Lune

NeurIPS2025Top-tier venue

Bivariate Matrix-valued Linear Regression (BMLR): Finite-sample performance under Identifiability and Sparsity Assumptions

Nayel Bettache

Abstract

This study explores the estimation of parameters in a matrix-valued linear regression model, where the TT responses (Yt)t=1T∈Rn×p(Y_t)_{t=1}^T \in \mathbb{R}^{n \times p} and predictors (Xt)t=1T∈Rm×q(X_t)_{t=1}^T \in \mathbb{R}^{m \times q} satisfy the relationship Yt=A∗XtB∗+EtY_t = A^* X_t B^* + E_t for all t=1,…,Tt = 1, \ldots, T. In this model, A∗∈R+n×mA^* \in \mathbb{R}_+^{n \times m} has L1L_1-normalized rows, B∗∈Rq×pB^* \in \mathbb{R}^{q \times p}, and (Et)t=1T(E_t)_{t=1}^T are independent noise matrices following a matrix Gaussian distribution. The primary objective is to estimate the unknown parameters A∗A^* and B∗B^* efficiently. We propose explicit optimization-free estimators and establish non-asymptotic convergence rates to quantify their performance. Additionally, we extend our analysis to scenarios where A∗A^* and B∗B^* exhibit sparse structures. To support our theoretical findings, we conduct numerical simulations that confirm the behavior of the estimators, particularly with respect to the impact of the dimensions n,m,p,qn, m, p, q, and the sample size TT on finite-sample performances. We complete the simulations by investigating the denoising performances of our estimators on noisy real-world images.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Related papers

  1. Sparse Linear Regression Is Easy on Random SupportsGautam Chandrasekaran, Raghu Meka, Konstantinos StavropoulosSTOC 2026
  2. Finite Sample Analysis Of Dynamic Regression Parameter LearningMark Kozdoba, Edward Moroshko, Shie Mannor, Yacov CrammerNeurIPS 2022
  3. A convex optimization formulation for multivariate regressionYunzhang ZhuNeurIPS 2020 · 10 citations
  4. A Completely Tuning-Free and Robust Approach to Sparse Precision Matrix EstimationChau Tran, Guo YuICML 2022 · 4 citations
  5. How Over-Parameterization Slows Down Gradient Descent in Matrix Sensing: The Curses of Symmetry and InitializationNuoya Xiong, Lijun Ding, Simon Shaolei DuICLR 2024 · 22 citations
Dusk over the sea between two cliffs drawn in fine vertical lines