Signals 4 · free daily AI digest

Algorithmic stability via ensembling

Paper recorded by Signals 4 on 2026-09-09 in cs.LG. Abstract reproduced from arXiv; link to the original below.

Published 2026-09-09 on arXiv · recorded by Signals 4 on 2026-09-10

Category: cs.LG · 机器学习 · first seen 2026-09-10

Abstract

Algorithmic stability refers to the property of an algorithm being insensitive to perturbations of the input data, where the type of perturbation may vary depending on the setting. In this work, we develop a general framework to quantify the extent to which any ensembling strategy defined via averaging can yield stability guarantees for any type of data perturbation. Our main theoretical result is

Read on arXiv →

#89 most recent of 215 cs.LG papers we have recorded · ↑ newer: Multi-Agent Reinforcement Learning for Autonomous UAV Exploration in W · ↓ older: HybridFLow: SDN-Orchestrated Client Partitioning for Hybrid Federated
Cite this page: Algorithmic stability via ensembling: the #89 most recent of 215 cs.LG papers we have recorded (as of 2026-09-09). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/algorithmic-stability-via-ensembling.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable: papers.json
Related: More cs.LG papers · arXiv signals · All papers · Today in AI
Get 4 AI signals a day by email — free.
Subscribe free → See all plans →
Get 4 AI signals a day by email — free
All models · All repos · By company · Daily editions