stat.ML · 2026-07-22 · No. 61
Machine Learning, 2026-07-22.
5 new papers in stat.ML. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
5 entries-
01
Fundamental limits of distributed multiclass classification from simple binary decisions
Ioannis Papageorgiou, Srinivas Nomula, Ayalvadi Ganesh, Sidharth Jaggi, Parimal Parag
stat.ML · cs.IT · cs.LG · math.ST
We consider the problem of constructing a $K$-class classifier from the combination of $O(\log K)$ simple binary classifiers -- this is a natural paradigm to construct a sophisticated classifier in a distributed manner with each agent performing a relatively straightforward task. We study the fundamental performance limits of such a classifier when the corresponding binary classifiers are hyperplanes. For a stylized Gaussian setting where the...
-
02
The Tractability Landscape of Sampling with Inexact Scores
Anming Gu, Kevin Tian, Hubert Yang, Yusong Zhu
stat.ML · cs.LG · math.ST
We provide a simple and tight characterization of the types of inexact score oracle access that permit sampling with vanishing total variation bias, for a standard, well-behaved target family. Our main result shows that any weaker error than the sub-Gaussian assumption used by [YW26] rules out the tractability of unbiased sampling. This strengthens the conclusion of [CCSW26] to be algorithm-agnostic, and to hold for a wider range of error assumptions.
-
03
Algebraic Signatures for Structural Learning in Probability Tensors
Akihiro Maeda, Shohei Hidaka, Satoshi Aoki
stat.ML · cs.LG
Algebraic statistics characterizes statistical models through polynomial constraints, but it has mainly been used for analytically specified model classes. This paper studies the inverse problem: identifying probabilistic structure from vanishing binomials observed in empirical probability tensors. We treat the vanishing binomials of a toric model as its algebraic signature, and turn the ideal-variety correspondence of algebraic statistics...
-
04
The Price of Hidden Curvature: An $\widetildeΩ (d^{5/4} \sqrt{T})$ Lower Bound for Bandit Convex Optimization
Nived Rajaraman
stat.ML · cs.IT · cs.LG
We establish a $\widetildeΩ(d^{5/4}\sqrt T)$ lower bound on the minimax expected regret of stochastic bandit convex optimization of $1$-Lipschitz functions on the Euclidean ball. This presents the first nontrivial regret lower bound that grows faster than $d\sqrt{T}$ for this problem, establishing that stochastic bandit convex optimization is fundamentally harder than linear bandits. The hard class of convex functions we construct takes the...
-
05
Mixing-Free and Signal-Optimal Learning of Gaussian Graphical Models from Glauber Dynamics
Vignesh Tirukkonda, Gautam Dasarathy
stat.ML · cs.LG · math.ST
Gaussian graphical model selection is usually studied under independent sampling, but in many applications the data arise as a single trajectory of a dependent stochastic process. We study exact recovery of the graph from one trajectory of random-scan Gaussian Glauber dynamics. Existing techniques for this problem either inherit the mixing time of the chain, which can be super-polynomial in the dimension $p$ without strong assumptions, or are...
This edition is part of The Daily Abstract — stat.ML archive. Subscribe to receive these in your inbox each morning, automatically translated to Spanish, with reply-to-PDF: arxivdaily.ignorelist.com.
#D99C5E. Built and served on an always-free VM. The masthead is set 14% letterspaced because newspapers do that and it works.