Researchers Develop Efficient Algorithm for Learning Changing Concepts with Noisy Data
Researchers have developed a computationally efficient algorithm for learning drifting halfspace classifiers in the presence of Massart noise, achieving an error rate scaling as Δ^(1/3)/γ above the noise floor. The work addresses an online learning setting where both the target concept and label noise can change over time. The results are significant because the authors also prove a matching lower bound showing that Δ^(1/3)-scaling is essentially unavoidable for efficient algorithms, revealing a fundamental information-computation tradeoff.
A paper accepted to ICML 2026 presents a new efficient online learning algorithm for the problem of drifting halfspaces under Massart noise, a setting where an adversary may corrupt labels with instance-dependent noise up to rate η, and the target classifier may shift between rounds at a drift rate Δ. The proposed learner achieves prediction error of η + Õ(Δ^(1/3)/γ), where γ is the margin parameter. In the realizable (noiseless) setting, an adaptation of the same techniques yields improved error rates over prior work. On the lower-bound side, the authors prove that no algorithm based on low-degree polynomial tests can achieve better than Δ^(1/3)-scaling, even under the simpler random classification noise model, providing strong evidence that the algorithm is computationally optimal. This stands in contrast to the information-theoretically optimal rate of Δ^(1/2), which is achievable in principle but appears computationally intractable. The gap between statistical and computational optima constitutes a formal information-computation tradeoff for this class of problems.
What's missing
The paper does not discuss empirical evaluations on real or synthetic datasets; all results are theoretical. The tightness of the lower bound for algorithms beyond low-degree polynomial tests remains an open question.
What different sources said
- arXiv cs.LGCenter
Efficiently Learning Drifting Halfspaces with Massart Noise
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.