1 citations · 2 across the 5 of their papers we have counts for
7 papers
Efficient Swap Multicalibration of Elicitable Properties
Lunjia Hu, Haipeng Luo, Spandan Senapati +1
Multicalibration [HJKRR18] is an algorithmic fairness perspective that demands that the predictions of a predictor are correct conditional on themselves and membership in a collect…
Improved Bounds for Swap Multicalibration and Swap Omniprediction
Haipeng Luo, Spandan Senapati, Vatsal Sharan
In this paper, we consider the related problems of multicalibration -- a multigroup fairness notion and omniprediction -- a simultaneous loss minimization paradigm, both in the dis…
Simultaneous Swap Regret Minimization via KL-Calibration
Haipeng Luo, Spandan Senapati, Vatsal Sharan
Calibration is a fundamental concept that aims at ensuring the reliability of probabilistic predictions by aligning them with real-world outcomes. There is a surge of studies on ne…
Optimal Multiclass U-Calibration Error and Beyond
Haipeng Luo, Spandan Senapati, Vatsal Sharan
We consider the problem of online multiclass U-calibration, where a forecaster aims to make sequential distributional predictions over classes with low U-calibration error, tha…
Online Convex Optimization with Switching Cost and Delayed Gradients
Spandan Senapati, Rahul Vaze
We consider the online convex optimization (OCO) problem with quadratic and linear switching cost in the limited information setting, where an online algorithm can choose its actio…
Sharpened Lazy Incremental Quasi-Newton Method
Aakash Lahoti, Spandan Senapati, Ketan Rajawat +1
The problem of minimizing the sum of functions in dimensions is ubiquitous in machine learning and statistics. In many applications where the number of observations is…
Proximal Algorithms for Smoothed Online Convex Optimization with Predictions
Spandan Senapati, Ashwin Shenai, Ketan Rajawat
We consider a smoothed online convex optimization (SOCO) problem with predictions, where the learner has access to a finite lookahead window of time-varying stage costs, but suffer…