ShakyPrepend: A Multi-Group Learner with Improved Sample Complexity

Lujing Zhang, Daniel Hsu, Sivaraman Balakrishnan
3/7/2026
cs.LG

No confident code implementation found for this paper. 1 possible match can be shown below.

Abstract

Multi-group learning is a learning task that focuses on controlling predictors' conditional losses over specified subgroups. We propose ShakyPrepend, a method that leverages tools inspired by differential privacy to obtain improved theoretical guarantees over existing approaches. Through numerical experiments, we demonstrate that ShakyPrepend adapts to both group structure and spatial heterogeneity. We provide practical guidance for deploying multi-group learning algorithms in real-world settings.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. 1 weaker match is hidden by default — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Group-realizable multi-group learning by minimizing empirical risk

80% match2026

Multi-Task Differential Privacy Under Distribution Skew

78% match2023

Multigroup Robustness

78% match2024

Multi-group Learning for Hierarchical Groups

78% match2026

A Bayesian Approach for Personalized Federated Learning in Heterogeneous Settings

77% match2026

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

77% match2024

Cite this paper

@article{zhang2026shakyprepend,
  title  = {ShakyPrepend: A Multi-Group Learner with Improved Sample Complexity},
  author = {Lujing Zhang and Daniel Hsu and Sivaraman Balakrishnan},
  year   = {2026},
  eprint = {2603.07319},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2603.07319v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2603.07319.svg)](https://codeofpaper.com/paper/2603.07319)

Discussion