paper-with-me

홈 › Papers

Group-wise oracle-efficient algorithms for online multi-group learning

2024-06-07 · Samuel Deng, Daniel Hsu, Jingwen Liu

We study the problem of online multi-group learning, a learning model in which an online learner must simultaneously achieve small prediction regret on a large collection of (possibly overlapping) subsequences corresponding to a family of groups. Groups are subsets of the context space, and in fairness applications, they may correspond to subpopulations defined by expressive functions of demographic attributes. In contrast to previous work on this learning model, we consider scenarios in which the family of groups is too large to explicitly enumerate, and hence we seek algorithms that only access groups via an optimization oracle. In this paper, we design such oracle-efficient algorithms with sublinear regret under a variety of settings, including: (i) the i.i.d. setting, (ii) the adversarial setting with smoothed context distributions, and (iii) the adversarial transductive setting.

📄 PDF Abstract BibTeX arXiv:2406.05287

Code (0)

등록된 구현이 없습니다.

Tasks

Fairness

Similar Papers 제목 키워드 기반

Oracle Efficient Algorithms for Groupwise Regret

2023-10-07 · Krishna Acharya, Eshwar Ram Arunachaleswaran, Sampath Kannan, Aaron Roth 외

We study the problem of online prediction, in which at each time step $t$, an individual $x_t$ arrives, whose label we must predict. Each individual is associated with various groups, defined based on their features such…

Combinatorial Optimization

Fair Active Ranking from Pairwise Preferences

2024-02-05 · Sruthi Gorantla, Sara Ahmadian

We investigate the problem of probably approximately correct and fair (PACF) ranking of items by adaptively evoking pairwise comparisons. Given a set of $n$ items that belong to disjoint groups, our goal is to find an $(…

Fairness

Spatially Adaptive Online Prediction of Piecewise Regular Functions

2022-03-30 · Sabyasachi Chatterjee, Subhajit Goswami

We consider the problem of estimating piecewise regular functions in an online setting, i.e., the data arrive sequentially and at any round our task is to predict the value of the true function at the next revealed point…

Prediction

Oracle Efficient Online Multicalibration and Omniprediction

2023-07-18 · Sumegha Garg, Christopher Jung, Omer Reingold, Aaron Roth

A recent line of work has shown a surprising connection between multicalibration, a multi-group fairness notion, and omniprediction, a learning paradigm that provides simultaneous loss minimization guarantees for a large…

Fairness

Improved and Oracle-Efficient Online $\ell_1$-Multicalibration

2025-05-23 · Rohan Ghuge, Vidya Muthukumar, Sahil Singla

We study \emph{online multicalibration}, a framework for ensuring calibrated predictions across multiple groups in adversarial settings, across $T$ rounds. Although online calibration is typically studied in the $\ell_1$…