Researchers Prove Last-Iterate Convergence Property for Optimistic Multiplicative Weight Update Algorithm
A new preprint posted to arXiv establishes that the Optimistic Multiplicative-Weights Update (OMWU) algorithm asymptotically converges to a saddle point in smooth convex-concave saddle-point problems. This resolves an open question that has persisted since the 1980s, when analogous convergence was already known for the related OGDA algorithm. The result matters because OMWU is widely used in machine learning and game theory, and confirming its last-iterate convergence strengthens its theoretical foundations.
Francesco Orabona's preprint, submitted to arXiv on June 10, 2026, proves that the last iterate of the Optimistic Multiplicative-Weights Update (OMWU) algorithm converges asymptotically to a saddle point for smooth convex-concave saddle-point problems when using a sufficiently small constant learning rate. OMWU is the non-Euclidean, entropic counterpart to Optimistic Gradient Descent Ascent (OGDA), whose last-iterate convergence has been known since the 1980s, making the analogous question for OMWU a longstanding open problem. The proof requires no assumption of solution uniqueness, strict complementarity, an error bound, or initialization near a solution, making it broadly applicable. The key technical contribution is a boundary argument demonstrating that every cluster point satisfies the inactive-coordinate KKT inequalities. Notably, the author credits ChatGPT with assisting in the discovery of this boundary argument, documenting the interaction in an appendix. Both OGDA and OMWU are prominent tools for solving minimax and game-theoretic optimization problems, so this result has implications for training generative adversarial networks, multi-agent reinforcement learning, and related areas.
What's missing
The preprint has not yet undergone peer review, so the correctness of the proof has not been independently verified by the research community. The paper does not specify convergence rates, leaving open how quickly OMWU reaches a saddle point in practice compared to OGDA.
What different sources said
- arXiv cs.LGCenter
Last-Iterate Convergence of Optimistic Multiplicative Weight Update
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.