← Back to all news
arXiv Machine Learning By Richard Bergna (University of Cambridge, Spotify), Fernando Ruiz Mazo (University of Cambridge), Nicol\`o Felicioni (Spotify), Jos\'e Miguel Hern\'andez-Lobato (University of Cambridge), Kamil Ciosek (Spotify)

$\sigma$Transfer: Uncertainty Transfer from Small to Large Networks under $\mu\mathrm{P}$

Read the original on arXiv Machine Learning →

arXiv:2610. 11668v1 Announce Type: cross Abstract: Reliable predictive uncertainty in Laplace approximations depends critically on the prior precision, yet selecting it requires a posterior sweep that is prohibitively expensive for neural networks with billions of parameters.

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
Aug 17

You Only Pass Once: Answering and Abstaining Together in a Single Forward Pass of a Frozen Language Model

arXiv:2608. 14465v1 Announce Type: cross Abstract: A frozen language model on reasoning tasks has two coupled weaknesses: it under-uses evidence its own residual stream already encodes, and it fails to detect when the input is insufficient to answer, so it confabulates.

By Ziyang Luo, Zhongyao Chu, Xinjie He, Youting Wang, Xukui Qin, Runxiong Wu, Yan-Syuan Chen
llmsbenchmarks
More like this →
arXiv Machine Learning
Jun 18

Not Just How Much, But Where: Decomposing Epistemic Uncertainty into Per-Class Contributions

arXiv:2602. 21160v3 Announce Type: replace-cross Abstract: In safety-critical classification, the cost of failure is often asymmetric, yet Bayesian deep learning summarises epistemic uncertainty with a single scalar, mutual information (MI), that cannot distinguish whether a model's ignorance involves a benign or safety-critical class.

By Mame Diarra Toure, David A. Stephens
fine-tuningbenchmarkssafety
More like this →
arXiv AI
5d ago

One-Shot Localisation of the Global Minimum of a Noisy One-Dimensional Function: An Iterative Neural Minimizer Compared with Set Transformers and Classical Estimators

The paper introduces the Neural Function Minimizer (NFM), an iterative neural model that predicts the global minimum of a noisy one‑dimensional function from only twenty samples. It compares the NFM to two Set Transformers and classical zero‑query estimators, finding that all learned models outperform classical methods on held‑out data, with the NFM achieving the lowest error relative to the Gaussian‑process posterior argmin. The study also examines how different estimator outputs affect tie‑breaking between equally deep valleys and plans to release a benchmark and self‑checking harness.

By Qusay Muzaffar, David Levin, Michael Werman
llmsbenchmarks
More like this →