activity
20242026
collaborators

9 papers

cs.LG2026

Flexible Routing via Uncertainty Decomposition

Charlotte Peale, Siddartha Devic, Parikshit Gopalan +2

A key strategy for balancing performance and cost in modern machine learning systems is to dynamically route queries to either a low-cost model or a more expensive oracle (such as…

cs.LG2026

The Importance of Being Smoothly Calibrated

Parikshit Gopalan, Konstantinos Stavropoulos, Kunal Talwar +1

Recent work has highlighted the centrality of smooth calibration [Kakade and Foster, 2008] as a robust measure of calibration error. We generalize, unify, and extend previous resul…

cs.LG2026

How Global Calibration Strengthens Multiaccuracy

Sílvia Casacuberta, Parikshit Gopalan, Varun Kanade +1

Multiaccuracy and multicalibration are multigroup fairness notions for prediction that have found numerous applications in learning and computational complexity. They can be achiev…

cs.CC2025

The communication complexity of distributed estimation

Parikshit Gopalan, Raghu Meka, Prasad Raghavendra +2

We study an extension of the standard two-party communication model in which Alice and Bob hold probability distributions and over domains and , respectively. Their…

cs.LG2025

Efficient Calibration for Decision Making

Parikshit Gopalan, Konstantinos Stavropoulos, Kunal Talwar +1

A decision-theoretic characterization of perfect calibration is that an agent seeking to minimize a proper loss in expectation cannot improve their outcome by post-processing a per…

cs.LG2025

Calibration through the Lens of Indistinguishability

Parikshit Gopalan, Lunjia Hu

Calibration is a classical notion from the forecasting literature which aims to address the question: how should predicted probabilities be interpreted? In a world where we only ge…