arXiv Machine Learning July 13, 2026 By Zhang Gongyue, Wang Zhiyong, Liu Donghan, Ren Weihong, Sheng Yixuan, Liu Honghai

The Anatomy of Implicit Bias: Information Allocation in Neural Network Training

Read the original on arXiv Machine Learning →

arXiv:2607. 07156v2 Announce Type: replace Abstract: Implicit bias is usually explained as the preference of an optimization process for certain final solutions and their geometry.

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.

safety

arXiv Machine Learning

Jul 9

Information Allocation Dynamics in Neural Network Optimization

arXiv:2607. 07156v1 Announce Type: new Abstract: Different optimizers have different update biases, but these biases are usually implicit.

By Zhang Gongyue, Liu Donghan, Ren Weihong, Sheng Yixuan, Wang Zhiyong, Liu Honghai

safety

arXiv Machine Learning

Aug 10

Capacity Confounds and Coverage Guarantees in Adaptive Sub-model Federated Learning

arXiv:2608. 07157v1 Announce Type: new Abstract: Sub-model federated learning lets resource-constrained clients train width-reduced versions of a global model, but existing methods allocate capacity by device resources alone.

By Alireza Moayedikia, Alicia Troncoso Lora

benchmarks

arXiv AI

5d ago

Which Optimizer Leaks Most? Optimizer Implicit Bias as a Training-Data Privacy Controller

arXiv:2610.18294v1 Announce Type: cross Abstract: Releasing a neural network checkpoint can leak information about its training data, and existing reconstruction results rely on gradient-descent trai...

By Sagi Habani, Yehonathan Refael, Ofir Lindenbaum

safety

arXiv Machine Learning

Aug 13

Drift and Dependence: Layer-wise Information-Theoretic Bounds for Replay-Based Continual Learning

arXiv:2608. 11690v1 Announce Type: new Abstract: Continual learning must absorb new tasks without erasing old ones, and replay---mixing a small buffer of past examples into current training---is among the most effective remedies for catastrophic forgetting.

By Tieliang Gong, Zhongbo Zhang, Wen Wen, Yong-Jin Liu

benchmarks safety

arXiv Machine Learning

1d ago

Error Correction in Trained TTT Layers

arXiv:2610.16268v2 Announce Type: replace Abstract: Test-time-training (TTT) layers update fast-weight memory while processing an input sequence. A gradient-based update, however, does not by itself...

By Yuhe Hu

arXiv Machine Learning

1d ago

TALLOP: Joint Optimization of Local Training and Communication Compression for Time-Constrained Federated Learning

TALLOP is a method for federated learning that jointly optimizes local training workload and communication compression within a fixed per‑round time budget. It predicts achievable training loss from early mini‑batch loss trajectories (LENS) and estimates compression‑induced degradation using a compression‑error model (CLEN). By combining these predictions, TALLOP selects a training‑communication allocation that minimizes post‑compression loss, achieving competitive or improved time‑to‑accuracy in heterogeneous federated learning environments.

By Honoka Anada, Yafei Ou, Shinya Takamaeda-Yamazaki

One email a morning, machine-written

Related stories

Information Allocation Dynamics in Neural Network Optimization

Capacity Confounds and Coverage Guarantees in Adaptive Sub-model Federated Learning

Which Optimizer Leaks Most? Optimizer Implicit Bias as a Training-Data Privacy Controller

Drift and Dependence: Layer-wise Information-Theoretic Bounds for Replay-Based Continual Learning

Error Correction in Trained TTT Layers

TALLOP: Joint Optimization of Local Training and Communication Compression for Time-Constrained Federated Learning