← Back to all news
arXiv Machine Learning By Jin Lei

Integrating Out, Twice:The Open-System Case That Neural-Network Ensemble Theory Is Missing

Read the original on arXiv Machine Learning →

arXiv:2606. 09950v1 Announce Type: new Abstract: Averaging a neural network over its random parameters and marginalizing a Gaussian sector are the same operation, the Schur complement of the eliminated block, and when that block is closed it returns a covariance and its inverse.

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.

Related stories

arXiv Machine Learning
Sep 23

When are bosonic Gaussian states classical to learn?

arXiv:2609.26705v1 Announce Type: cross Abstract: A fundamental question in physics is: When does classical behavior emerge from quantum systems? Bosonic Gaussian states provide a natural setting to...

By Senrui Chen, Antonio Anna Mele, Francesco Anna Mele, John Preskill
More like this →
arXiv Machine Learning
Aug 31

What Neural Network Field Theory Can and Cannot Realise on a Computer

The paper investigates the limits of implementing neural network field theory on a computer, focusing on function classes that are regular enough for computation. It presents a no‑go theorem showing that finite‑width network ensembles cannot consistently realize either a quantum or effective field theory due to violations of reflection positivity and lack of scale separation. The study distinguishes between finite‑width and infinite‑width interpretations, concluding that only smeared correlators of the infinite‑width limit are computable with controlled error, and identifies two possible ways to evade the theorem—by relaxing finite variance or exact rotation invariance.

By Thomas R. Harvey
More like this →
arXiv Machine Learning
Jun 19

Effective Dimension Governs Generalization in Quantum Kernel Vision Models

arXiv:2606. 20183v1 Announce Type: new Abstract: Recent quantum vision models-quantum vision transformers and quantum convolutional networks-report two striking but unexplained empirical phenomena: (i) ansatze with more, or more uniformly distributed, entanglement generalize better, and (ii) injecting quantum noise can improve test accuracy rather than degrade it.

By Jian Xu, Delu Zeng, John Paisley, Qibin Zhao
llmssafety
More like this →
arXiv Machine Learning
Jul 16

Algebraic Representability as the Limiting Regime of Grokking: An Exactly Solvable Model with Holomorphic Activations

arXiv:2607. 13749v1 Announce Type: new Abstract: Neural networks trained on modular arithmetic exhibit grokking, a delayed transition from memorisation to generalisation known to depend on model capacity: too little and the network memorises slowly or not at all, too much and it generalises almost immediately.

By Chon-Fai Kam, Xavier Cadet, Miloud Bessafi, Frederic Cadet
benchmarks
More like this →