PulseAugur
LIVE 10:06:33
research · [5 sources] ·
0
research

Researchers propose new algorithms for matrix and tensor completion tasks

By PulseAugur Editorial · Summary by gemini-2.5-flash-lite from 5 sources

Researchers have developed a novel algorithm for low-rank tensor completion, extending matrix completion techniques using an alternating direction method of multipliers (ADMM) optimization framework. This new method reformulates the problem into subproblems solved iteratively, incorporating over-relaxation and adaptive penalty parameters to enhance convergence and performance. Separately, a new multi-task active learning algorithm called MAlocate has been proposed for simultaneously solving multiple matrix completion problems, adapting to unknown matrix ranks and demonstrating minimax-optimality. AI

Summary written by gemini-2.5-flash-lite from 5 sources. How we write summaries →

IMPACT These papers introduce new algorithmic approaches for tensor and matrix completion, potentially improving data imputation and analysis in various machine learning applications.

RANK_REASON Two distinct arXiv papers are presented, one on low-rank tensor completion via ADMM and another on active multiple matrix completion.

Read on arXiv stat.ML →

COVERAGE [5]

  1. arXiv cs.LG TIER_1 · Chandler Smith, HanQin Cai, Abiy Tasissa ·

    Provable Non-Convex Euclidean Distance Matrix Completion: Geometry, Reconstruction, and Robustness

    arXiv:2508.00091v3 Announce Type: replace-cross Abstract: The problem of recovering the configuration of points from their partial pairwise distances, referred to as the Euclidean Distance Matrix Completion (EDMC) problem, arises in a broad range of applications, including sensor…

  2. arXiv cs.LG TIER_1 · Niclas F\"uhrling, Getuar Rexhepi, Giuseppe Thadeu Freitas de Abreu ·

    Low Rank Tensor Completion via Adaptive ADMM

    arXiv:2605.03736v1 Announce Type: cross Abstract: We consider a novel algorithm, for the completion of partially observed low-rank tensors, as a generalization of matrix completion. The proposed low-rank tensor completion (TC) method builds on the conventional nuclear norm (NN) m…

  3. arXiv cs.LG TIER_1 · Giuseppe Thadeu Freitas de Abreu ·

    Low Rank Tensor Completion via Adaptive ADMM

    We consider a novel algorithm, for the completion of partially observed low-rank tensors, as a generalization of matrix completion. The proposed low-rank tensor completion (TC) method builds on the conventional nuclear norm (NN) minimization-based low-rank TC paradigm, by leverag…

  4. arXiv stat.ML TIER_1 · Andrea Locatelli, Alexandra Carpentier, Michal Valko ·

    Active multiple matrix completion with adaptive confidence sets

    arXiv:2605.02458v1 Announce Type: new Abstract: In this work, we formulate a new multi-task active learning setting in which the learner's goal is to solve multiple matrix completion problems simultaneously. At each round, the learner can choose from which matrix it receives a sa…

  5. arXiv stat.ML TIER_1 · Michal Valko ·

    Active multiple matrix completion with adaptive confidence sets

    In this work, we formulate a new multi-task active learning setting in which the learner's goal is to solve multiple matrix completion problems simultaneously. At each round, the learner can choose from which matrix it receives a sample from an entry drawn uniformly at random. Ou…

RELATED ENTITIES

RELATED TOPICS