9 papers
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…
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…
How Global Calibration Strengthens Multiaccuracy
SÃlvia 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…
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…
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…
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…