activity
20122025
most citedGuarantees for Spectral Clustering with Fairness Constraints

46 citations · 165 across the 45 of their papers we have counts for

collaborators
Showing 2022Show all

9 papers · 1 filter

cs.CL2022★ 1 cited

Maximizing Use-Case Specificity through Precision Model Tuning

Pranjali Awasthi, David Recio-Mitter, Yosuke Kyle Sugi

Language models have become increasingly popular in recent years for tasks like information retrieval. As use-cases become oriented toward specific domains, fine-tuning becomes def…

cs.LG2022★ 1 cited

On the Adversarial Robustness of Mixture of Experts

Joan Puigcerver, Rodolphe Jenatton, Carlos Riquelme +2

Adversarial robustness is a key desirable property of neural networks. It has been empirically shown to be affected by their sizes, with larger networks being typically more robust…

cs.LG2022

Agnostic Learning of General ReLU Activation Using Gradient Descent

Pranjal Awasthi, Alex Tang, Aravindan Vijayaraghavan

We provide a convergence analysis of gradient descent for the problem of agnostically learning a single ReLU function with moderate bias under Gaussian distributions. Unlike prior…

cs.LG2022★ 1 cited

Individual Preference Stability for Clustering

Saba Ahmadi, Pranjal Awasthi, Samir Khuller +4

In this paper, we propose a natural notion of individual preference (IP) stability for clustering, which asks that every data point, on average, is closer to the points in its own…

cs.LG2022★ 10 cited

Do More Negative Samples Necessarily Hurt in Contrastive Learning?

Pranjal Awasthi, Nishanth Dikkala, Pritish Kamath

Recent investigations in noise contrastive estimation suggest, both empirically as well as theoretically, that while having more "negative samples" in the contrastive loss improves…

cs.LG2022

Trimmed Maximum Likelihood Estimation for Robust Learning in Generalized Linear Models

Pranjal Awasthi, Abhimanyu Das, Weihao Kong +1

We study the problem of learning generalized linear models under adversarial corruptions. We analyze a classical heuristic called the iterative trimmed maximum likelihood estimator…