Answers are grounded in this paper and cite their sources.
Analysis reveals improved covariance estimation thresholds in sub-Weibull martingales, suggesting greater confidence in high-stakes scenarios.
In this paper, we establish a matrix Freedman inequality for martingales with sub‐Weibull tails. Under conditional control of the increments, the top eigenvalue admits a non‐asymptotic tail bound with explicit, dimension‐aware constants. Via Hermitian dilation, our result extends to rectangular matrices, recovers the sub‐Gaussian case at and admits a time‐uniform (supremum‐over‐time) form. Relative to recent Bennett/Bernstein bounds for sub‐Weibull matrix martingales, our thresholds depend only on a variance proxy and a radius. Concretely, in high‐confidence regimes with , these new thresholds match or improve the corresponding modern envelopes at the same confidence level. We illustrate the utility of our bound in two applications: (i) self‐normalized confidence sets for stochastic linear bandits with heavy‐tailed noise and (ii) operator‐norm error bounds for covariance estimation. We corroborate the theory and highlight constant‐level effects through simulations over a range of tail indices and variance levels.
No takes yet. Share an insight, caveat, or question.
Íñigo Torres (2025) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: