activity
20242026
collaborators

7 papers

cs.LG2026

Auditing of Unlearning Algorithms

Sahasrajit Sarmasarkar, Anastasia Koloskova, Sanmi Koyejo

Evaluating whether unlearning algorithms truly remove training data influence remains an open challenge. We propose a practical auditor that computes data-dependent lower bounds on…

stat.ML2026

Shuffle and Joint Differential Privacy for Generalized Linear Contextual Bandits

Sahasrajit Sarmasarkar

We present the first algorithms for generalized linear contextual bandits under shuffle differential privacy and joint differential privacy. While prior work on private contextual…

cs.LG2025

Preference Learning with Response Time: Robust Losses and Guarantees

Ayush Sawarni, Sahasrajit Sarmasarkar, Vasilis Syrgkanis

This paper investigates the integration of response time data into human preference learning frameworks for more effective reward model elicitation. While binary preference data ha…

cs.LG2025

Multi-Selection for Recommendation Systems

Sahasrajit Sarmasarkar, Zhihao Jiang, Ashish Goel +2

We present the construction of a multi-selection model to answer differentially private queries in the context of recommendation systems. The server sends back multiple recommendat…

cs.LG2025

A Characterization of List Regression

Chirag Pabbaraju, Sahasrajit Sarmasarkar

There has been a recent interest in understanding and characterizing the sample complexity of list learning tasks, where the learning algorithm is allowed to make a short list of $…

cs.DC2025

Optimal moments on redundancies in job cloning

Sahasrajit Sarmasarkar, Harish Pillai

We consider the problem of job assignment where a master server aims to compute some tasks and is provided a few child servers to compute under a uniform straggling pattern where e…