arXiv Machine Learning October 19, 2026 By Niclas G\"oring, Shuofeng Zhang, Branton DeMoss, Ard A. Louis

Escaping Parameter Space: Tight Generalization Bounds via Representation Quality

Read the original on arXiv Machine Learning →

The paper presents a tight generalization bound for deterministic neural networks that relies on the quality of their last hidden layer representations rather than traditional parameter-space metrics. By using a parameter‑free k‑nearest‑neighbor classifier to assess representation quality, the bound decomposes into three measurable components—local class geometry, decoder‑network agreement, and training stability—providing both a non‑vacuous certificate and a diagnostic tool for understanding generalization. Experiments show the bound achieves an 8.0‑percentage‑point gap to test error on CIFAR‑10 with ResNet‑18, yields the first non‑vacuous certificates on CIFAR‑100, and certifies 1.4 % on CIFAR‑10 and 23.1 % on 1,000‑class ImageNet using frozen DINOv2 representations.

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

Jun 2

Non-vacuous Generalization Bounds for Deep Neural Networks without any modification to the trained models

arXiv:2503. 07325v2 Announce Type: replace Abstract: Understanding and certifying the behavior of modern deep neural networks remains a fundamental challenge in reliable machine learning.

By Khoat Than, Dat Phan

arXiv Machine Learning

Jul 14

Requential Coding: Pushing the Limits of Model Compression with Self-Generated Training Data

arXiv:2607. 11883v1 Announce Type: new Abstract: Compression is fundamental to intelligence.

By Shikai Qiu, Marc Finzi, Yujia Zheng, Kun Zhang, Andrew Gordon Wilson

llms efficiency benchmarks

Hugging Face Trending Papers

Jul 13

Requential Coding: Pushing the Limits of Model Compression with Self-Generated Training Data

Compression is fundamental to intelligence. A model that can represent its training data as a short code has discovered regularities that enable generalization.

llms efficiency benchmarks

arXiv AI

Jun 16

Upper Bounds on the Generalization Error of Deep Learning Models via Local Robustness and Stability

arXiv:2606. 16883v1 Announce Type: cross Abstract: Generalization is a critical property of data-driven models, particularly deep learning models deployed in safety-critical applications.

By Abdul-Rauf Nuhu, Parham M. Kebria, Vahid Hemmati, Mahmoud N. Mahmoud, Edward Tunstel, Abdollah Homaifar

safety

arXiv Machine Learning

Sep 21

On the Limits of Maximal Coding Rate Reduction for Out-of-Distribution Generalisation

The paper investigates the limits of the maximal coding rate reduction (MCR²) framework for out‑of‑distribution (OOD) generalisation. It shows that MCR² can lead to complete prediction failure under distribution shift, even when a perfectly stable feature is available, and that adding invariance principles from IRM or REx does not resolve this issue. The authors conclude that additional assumptions or learning principles are needed to guarantee stable OOD predictions with MCR².

By Menghui Zhou, Gaoshan Bi, Vitaveska Lanfranchi, Po Yang

safety

arXiv Machine Learning

Aug 11

Domain-Aware Pruning: Sparsity and Domain Generalization via Regularized Probabilistic Masking

arXiv:2608. 08624v1 Announce Type: new Abstract: Domain generalization (DG) and neural network pruning are conventionally treated as distinct objectives, targeting out-of-distribution (OOD) robustness and model efficiency, respectively.

By Parham Sazdar, Mostafa Tavassolipour, Reshad Hosseini

fine-tuning efficiency benchmarks safety

One email a morning, machine-written

Related stories

Non-vacuous Generalization Bounds for Deep Neural Networks without any modification to the trained models

Requential Coding: Pushing the Limits of Model Compression with Self-Generated Training Data

Requential Coding: Pushing the Limits of Model Compression with Self-Generated Training Data

Upper Bounds on the Generalization Error of Deep Learning Models via Local Robustness and Stability

On the Limits of Maximal Coding Rate Reduction for Out-of-Distribution Generalisation

Domain-Aware Pruning: Sparsity and Domain Generalization via Regularized Probabilistic Masking