heavy tails. We show that a combination of gradient clipping,…

cs.LG2020

Momentum Improves Normalized SGD

Ashok Cutkosky, Harsh Mehta

We provide an improved analysis of normalized SGD showing that adding momentum provably removes the need for large batch sizes on non-convex objectives. Then, we consider the case…

cs.LG20197 cited

VALAN: Vision and Language Agent Navigation

Larry Lansing, Vihan Jain, Harsh Mehta +2

VALAN is a lightweight and scalable software framework for deep reinforcement learning based on the SEED RL architecture. The framework facilitates the development and evaluation o…