Signals 4 · free daily AI digest

Even Sharper Bounds for Transductive Learning and Its Applications

Paper recorded by Signals 4 on 2026-09-23 in cs.LG. Abstract reproduced from arXiv; link to the original below.

Published 2026-09-23 on arXiv · recorded by Signals 4 on 2026-09-24

Category: cs.LG · 机器学习 · first seen 2026-09-24

Abstract

We introduce Sharper Transductive Local Complexity (STLC), a localized complexity method for transductive learning under uniform sampling without replacement. The construction starts from a Bernstein-type concentration inequality for the supremum of the test--train empirical process. Its proof uses the modified log-Sobolev inequality for the swap walk and a two-parameter entropy closure. A peeling

Read on arXiv →

#3 most recent of 278 cs.LG papers we have recorded · ↑ newer: Contrastive Learning for Authorship Verification · ↓ older: Nonequilibrium Phases of Repulsive Self-Attention: Chaos, Attention Co

Cite this page: Even Sharper Bounds for Transductive Learning and Its Applications: the #3 most recent of 278 cs.LG papers we have recorded (as of 2026-09-23). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/even-sharper-bounds-for-transductive-learning-and-its-applications.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