arXiv Machine Learning August 14, 2026 By Jianwei Lou (RailMind Systems, Neuss, Germany)

Gradient-Free Warm-Start Library Recovery: an Amortized-Regret Separation

Read the original on arXiv Machine Learning →

arXiv:2606. 21253v2 Announce Type: replace Abstract: Continual learning that is gradient-free, local, online, and append-only is attractive for edge and streaming deployment, but its value is usually argued informally.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

Aug 28

Sharp Minimax Regret for Infinite-Memory Logistic Prediction

arXiv:2608. 26515v1 Announce Type: cross Abstract: We study online prediction for a specific finite-alphabet, exogenously driven source with infinite input memory.

By Vaneet Aggarwal

arXiv Machine Learning

Aug 11

Information Routing across Batch Boundaries: Memory--Batch Tradeoffs in Lipschitz Bandits

arXiv:2608. 07922v1 Announce Type: new Abstract: Adaptive learning needs both a state that preserves what observations imply and opportunities to act on that state.

By Zicheng Lyu, Zengfeng Huang

arXiv Machine Learning

Aug 31

Memorization Is Not Extraction: Tight Differential-Privacy Bounds and Audit Blind Spots

arXiv:2608.27782v1 Announce Type: cross Abstract: Memorization in large language models is measured through a zoo of definitions whose formal relations are unknown, and differential privacy (DP) is t...

By Xujun Che, Depeng Xu, Shuhan Yuan

llms safety

arXiv Machine Learning

5d ago

Dynamic Regret in Online Convex Optimization with Indicator Switching Costs

arXiv:2609. 30556v1 Announce Type: new Abstract: We study dynamic regret in online convex optimization with an \emph{indicator switching cost}: a fixed penalty incurred whenever two consecutive decisions differ.

By Naram Mhaisen, George Iosifidis

arXiv Machine Learning

4d ago

Fine-Tuning on Self-Generated and Reward-Weighted Data: Learning Dynamics, Convergence Rates, and Benefits of Off-Policyness

arXiv:2609.36945v1 Announce Type: new Abstract: We study the learning dynamics of fine-tuning a policy model on self-generated and reward-weighted data, with particular focus on a generalized version...

By Zhiwei Wang, Yanxi Chen, Yaliang Li, Bolin Ding

llms reinforcement-learning fine-tuning

arXiv AI

Jul 24

When Does Recurrence Become an Algorithm? Convergence Selection in Weight-Tied Looped Transformers

arXiv:2607. 20594v1 Announce Type: cross Abstract: When does a weight-tied looped transformer -- one block applied T times -- implement an actual algorithm?

By Tong Zhang, Junhao Hu, Yun Peng, Tao Xie

llms benchmarks

One email a morning, machine-written

Related stories

Sharp Minimax Regret for Infinite-Memory Logistic Prediction

Information Routing across Batch Boundaries: Memory--Batch Tradeoffs in Lipschitz Bandits

Memorization Is Not Extraction: Tight Differential-Privacy Bounds and Audit Blind Spots

Dynamic Regret in Online Convex Optimization with Indicator Switching Costs

Fine-Tuning on Self-Generated and Reward-Weighted Data: Learning Dynamics, Convergence Rates, and Benefits of Off-Policyness

When Does Recurrence Become an Algorithm? Convergence Selection in Weight-Tied Looped Transformers