Sharp lower bounds are established for Gaussian approximation of Polyak-Ruppert averaged stochastic gradient descent with polynomially decreasing step sizes for Polyak-Ruppert averaged stochastic gradient descent with polynomially decreasing step sizes.
D. Belomestny, Alexey Naumov, Sergey Samsonov· 0 citations
In this paper, we study the bias and high-order error bounds of the Linear Stochastic Approximation (LSA) algorithm with Polyak-Ruppert (PR) averaging under Markovian noise. We focus on the version of the algorithm with constant step size and propose a novel decomposition of the bias via a linearization technique. We a...
I. Levin, Alexey Naumov, Sergey Samsonov· AAAI Conference on Artificia...· 2 citations
We establish a nonasymptotic Gaussian approximation bound over centered Euclidean balls for sums of independent, not necessarily identically distributed, random vectors in \(\mathbb R^p\). Let \(S_n\) denote the sum, let \(\Sigma=\operatorname{Var}(S_n)\), and let \(G\sim N(0,\Sigma)\). Define the effective rank and th...
A. Naumov, Sergey Samsonov, Vladimir Spokoiny et al.· 0 citations
High-probability bounds are proved, uniform over a realized localization neighbourhood, for the conditional-coverage gap and the length error relative to the oracle and uniform local guarantees decompose into fixed-score calibration and uniform score-estimation errors, showing that improved learning sharpens localized...
Anton Conrad, R. Isaev, D. Belomestny et al.· arXiv.org· 0 citations
In this paper, we study nonasymptotic $L^p$ error bounds for interval length and conditional coverage in split conformalized quantile regression (CQR). Our bounds rely on local regularity conditions and accuracy guarantees for the estimated quantiles. We further instantiate our bounds for quantile regression with spars...
R. Isaev, Anton Conrad, D. Belomestny et al.· 0 citations
A statistical framework for Inverse Entropy-regularized Reinforcement Learning is developed that resolves ambiguity by combining entropy regularization with a least-squares reconstruction of the reward from the soft Bellman residual, leading to a unique and well-defined so-called least-squares reward consistent with th...
D. Belomestny, Alexey Naumov, Sergey Samsonov· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.