Matrix Estimation

Matrix estimation focuses on recovering complete matrices from incomplete or noisy observations, aiming to accurately predict missing values and understand underlying structure. Current research emphasizes developing algorithms robust to arbitrary sampling patterns and non-linear noise, exploring techniques like network flow analysis and unrolled iterative algorithms (e.g., SpodNet for positive-definite matrices) to improve estimation accuracy and efficiency. These advancements have significant implications across diverse fields, including reinforcement learning, causal inference, and fairness-aware machine learning, by enabling more accurate modeling and improved decision-making in the face of incomplete or uncertain data.

Papers

October 30, 2024

Model-free Low-Rank Reinforcement Learning via Leveraged Entry-wise Matrix Estimation
Stefan Stojanovic, Yassir Jedra, Alexandre Proutiere
Reinforcement Learning Optimal Policy Model Free Policy Iteration Low Rank Matrix Free Learning Matrix Estimation

September 6, 2024

Entry-Specific Matrix Estimation under Arbitrary Sampling Patterns through the Lens of Network Flows
Yudong Chen, Xumei Xi, Christina Lee Yu
Network Programming Camera Lens Matrix Completion Low Rank Matrix Data Sampling Minimax Optimal Matrix Estimation

June 13, 2024

Schur's Positive-Definite Network: Deep Learning in the SPD cone with structure
Can Pouliquen, Mathurin Massias, Titouan Vayer
Deep Learning Inner Structure Sparse Matrix Symmetric Positive Definite Matrix Estimation

March 7, 2024

Fundamental limits of Non-Linear Low-Rank Matrix Estimation
Pierre Mergny, Justin Ko, Florent Krzakala, Lenka Zdeborová
Fisher Information Non Linear Gaussian Model Fundamental Limit Mean Squared Error Matrix Estimation

February 17, 2024

Efficient Low-Rank Matrix Estimation, Experimental Design, and Arm-Set-Dependent Low-Rank Bandits
Kyoungseok Jang, Chicheng Zhang, Kwang-Sung Jun
High Efficiency Low Rank Experimental Design Low Rank Matrix Estimation Matrix Estimation

January 24, 2024

Weakly supervised covariance matrices alignment through Stiefel matrices estimation for MEG applications
Antoine Collas, Rémi Flamary, Alexandre Gramfort
Global Mixing Covariance Alignment Domain Mixing Novel Domain Adaptation Matrix Estimation Magnetoencephalography Data

January 4, 2024

Structured Matrix Learning under Arbitrary Entrywise Dependence and Estimation of Markov Transition Kernel
Jinhang Chai, Jianqing Fan
Estimation Task Low Rank Matrix Transition Kernel Low Rank Matrix Recovery Matrix Estimation Matrix Learning

October 10, 2023

Spectral Entry-wise Matrix Estimation for Low-Rank Reinforcement Learning
Stefan Stojanovic, Yassir Jedra, Alexandre Proutiere
Low Rank Low Rank Matrix Estimation Matrix Estimation

May 24, 2023

Matrix Estimation for Offline Reinforcement Learning with Low-Rank Structure
Xumei Xi, Christina Lee Yu, Yudong Chen
Offline Reinforcement Learning Inner Structure State Action Pair Offline Policy Evaluation Matrix Estimation

February 4, 2023

Matrix Estimation for Individual Fairness
Cindy Y. Zhang, Sarah H. Cen, Devavrat Shah
Algorithmic Fairness Individual Fairness Fairness Performance Trade Matrix Estimation

Matrix Estimation

Papers

Model-free Low-Rank Reinforcement Learning via Leveraged Entry-wise Matrix Estimation

Entry-Specific Matrix Estimation under Arbitrary Sampling Patterns through the Lens of Network Flows

Schur's Positive-Definite Network: Deep Learning in the SPD cone with structure

Fundamental limits of Non-Linear Low-Rank Matrix Estimation

Efficient Low-Rank Matrix Estimation, Experimental Design, and Arm-Set-Dependent Low-Rank Bandits

Weakly supervised covariance matrices alignment through Stiefel matrices estimation for MEG applications

Structured Matrix Learning under Arbitrary Entrywise Dependence and Estimation of Markov Transition Kernel

Spectral Entry-wise Matrix Estimation for Low-Rank Reinforcement Learning

Matrix Estimation for Offline Reinforcement Learning with Low-Rank Structure

Matrix Estimation for Individual Fairness