Simple and near-optimal algorithms for hidden stratification and multi-group learning

• URL: http://arxiv.org/abs/2112.12181v2
• Date: Fri, 14 Jun 2024 19:39:04 GMT
• Title: Simple and near-optimal algorithms for hidden stratification and multi-group learning
• Authors: Christopher Tosh, Daniel Hsu,
• Abstract summary: This paper studies the structure of solutions to the multi-group learning problem. It provides simple and near-optimal algorithms for the learning problem.
• Score: 13.337579367787253
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Multi-group agnostic learning is a formal learning criterion that is concerned with the conditional risks of predictors within subgroups of a population. The criterion addresses recent practical concerns such as subgroup fairness and hidden stratification. This paper studies the structure of solutions to the multi-group learning problem, and provides simple and near-optimal algorithms for the learning problem.

Related papers

• Group-wise oracle-efficient algorithms for online multi-group learning [12.664869982542895]
  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 subsequences corresponding to a family of groups. In this paper, we design such oracle-efficient algorithms with sublinear regret under a variety of settings, including adversarial and adversarial transductive settings.
  arXiv  Detail & Related papers  (2024-06-07T23:00:02Z)
• Multi-group Learning for Hierarchical Groups [12.473780585666768]
  We extend the study of multi-group learning to the natural case where the groups are hierarchically structured. We design an algorithm for this setting that outputs an interpretable and deterministic decision tree predictor with near-optimal sample complexity.
  arXiv  Detail & Related papers  (2024-02-01T01:06:32Z)
• A structured regression approach for evaluating model performance across intersectional subgroups [53.91682617836498]
  Disaggregated evaluation is a central task in AI fairness assessment, where the goal is to measure an AI system's performance across different subgroups. We introduce a structured regression approach to disaggregated evaluation that we demonstrate can yield reliable system performance estimates even for very small subgroups.
  arXiv  Detail & Related papers  (2024-01-26T14:21:45Z)
• Group conditional validity via multi-group learning [5.797821810358083]
  We consider the problem of distribution-free conformal prediction and the criterion of group conditional validity. Existing methods achieve such guarantees under either restrictive grouping structure or distributional assumptions. We propose a simple reduction to the problem of achieving validity guarantees for individual populations by leveraging algorithms for a problem called multi-group learning.
  arXiv  Detail & Related papers  (2023-03-07T15:51:03Z)
• Outlier-Robust Group Inference via Gradient Space Clustering [50.87474101594732]
  Existing methods can improve the worst-group performance, but they require group annotations, which are often expensive and sometimes infeasible to obtain. We address the problem of learning group annotations in the presence of outliers by clustering the data in the space of gradients of the model parameters. We show that data in the gradient space has a simpler structure while preserving information about minority groups and outliers, making it suitable for standard clustering methods like DBSCAN.
  arXiv  Detail & Related papers  (2022-10-13T06:04:43Z)
• Focus on the Common Good: Group Distributional Robustness Follows [47.62596240492509]
  This paper proposes a new and simple algorithm that explicitly encourages learning of features that are shared across various groups. While Group-DRO focuses on groups with worst regularized loss, focusing instead, on groups that enable better performance even on other groups, could lead to learning of shared/common features.
  arXiv  Detail & Related papers  (2021-10-06T09:47:41Z)
• Algorithm Selection on a Meta Level [58.720142291102135]
  We introduce the problem of meta algorithm selection, which essentially asks for the best way to combine a given set of algorithm selectors. We present a general methodological framework for meta algorithm selection as well as several concrete learning methods as instantiations of this framework.
  arXiv  Detail & Related papers  (2021-07-20T11:23:21Z)
• Certifiably Polynomial Algorithm for Best Group Subset Selection [0.9667631210393929]
  Best group subset selection aims to choose a small part of non-overlapping groups to achieve the best interpretability on the response variable. We propose a group-splicing algorithm that iteratively detects effective groups and excludes the helpless ones. We demonstrate the efficiency and accuracy of our proposal by comparing state-of-the-art algorithms on both synthetic and real-world datasets.
  arXiv  Detail & Related papers  (2021-04-23T03:05:11Z)
• Provably Efficient Exploration for Reinforcement Learning Using Unsupervised Learning [96.78504087416654]
  Motivated by the prevailing paradigm of using unsupervised learning for efficient exploration in reinforcement learning (RL) problems, we investigate when this paradigm is provably efficient. We present a general algorithmic framework that is built upon two components: an unsupervised learning algorithm and a noregret tabular RL algorithm.
  arXiv  Detail & Related papers  (2020-03-15T19:23:59Z)
• Optimal Clustering from Noisy Binary Feedback [75.17453757892152]
  We study the problem of clustering a set of items from binary user feedback. We devise an algorithm with a minimal cluster recovery error rate. For adaptive selection, we develop an algorithm inspired by the derivation of the information-theoretical error lower bounds.
  arXiv  Detail & Related papers  (2019-10-14T09:18:26Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.