Skip to content

Adaptive Schauder Stochastic Mirror Descent in Banach Spaces

Aug 2026 · arXiv.org · Vol abs/2608.13121 · 0 citations · 60 references
Mathematics Computer Science

Abstract

In this paper, we solve risk functional minimization problems with general losses in Banach spaces within the framework of stochastic approximation. We introduce an adaptive regularization strategy for stochastic mirror descent (SMD). Specifically, using a Schauder basis, we construct nested finite-dimensional subspaces whose dimensions adapt to the sample size $n$ to balance approximation and optimization errors. We solve each SMD subproblem over the corresponding subspace and project the stochastic subgradient onto its dual space. This yields closed-form solutions and coordinate-wise coefficient updates with low computational and storage complexity. For risk minimization in $\mathcal{L}^p$ spaces with $1<p<\infty$, we construct Bregman distances adapted to the uniform convexity of the underlying Banach space using $\max\{2,p\}$-convex functionals. At the $\mathcal{L}^1$ endpoint, we instead construct a locally strongly convex functional based on the entropy function. By developing a new analytical framework, we show that the risk functional values converge to the minimum at a rate of $\mathcal{O}\left(n^{-\min\{\frac12,\frac1p\}}\right)$, up to logarithmic factors. In the misspecified setting, we prove convergence under weaker regularity assumptions and derive explicit polynomial rates under suitable regularity conditions. Finally, we apply the method to statistical inverse problems and illustrate its empirical performance through numerical experiments in both settings.

View source

Similar papers

#machine learning Preprint Oct 2026

Differential Privacy of Gradient Descent on Perturbed Objectives

Objective perturbation adds a random linear term to a regularized empirical risk and releases the exact perturbed minimizer. We study the finite computation obtained by releasing the $N$-th iterate of deterministic gradient descent on $w\mapsto F(w;S)+\langle z,w\rangle$, where $z\sim\mathcal N(0,\sigma^2I_d)$ is drawn...

Austin Watkins, Raman Arora · 0 citations
Preprint Oct 2026

Spectral gap for the stochastic primitive equations under degenerate Brownian forcing

We prove a weighted Wasserstein spectral gap for the three-dimensional primitive equations on $\mathscr E=\{u\in H^1\cap L^8: \partial_zu\in L^4\}$ under finite-rank additive Brownian forcing that is phase-complete finite Fourier and satisfies a quantitative quadratic saturation condition. In particular, four real forc...

Qu-Yuan Lin, Rong-Chang Liu, Ke-Ning Lu · 0 citations
Preprint Nov 2026

Approximating It\^o Processes in Adapted Wasserstein Distance with Finite Support Laws

Motivated by finite-scenario surrogates in stopping and control problems, we study the approximation of It\^o diffusion laws by laws supported on $M$ paths in an adapted Wasserstein distance, which we term adapted functional quantization. Under the strict adapted Wasserstein distance, no finite-support approximation ca...

Xi-Hao He, Feng-Yi Yuan · 0 citations
Preprint Oct 2026

Uniform Approximation for Operator Learning on Compact Sets

It is proved that nonlinear recovery with a common vanishing gauge and a rank bound depending only on the model dimension is equivalent to the uniform approximation property (UAP).

Rui-Ke Liu, Jie Shen · 0 citations
#machine learning Preprint Nov 2026

Reproducing Kernel (Quasi-)Banach Spaces with the $\ell^p$ Coefficient Norms

This paper advances the theory of reproducing kernel Banach spaces (RKBSs) by investigating the general $\ell^p$ regularization framework, with a particular focus on the non-convex regime $0<p<1$. While our preceding work established the foundation for RKBSs with the $\ell^1$ norm, the pursuit of stronger sparsity---cl...

Tian-Fang Wang, Guo-Hui Song, Hai-Zhang Zhang · 0 citations
Preprint Oct 2026

Gaussian Approximation of Besov Functions for Logistic Classification on Manifolds

We study Gaussian kernel approximation and regularized logistic classification on a connected compact smooth embedded manifold $X\subset\mathbb R^d$ without boundary and of intrinsic dimension $\varrho$. Two main challenges are to derive a fast oracle inequality without assuming a bounded Bayes function and to construc...

Guan-Hang Lei, Lei Shi, Xiao-Ming Yuan · 1 citation

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.