3 papers
cs.LG2026
Cascading Bandits With Feedback
R Sri Prakash, Nikhil Karamchandani, Sharayu Moharir
Motivated by the challenges of edge inference, we study a variant of the cascade bandit model in which each arm corresponds to an inference model with an associated accuracy and er…
cs.LG2025
Observation-Free Attacks on Online Learning to Rank
Sameep Chattopadhyay, Nikhil Karamchandani, Sharayu Moharir
Online learning to rank (OLTR) plays a critical role in information retrieval and machine learning systems, with a wide range of applications in search engines and content recommen…
cs.IT2025
Byzantine-Resilient Distributed Computation via Task Replication and Local Computations
Aayush Rajesh, Nikhil Karamchandani, Vinod M. Prabhakaran
We study a distributed computation problem in the presence of Byzantine workers where a central node wishes to solve a task that is divided into independent sub-tasks, each of whic…