Signals 4 · free daily AI digest

One Loop, Two Gains: Can Active Learning win the Lottery for Free?

Paper recorded by Signals 4 on 2026-09-09 in cs.AI. 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.AI · 人工智能 · first seen 2026-09-10

Abstract

The lottery ticket hypothesis posits the existence of winning tickets: sparse subnetworks that, when trained in isolation from their original initialization, match the accuracy of the full dense network. The predominant method for discovering such tickets, iterative magnitude pruning, alternates pruning with full retraining from scratch until convergence over many cycles. Similarly, deep active le

Read on arXiv →

#137 most recent of 300 cs.AI papers we have recorded · ↑ newer: TRACE: Training Reasoning Agents for Causal Exploration with Synthesiz · ↓ older: RiLM: Parameter-Efficient Language Modeling via Geodesic Decoding
Cite this page: One Loop, Two Gains: Can Active Learning win the Lottery for Free?: the #137 most recent of 300 cs.AI papers we have recorded (as of 2026-09-09). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/one-loop-two-gains-can-active-learning-win-the-lottery-for-free.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable: papers.json
Related: More cs.AI 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