Tech

Anisotropic Trust Region Warping for Prior-Data Fitted Networks in Bayesian Optimisation

By Samuel Younger, Tinkle Chugh, George De Ath · arXiv cs.LG

cs.LGstat.ML

arXiv:2610.37737v1 Announce Type: new Abstract: Prior-Data Fitted Networks (PFNs) replace the hyperparameter refitting of Gaussian Process (GP) surrogates in Bayesian optimisation with a single forward pass, at the cost of a…

Published: October 30, 2026 (4 h ago)
Outlet: arXiv cs.LG
Section: Tech
Length here: Headline and 31-word snippet. The full article is at the source.

More from arXiv cs.LG and around the same time

A semiconductor wafer being lifted from processing equipment

Depth through Recurrence: Towards Ultra-Efficient On-Device ASRarXiv:2610.37833v1 Announce Type: new Abstract: Modern automatic speech recognition (ASR) systems have achieved remarkable accuracy by scaling model depth and capacity, but at the cost of increased memory, energy, and…arXiv cs.LG · 4 h ago · reads at arXiv cs.LG

Improving Data-Constrained Scaling with Hyperparameter Transfer and EnsemblingarXiv:2610.37842v1 Announce Type: new Abstract: As growing compute budgets outpace the growth of high-quality training data, large language models must be trained with both compute and data constraints in mind. Unfortunately…arXiv cs.LG · 4 h ago · reads at arXiv cs.LG

Interpretable neural equation learning for high-dimensional materials dataarXiv:2610.37880v1 Announce Type: new Abstract: Equation learning seeks to discover compact, interpretable equations from data using various machine-learning techniques. However, few workflows discover and interpret learned…arXiv cs.LG · 4 h ago · reads at arXiv cs.LG

Learning Lotteries with Minimal Stakeholder Violations from Membership QueriesarXiv:2610.37828v1 Announce Type: new Abstract: An AI developer often has several candidate versions of a system and can deploy a mixture of them, sending each request to a randomly chosen version, as in A/B testing. Each…arXiv cs.LG · 4 h ago · reads at arXiv cs.LG

Learning Without Clocks: Partition-Invariant Neural NetworkarXiv:2610.37823v1 Announce Type: new Abstract: Event cameras, spiking cochleas and similar sensors emit asynchronous events, yet most learning systems first bin them into frames or packets, so the output depends on how the…arXiv cs.LG · 4 h ago · reads at arXiv cs.LG

Moment-Guided Optimizers for Noisy Deep Learning: MGO-SC as a Simple Consistency Gate for Adam-Style UpdatesarXiv:2610.37712v1 Announce Type: new Abstract: Adaptive optimizers are widely used in deep learning, yet their behavior can degrade under heavy stochasticity and label noise where the sign and magnitude of gradients can be…arXiv cs.LG · 4 h ago · reads at arXiv cs.LG

This page holds the headline and a short snippet as published by arXiv cs.LG, whose feed they came from. The story itself, the photography and the rights stay with them, and the button above goes straight to their site. We keep this page so the headline has a stable address and a record of when it ran.