← Back to all news
arXiv Machine Learning

Online Learning via Learned Latent Bayesian Tracking

The paper introduces AURA, a meta‑learning framework that learns a low‑dimensional latent state‑space model for the evolution of optimal model parameters under distribution shift. Online adaptation is performed via extended Kalman filtering in this latent space, followed by reconstruction of full model parameters through a learned lifting map, enabling efficient single‑step updates. Experiments on neural wireless receivers and non‑stationary image classification show that AURA improves adaptation speed, accuracy, and computational efficiency compared to existing online learning and Bayesian filtering baselines.

Related stories

arXiv Machine Learning
Sep 24

Full-Covariance Smoothing of Bayesian Neural Networks for Online Adaptation

The paper proposes treating a neural network’s layers as time steps in a state‑space model, converting Bayesian training into a smoothing problem. By propagating Gaussian moments forward and applying a Rauch–Tung–Striebel backward pass, weight posteriors are updated in closed form without gradient iterations or replay. The authors extend prior work by introducing a cross‑covariance identity that allows full‑covariance propagation through nonlinear activations, enabling more accurate online adaptation in non‑stationary classification, dynamics learning, and vision‑language‑action policy adaptation.

By Oren Wright, Haoming Jing, Qiaoan Shen, Koichiro Niinuma, Yorie Nakahira, Jos\'e M. F. Moura
multimodal
More like this →
arXiv AI
Sep 10

FILT3R: Latent State Adaptive Kalman Filter for Streaming 3D Reconstruction

FILT3R is a training‑free latent filtering layer for streaming 3D reconstruction that treats recurrent state updates as stochastic state estimation in token space. It maintains per‑token variance and computes a Kalman‑style gain to balance memory retention with new observations, estimating process noise online from temporal drift of candidate tokens. Experiments show that FILT3R generalizes overwrite and gating policies, shrinking gains in stable regimes and increasing them during genuine scene changes, thereby improving long‑horizon stability for depth, pose, and 3D reconstruction.

By Seonghyun Jin, Jong Chul Ye
More like this →
arXiv Machine Learning
Aug 26

Adaptive prediction theory combining offline and online learning

The paper studies a two‑stage learning framework that first trains an offline model using approximate nonlinear‑least‑squares estimation and then adapts it online with a meta‑LMS algorithm to handle parameter drift in nonlinear stochastic dynamical systems. It provides an upper bound on the offline generalization error that accounts for strong data correlation and distribution shift via Kullback‑Leibler divergence, and it demonstrates that the combined offline‑online approach outperforms methods that rely solely on offline or online learning. Both theoretical analysis and empirical experiments support the claimed performance gains.

By Haizheng Li, Lei Guo
More like this →
arXiv Machine Learning
Sep 22

Bayesian Filtering in Physical Systems via Test-time Trained Flow Matching

The paper introduces the Belief Flow Filter (BFF), a generative filtering framework that encodes the evolving posterior distribution directly into flow matching model weights and updates them via test‑time gradient descent. By avoiding particle representations and Gaussian assumptions, BFF aligns structurally with Bayesian filtering and targets the recursive filtering operator. Empirical results on five physical systems—including chaotic dynamics, sparse observations, and a tokamak plasma estimation task—show that BFF outperforms existing methods in most benchmark metrics.

By Ruiqi Feng, Chongyi Wang, Tao Zhang, Tailin Wu
diffusionbenchmarks
More like this →