Pradeep Niroula

PhD student, University of Maryland, College Park

2 papers at NeurIPS 2025

Homepage· OpenReview· Semantic Scholar· Google Scholar

Poster Session 3

Thursday, December 4, 2025 · 11:00 AM → 2:00 PM

A Unified Framework for Provably Efficient Algorithms to Estimate Shapley Values

#1107 · Tyler Chen, Akshay Seshadri, Mattia Jacopo Villani, Pradeep Niroula, Shouvanik Chakrabarti, Archan Ray, Pranav Deshpande, Romina Yalovetzky, Marco Pistoia, Niraj Kumar

We present a unified framework of provably efficient randomized estimators for Shapley values. We also provide, for the first time to our knowledge, provable guarantees for KernelSHAP, the most popular Shapley value method.

Poster Session 4

1 paper

Thursday, December 4, 2025 · 4:30 PM → 7:30 PM

Exhibit Hall C,D,E

The Unseen Threat: Residual Knowledge in Machine Unlearning under Perturbed Samples

#1302 · Hsiang Hsu, Pradeep Niroula, Zichang He, Ivan Brugere, Freddy Lecue, Chun-Fu Chen