12 citations · 12 across the 4 of their papers we have counts for
4 papers
Data-Centric Debugging: mitigating model failures via targeted data collection
Sahil Singla, Atoosa Malemir Chegini, Mazda Moayeri +1
Deep neural networks can be unreliable in the real world when the training set does not adequately cover all the settings where they are deployed. Focusing on image classification,…
Online and Bandit Algorithms Beyond Norms
Thomas Kesselheim, Marco Molinaro, Sahil Singla
Vector norms play a fundamental role in computer science and optimization, so there is an ongoing effort to generalize existing algorithms to settings beyond and $\el…
Low Curvature Activations Reduce Overfitting in Adversarial Training
Vasu Singla, Sahil Singla, David Jacobs +1
Adversarial training is one of the most effective defenses against adversarial attacks. Previous works suggest that overfitting is a dominant phenomenon in adversarial training lea…
Online Matroid Intersection: Beating Half for Random Arrival
Guru Guruganesh, Sahil Singla
For two matroids and defined on the same ground set , the online matroid intersection problem is to design an algorithm that constructs a large c…