Skip to content

Full-Covariance Smoothing of Bayesian Neural Networks for Online Adaptation

Sep 2026 · 0 citations · 36 references
Computer Science Engineering

TL;DR

A one-step-per-layer smoother that approximates as Gaussian only each layer's affine output is derived that applies both to deterministic systems with noisy observations and to stochastic systems described by output statistics.

Abstract

A neural network's layers can be treated as time steps of a state-space model, turning Bayesian training into a smoothing problem: a forward pass propagates Gaussian moments through the network, and a backward Rauch--Tung--Striebel pass updates the weight posteriors in closed form. Such methods learn from each observation in a single pass, in an uncertainty-aware manner, and without gradient-based iterations or replay, which makes them well suited for online adaptation and data-efficient learning. Existing smoothing-based methods, however, are restricted to diagonal covariances across activations, discarding correlations between neurons. We overcome this limitation via a cross-covariance identity that enables full-covariance propagation through a network's nonlinear activations. We derive a one-step-per-layer smoother that approximates as Gaussian only each layer's affine output, and that applies both to deterministic systems with noisy observations and to stochastic systems described by output statistics. We demonstrate this method in non-stationary classification, online dynamics learning, and policy adaptation of a vision-language-action model, and find that it is generally more accurate than other smoothing-based methods.

View source

Similar papers

Preprint Aug 2026

Modified Bryson-Frazier Smoothing and Hyperparameter Learning for Temporal Gaussian Process Regression

The modified Bryson-Frazier (MBF) smoother is revisited as an alternative to the RTS smoother for Gaussian process regression in its state-space representation and it is demonstrated that the intermediate quantities computed by the MBF smoother can be reused to compute gradients of the negative log marginal likelihood,...

Tom Colemont, B. Evens, T. Li et al. · 0 citations
Open access Nov 2024

Rapid Bayesian computation and estimation for neural networks via log-concave coupling

It is demonstrated that the posterior density can be written as a mixture density with suitably defined auxiliary random variables, where the mixture components are log-concave, and neuron parameters can be sampled from the posterior by only sampling log-concave densities.

Curtis McDonald, Andrew R. Barron · 1 citation
Preprint Aug 2026

Uncertainty propagation in auto-regressive random neural network models

Analytical and particle-based methods for uncertainty propagation in random neural network models, where both the inputs and network parameters are allowed to be random, are developed and extended to autonomous dynamical systems whose one-step evolution map is represented by a random neural network.

J. Adams, Daniele Venturi · 0 citations
Preprint Sep 2026

Forgetting While Remembering, an Invariant Online Data-Driven Predictive Control Formulation

A Bayesian, online DPC framework based on autoregressive models with exogenous inputs (ARX) that uses an externally-provided prior, which encodes inductive bias such as smooth system dynamics and stability, to safeguard performance when SNR is low is proposed.

Alessandro Chiuso, F. Dörfler, Keith Moffat · 0 citations
#artificial intelligence Preprint Oct 2026

Posterior sampling by source-space MCMC via prior-based few-step transport maps

This work develops a framework for source-space generalized Bayesian inference that combines inexpensive few-step prior transports with posterior stability guarantees and establishes Wasserstein error bounds between the exact and learned posteriors in terms of the joint population iMF and auxiliary-velocity loss.

Hoang Phuc Hau Luu, Marcelo Hartmann, Zhong-Jian Wang · 0 citations

Related blog posts

MIT News · Artificial Intelligence Nov 17, 2026

Learning the language of machine learning

By studying the computational foundations of language learning, Associate Professor Jacob Andreas builds intelligent systems that can communicate effectively with humans.

Microsoft Research Blog Nov 16, 2026

TokenEconomizer: Learning from Experience to Make AI Coding Agents More Efficient

AI coding agents are increasingly help developers fix bugs and build features largely on their own, but every interaction with their models consumes tokens. In each session, an agent sends instructions, tool descriptions, and session history to its model. Most efforts to reduce this cost focus on individual tasks. Yet developers return to the same […] The post TokenEconomizer: Learning from Experience to Make AI Coding Agents More Efficient appeared first on Microsoft Research.

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.