activity
20162022
most citedLow-Pass Filtering SGD for Recovering Flat Optima in the Deep Learning Optimization Landscape

4 citations · 10 across the 5 of their papers we have counts for

collaborators

15 papers

cs.LG20224 cited

Low-Pass Filtering SGD for Recovering Flat Optima in the Deep Learning Optimization Landscape

Devansh Bisla, Jing Wang, Anna Choromanska

In this paper, we study the sharpness of a deep learning (DL) loss landscape around local minima in order to reveal systematic mechanisms underlying the generalization abilities of…

cs.LG2021

A Theoretical-Empirical Approach to Estimating Sample Complexity of DNNs

Devansh Bisla, Apoorva Nandini Saridena, Anna Choromanska

This paper focuses on understanding how the generalization error scales with the amount of the training data for deep neural networks (DNNs). Existing techniques in statistical lea…

quant-ph20201 cited

Approximating Ground State Energies and Wave Functions of Physical Systems with Neural Networks

Cesar Lema, Anna Choromanska

Quantum theory has been remarkably successful in providing an understanding of physical systems at foundational scales. Solving the Schrödinger equation provides full knowledge of…

cs.LG2020

SGB: Stochastic Gradient Bound Method for Optimizing Partition Functions

Jing Wang, Anna Choromanska

This paper addresses the problem of optimizing partition functions in a stochastic learning setting. We propose a stochastic variant of the bound majorization algorithm that relies…

cs.RO20203 cited

Multi-modal Experts Network for Autonomous Driving

Shihong Fang, Anna Choromanska

End-to-end learning from sensory data has shown promising results in autonomous driving. While employing many sensors enhances world perception and should lead to more robust and r…

cs.LG2019

Learning to Score Behaviors for Guided Policy Optimization

Aldo Pacchiano, Jack Parker-Holder, Yunhao Tang +3

We introduce a new approach for comparing reinforcement learning policies, using Wasserstein distances (WDs) in a newly defined latent behavioral space. We show that by utilizing t…