arXiv:2610.07721v1 Announce Type: cross Abstract: We study ridge regression from exactly $s$ distinct rows of a fixed design. Responses are fixed, and only the subset is random. The determinant law a...
The paper investigates volume‑sampled linear readouts with fixed feature pools and responses, focusing on the randomness introduced solely by subset selection. It establishes a globally sharp Loewner envelope for centered, full‑Gram‑whitened coefficient covariance and characterizes when a positive geometric margin exists versus when it vanishes, using conditions on residual covariance slack and a pairwise Naimark‑complement minor test. The results provide explicit geometric boundaries and conservative certificates for strictness and variance terms in fixed‑query squared loss, offering a design‑specific phase characterization for this randomized linear‑readout primitive.
arXiv:2608.26877v3 Announce Type: replace Abstract: We classify when ordinary fixed-size volume sampling followed by unweighted least squares attains its sharp coefficient-covariance ceiling on a fix...
The paper extends prior work on volume sampling by providing a Loewner envelope for the centered coefficient covariance in least‑squares regression with a fixed pool of features and responses. It characterizes when this envelope is tight, linking tightness to strict spectral properties of residuals, and introduces a residual‑augmented change of measure to derive a one‑sided slack bound. The results also offer geometric insights at the boundary and demonstrate non‑vacuous certificates through frozen‑feature examples, focusing on conditional centered, full‑Gram‑whitened covariance rather than population generalization.
arXiv:2609.06394v1 Announce Type: cross Abstract: Massive datasets in modern machine learning have made data reduction a central challenge, particularly for clustering tasks where memory and computat...
The paper investigates how the choice of geometry in online mirror descent affects performance, particularly when loss gradients are sparse. It introduces randomized block‑norm mirror maps that interpolate between Euclidean and entropic geometries, achieving polynomial‑in‑dimension regret improvements over standard methods for various convex sets. The authors also demonstrate that naive alternation between mirror maps can lead to linear regret and propose a Hedge‑based meta‑algorithm that competes with the best mirror map in a finite portfolio, achieving near‑optimal regret for random block geometries.
arXiv:2609.38565v1 Announce Type: new Abstract: Over the past 25 years, sketching and sampling have become widely used tools for accelerating large-scale regression. In iterative randomized solvers,...
The paper studies high‑dimensional linear contextual bandits with knapsack constraints (CBwK), aiming to exploit sparsity for tighter regret bounds. It introduces an online hard‑thresholding estimator integrated into a primal‑dual framework, achieving sub‑linear regret that grows only logarithmically with the feature dimension. Under either a diverse‑covariate or margin condition, the regret improves to τ‑dependent rates, and when both hold simultaneously, a dual resolving scheme yields an even tighter bound. The approach also recovers optimal rates for high‑dimensional contextual bandits without knapsacks, and experiments demonstrate its practical effectiveness.
Bakhtiari, Lattimore and Szepesvári (COLT 2025) proved that Thompson sampling (TS) has Bayesian regret $\tilde O(d^{5/2}\sqrt n)$ for bandit convex optimisation with convex \emph{monotone} ridge losse...
The paper investigates restricted eigenvalue (RE) bounds for norm‑regularized estimators under heavy‑tailed designs. It shows that the previously conjectured sample‑size law based on Gaussian width fails for heavy‑tailed measurements, due to a phenomenon called simultaneous threshold occupancy. The authors provide explicit counterexamples, derive worst‑case sample‑complexity bounds, and compare the behavior of heavy‑tailed versus Gaussian designs on constant‑width polyhedral descent cones.
arXiv:2608. 13549v1 Announce Type: new Abstract: The per-instance Jaccard score, or intersection over union (IoU), is standard in multi-label classification and binary segmentation.
arXiv:2610.19652v1 Announce Type: new Abstract: Recent work has sought to transfer first-order nonconvex optimization guarantees to zeroth-order methods through gradient estimators, typically incurri...