collaborators

7 papers

cs.CY2026

Simulating Eutopia: Revisiting Long-term Fairness with Outcomes, Performativity, and Dynamics

Vedant Palit, Udvas Das, Brahim Driss +1

As AI-driven Decision Makers (ADMs) influence our socioeconomic reality, their roles in both enhancing efficiency and amplifying the social biases have drawn attention. In this pap…

cs.LG2026

Bandits for Efficient Experimentation: Adapting to Control Group, Preferences, and Context Drifts

Udvas Das, Waris Radji, Debabrota Basu +1

We consider a variant of the linear contextual stochastic multi-armed bandits, where the learner must provide recommendations to a group of users, each having its personalized pref…

cs.LG2026

Learning to Explore with Lagrangians for Bandits under Unknown Linear Constraints

Udvas Das, Debabrota Basu

Pure exploration in bandits formalises multiple real-world problems, such as tuning hyper-parameters or conducting user studies to test a set of items, where different safety, reso…

cs.LG2026

Performative Policy Gradient: Optimality in Performative Reinforcement Learning

Debabrota Basu, Udvas Das, Brahim Driss +1

Post-deployment machine learning algorithms often influence the environments they act in, and thus shift the underlying dynamics that the standard reinforcement learning (RL) metho…

cs.CG2025

Witness Set in Monotone Polygons: Exact and Approximate

Udvas Das, Binayak Dutta, Satyabrata Jana +2

Given a simple polygon , two points and within are {\em visible} to each other if the line segment between and is contained in $\mathscr{…

cs.LG2025

FraPPE: Fast and Efficient Preference-based Pure Exploration

Udvas Das, Apurv Shukla, Debabrota Basu

Preference-based Pure Exploration (PrePEx) aims to identify with a given confidence level the set of Pareto optimal arms in a vector-valued (aka multi-objective) bandit, where the…