SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2603.07319 · 2026

Shaky Prepend: A Multi-Group Learner with Improved Sample Complexity

Sivaraman Balakrishnan, Daniel Hsu, Lujing Zhang

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 1 functions out of this paper's own repositories and ran 0 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
lujingz/shaky_prepend — 0 of 1
FunctionStatusWhere it lives
shaky_prepend Not yet run lujingz/shaky_prepend/src/shaky_prepend.py
pointer only (licence: NONE) · get_code("3ea6042970881451")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

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

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2603.07319")
get_code_for_paper("2603.07319")
have("2603.07319")

Connect an agent — have() is free.