A three-regime batch-size phase diagram that reveals how the role of momentum changes with batch size is revealed, with Polyak enlarging the critical batch size, the largest batch size preserving the best small-batch data-scaling exponent, thereby enabling greater parallelism without sacrificing data efficiency.
Jia-Nan Wang, Zi-Xun Huang, Kai-Rui Li et al.· 0 citations
This work introduces the general class of so-called Chernoff-neural operators and shows in a universal approximation theorem that they can approximate the Chernoff one-step operators arbitrarily well, and introduces the more specialized class of envelope-neural operators for envelope semigroups which allows for quantit...
Jonas Blessing, Philipp Schmocker, Alessandro Sgarabottolo· 0 citations
This work addresses the computation of the MLT for CGGMs by focusing on its geometric formulation: finding the minimum rank of a sample covariance matrix such that its projection lies almost surely within the interior of the cone of sufficient statistics.
R. Homs, Olga Kuznetsova, Bernadette J. Stolz· 0 citations
By bridging graph topology learning and graph generation, this review provides a broader cross-disciplinary perspective on the field and outlines promising directions for future research.
Xiaowen Dong, Hoi-To Wai, Si-Heng Chen et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Experiments on logistic regression, probabilistic matrix factorization, and Bayesian neural networks show that HyperMC improves posterior approximation or predictive calibration relative to MAMBA, grid search, and heuristic baselines, while Robust HyperMC yields more stable and reproducible tuning results.
This work introduces a variant of the Thompson Sampling algorithm that uses a fractional or $\alpha$-posterior instead of the standard posterior, and identifies general regularity conditions on the prior and reward distributions that enable a regret analysis of $\alpha$-TS without assuming any tractable approximation o...
Prateek Jaiswal, D. Pati, A. Bhattacharya et al.· 0 citations
This work proves that on generated data, the state channel cuts regret by up to 79 percent against action-level weighting and, on the funnel family, by 32 to 68 percent against a tuned minimax-optimal method.
The FeeBee framework is extended, originally proposed for evaluating Bayes-error estimators, to the optimal BER and AUC, and the resulting procedure provides practical evaluation scores without requiring knowledge of the optimum.
This work characterize models from this family of methods as JEPA-WMs and investigates the technical choices that make algorithms from this class work, and proposes a model that outperforms two established baselines, DINO-WM and V-JEPA-2-AC, in both navigation and manipulation tasks.
Basile Terver, Tsung-Yen Yang, Jean Ponce et al.· Trans. Mach. Learn. Res.· 49 citations· ⚡7
A modular error bound in the bounded-Lipschitz path metric that provides a clean separation of errors due to endpoints, control regression, initialization, discretization, and related approximations is established.
This work studies online maximization of nonnegative, non-monotone DR-submodular functions over compact convex down-closed subsets of the $d$-dimensional unit cube and shows that the best known constructive offline approximation factor is also achievable online.
This study designed and empirically validated a three-layer Zero Trust architecture for Microsoft SQL Server that natively integrates instance-level authentication governance, enhanced Role-Based Access Control with Row-Level Security and Just-in-Time privilege elevation, and metadata-driven Attribute-Based Access Cont...
Maynard Capil, D. Dasig· JPAIR Multidisciplinary Rese...· 0 citations
A machine-learning approach called CheMeleon provides a practical way to develop new drugs or other molecules with much less detailed, expensive experimentation.
