Saved in:
Bibliographic Details
Main Author: Haq, Omer
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2602.00458
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912866029797376
author Haq, Omer
author_facet Haq, Omer
contents We introduce LatentTrack (LT), a sequential neural architecture for online probabilistic prediction under nonstationary dynamics. LT performs causal Bayesian filtering in a low-dimensional latent space and uses a lightweight hypernetwork to generate predictive model parameters at each time step, enabling constant-time online adaptation without per-step gradient updates. At each time step, a learned latent model predicts the next latent distribution, which is updated via amortized inference using new observations, yielding a predict--generate--update filtering framework in function space. The formulation supports both structured (Markovian) and unstructured latent dynamics within a unified objective, while Monte Carlo inference over latent trajectories produces calibrated predictive mixtures with fixed per-step cost. Evaluated on long-horizon online regression using the Jena Climate benchmark, LT consistently achieves lower negative log-likelihood and mean squared error than stateful sequential and static uncertainty-aware baselines, with competitive calibration, demonstrating that latent-conditioned function evolution is an effective alternative to traditional latent-state modeling under distribution shift.
format Preprint
id arxiv_https___arxiv_org_abs_2602_00458
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle LatentTrack: Sequential Weight Generation via Latent Filtering
Haq, Omer
Machine Learning
Artificial Intelligence
Robotics
We introduce LatentTrack (LT), a sequential neural architecture for online probabilistic prediction under nonstationary dynamics. LT performs causal Bayesian filtering in a low-dimensional latent space and uses a lightweight hypernetwork to generate predictive model parameters at each time step, enabling constant-time online adaptation without per-step gradient updates. At each time step, a learned latent model predicts the next latent distribution, which is updated via amortized inference using new observations, yielding a predict--generate--update filtering framework in function space. The formulation supports both structured (Markovian) and unstructured latent dynamics within a unified objective, while Monte Carlo inference over latent trajectories produces calibrated predictive mixtures with fixed per-step cost. Evaluated on long-horizon online regression using the Jena Climate benchmark, LT consistently achieves lower negative log-likelihood and mean squared error than stateful sequential and static uncertainty-aware baselines, with competitive calibration, demonstrating that latent-conditioned function evolution is an effective alternative to traditional latent-state modeling under distribution shift.
title LatentTrack: Sequential Weight Generation via Latent Filtering
topic Machine Learning
Artificial Intelligence
Robotics
url https://arxiv.org/abs/2602.00458