activity
20172023
most citedBridging Mode Connectivity in Loss Landscapes and Adversarial Robustness

33 citations · 136 across the 23 of their papers we have counts for

collaborators
Showing 2020Show all

11 papers · 1 filter

cs.LG20201 cited

Self-Progressing Robust Training

Minhao Cheng, Pin-Yu Chen, Sijia Liu +3

Enhancing model robustness under new and even adversarial environments is a crucial milestone toward building trustworthy machine learning systems. Current robust training methods…

cs.LG20207 cited

Optimizing Mode Connectivity via Neuron Alignment

N. Joseph Tatro, Pin-Yu Chen, Payel Das +3

The loss landscapes of deep neural networks are not well understood due to their high nonconvexity. Empirically, the local minima of these loss functions can be connected by a lear…

cs.CL2020

DualTKB: A Dual Learning Bridge between Text and Knowledge Base

Pierre L. Dognin, Igor Melnyk, Inkit Padhi +2

In this work, we present a dual learning approach for unsupervised text to path and path to text transfers in Commonsense Knowledge Bases (KBs). We investigate the impact of weak s…

q-bio.QM20204 cited

Explaining Chemical Toxicity using Missing Features

Kar Wai Lim, Bhanushee Sharma, Payel Das +2

Chemical toxicity prediction using machine learning is important in drug development to reduce repeated animal and human testing, thus saving cost and time. It is highly recommende…

cs.LG2020

Active learning of deep surrogates for PDEs: Application to metasurface design

Raphaël Pestourie, Youssef Mroueh, Thanh V. Nguyen +2

Surrogate models for partial-differential equations are widely used in the design of meta-materials to rapidly evaluate the behavior of composable components. However, the training…

cs.LG2020

Combinatorial Black-Box Optimization with Expert Advice

Hamid Dadkhahi, Karthikeyan Shanmugam, Jesus Rios +4

We consider the problem of black-box function optimization over the boolean hypercube. Despite the vast literature on black-box function optimization over continuous domains, not m…