New Bayesian Algorithm Achieves Valid Uncertainty Quantification in One-Pass Online Learning
Researchers have proposed a new Bayesian online learning algorithm designed for the one-pass regime, where data is processed sequentially without revisiting past observations. Existing theoretical guarantees for such methods typically require mini-batch sizes to grow unboundedly, a condition that breaks down in one-pass scenarios; the new algorithm addresses this with a warm-start phase for stable sequential updates. The work establishes an online analogue of the Bernstein-von Mises theorem, providing formal guarantees for uncertainty quantification that could make Bayesian sequential inference more reliable in practical streaming data applications.
A preprint posted to arXiv introduces a Bayesian online learning algorithm specifically tailored to the one-pass setting, in which a model is updated sequentially as data arrives and past data is not revisited. Prior theoretical work in this area has generally required mini-batch sample sizes to diverge—a condition incompatible with true one-pass learning—leaving a significant gap in the theoretical foundations of the field. The proposed algorithm incorporates a warm-start phase intended to stabilize early sequential updates before the main inference procedure begins. The authors prove that the sequentially updated posterior achieves the optimal convergence rate and derive an online version of the Bernstein-von Mises theorem, which guarantees that posterior uncertainty estimates are asymptotically valid (frequentist-calibrated) without the diverging mini-batch requirement. The theoretical analysis relies on a novel framework described as fundamentally different from existing approaches in the online learning literature. Numerical experiments on generalized linear models demonstrate that the method matches the performance of batch estimators while outperforming existing online procedures. The paper is 52 pages and was submitted in late April 2026, with a revised version posted in June 2026.
What's missing
As a preprint, this work has not yet undergone formal peer review. The numerical experiments are limited to generalized linear models, leaving open questions about performance on more complex model classes (e.g., deep neural networks or non-parametric settings). The paper does not appear to address computational cost of the warm-start phase relative to existing methods, nor scalability to very high-dimensional problems.
What different sources said
- arXiv stat.MLCenter
Bayesian online learning in the one-pass regime: Frequentist validity and uncertainty quantification
Related
Gut Bacteria Enzyme Found to Break Down Heat-Processed Food Compounds, Producing Novel Biogenic Amines
Researchers have discovered that an enzyme in common gut bacteria can degrade N-epsilon-carboxymethyllysine (CML), a compound formed during thermal food processing, producing previously unknown biogenic amines. The enzyme, ornithine decarboxylase SpeC from enterobacteria, acts on CML and related modified lysine derivatives through a low-level 'underground' catalytic activity. This finding suggests a previously unrecognized communication axis between thermally processed dietary compounds and gut microbial physiology, with potential implications for host health.
Full-Length Gene Sequencing Reveals Two Distinct Bacterial Communities in Black-Legged Ticks Expanding Into Canada
Researchers used Oxford Nanopore full-length 16S rRNA gene sequencing to characterize the microbiome of Ixodes scapularis black-legged ticks collected in Nova Scotia, Canada, distinguishing between tick-adapted bacteria and environmentally acquired bacteria. The study comes as I. scapularis — the primary vector of Lyme disease — is rapidly expanding northward into Canada due to climate change. The findings suggest that environmentally derived bacteria in tick microbiomes are not mere contamination, which has implications for how tick microbiome data is collected and interpreted across surveillance studies.
Study Identifies Metabolic Link Between Cell Envelope Stress and Biofilm Formation in Bacteria
Researchers have discovered that the metabolite acetyl-CoA directly inhibits enzymes that degrade the bacterial signaling molecule c-di-GMP, connecting cell envelope biosynthesis stress to biofilm formation in Pseudomonas aeruginosa. The study found that sub-inhibitory concentrations of antibiotics targeting early peptidoglycan biosynthesis — but not other antibiotic classes — elevate c-di-GMP levels by reducing phosphodiesterase activity, with acetyl-CoA competing for the enzyme active site. Because the relevant enzyme domain is broadly conserved across bacterial species, this checkpoint mechanism may be widespread and could have implications for understanding antibiotic-induced biofilm responses.