English
Related papers

Related papers: An extrapolated and provably convergent algorithm …

200 papers

In this paper we present a novel randomized block coordinate descent method for the minimization of a convex composite objective function. The method uses (approximate) partial second-order (curvature) information, so that the algorithm…

Optimization and Control · Mathematics 2015-05-11 Kimon Fountoulakis , Rachael Tappenden

Multi-criteria decision-making often requires finding a small representative set from the database. A recently proposed method is the regret minimization set (RMS) query. RMS returns a size $r$ subset $S$ of dataset $D$ that minimizes the…

Machine Learning · Computer Science 2022-03-10 Xingxing Xiao , Jianzhong Li

Low-rank representation (LRR) is an effective method for subspace clustering and has found wide applications in computer vision and machine learning. The existing LRR solver is based on the alternating direction method (ADM). It suffers…

Optimization and Control · Mathematics 2011-09-05 Zhouchen Lin , Risheng Liu , Zhixun Su

Many imaging science tasks can be modeled as a discrete linear inverse problem. Solving linear inverse problems is often challenging, with ill-conditioned operators and potentially non-unique solutions. Embedding prior knowledge, such as…

Numerical Analysis · Mathematics 2023-12-07 Elizabeth Newman , Jack Michael Solomon , Matthias Chung

Tensor decomposition (TD) is essential for analyzing high-dimensional sparse data, yet its irregular computations and memory-access patterns pose major performance challenges on modern parallel processors. Prior works rely on…

Machine Learning · Computer Science 2025-09-03 Ahmed E. Helal , Fabio Checconi , Jan Laukemann , Yongseok Soh , Jesmin Jahan Tithi , Fabrizio Petrini , Jee Choi

In this paper, we introduce a powerful technique based on Leave-one-out analysis to the study of low-rank matrix completion problems. Using this technique, we develop a general approach for obtaining fine-grained, entrywise bounds for…

Machine Learning · Statistics 2020-06-18 Lijun Ding , Yudong Chen

Matrix representations are a powerful tool for designing efficient algorithms for combinatorial optimization problems such as matching, and linear matroid intersection and parity. In this paper, we initiate the study of matrix…

Optimization and Control · Mathematics 2024-10-18 Taihei Oki , Tasuku Soma

We propose a prox-regular-type low-rank constrained nonconvex nonsmooth optimization model for Robust Low-Rank Matrix Recovery (RLRMR), i.e., estimate problem of low-rank matrix from an observed signal corrupted by outliers. For RLRMR, the…

Optimization and Control · Mathematics 2026-02-03 Keita Kume , Isao Yamada

LU-factorization of matrices is one of the fundamental algorithms of linear algebra. The widespread use of supercomputers with distributed memory requires a review of traditional algorithms, which were based on the common memory of a…

Symbolic Computation · Computer Science 2020-11-10 Gennadi Malaschonok

Low Rank Decomposition of matrix - splitting a large matrix into a product of two smaller matrix offers a means for compression that reduces the parameters of a model without sparsification, and hence delivering more speedup on modern…

Computation and Language · Computer Science 2023-09-26 Ayush Kaushal , Tejas Vaidhya , Irina Rish

By lifting the ReLU function into a higher dimensional space, we develop a smooth multi-convex formulation for training feed-forward deep neural networks (DNNs). This allows us to develop a block coordinate descent (BCD) training algorithm…

Machine Learning · Statistics 2017-11-21 Ziming Zhang , Matthew Brand

To improve the training efficiency of federated learning (FL), previous research has employed low-rank decomposition techniques to reduce communication overhead. In this paper, we seek to enhance the performance of these low-rank…

Machine Learning · Computer Science 2025-08-19 Shiwei Li , Xiandi Luo , Haozhao Wang , Xing Tang , Shijie Xu , Weihong Luo , Yuhua Li , Xiuqiang He , Ruixuan Li

Dictionary Learning (DL) is one of the leading sparsity promoting techniques in the context of image classification, where the "dictionary" matrix D of images and the sparse matrix X are determined so as to represent a redundant image…

Numerical Analysis · Mathematics 2022-03-10 Domitilla Brandoni , Margherita Porcelli , Valeria Simoncini

We propose a theoretical framework to analyze semi-supervised classification under the low density separation assumption in a high-dimensional regime. In particular, we introduce QLDS, a linear classification model, where the low density…

Machine Learning · Computer Science 2023-10-23 Vasilii Feofanov , Malik Tiomoko , Aladin Virmaux

The low-rank matrix recovery problem seeks to reconstruct an unknown $n_1 \times n_2$ rank-$r$ matrix from $m$ linear measurements, where $m\ll n_1n_2$. This problem has been extensively studied over the past few decades, leading to a…

Machine Learning · Statistics 2026-04-02 Zhenxuan Li , Meng Huang

This work considers low-rank canonical polyadic decomposition (CPD) under a class of non-Euclidean loss functions that frequently arise in statistical machine learning and signal processing. These loss functions are often used for certain…

Machine Learning · Statistics 2022-05-11 Wenqiang Pu , Shahana Ibrahim , Xiao Fu , Mingyi Hong

This paper introduces a deep reinforcement learning-based block coordinate descent (DRL-based BCD) algorithm to address the nonconvex weighted sum-rate maximization (WSRM) problem with a total power constraint. Firstly, we present an…

Networking and Internet Architecture · Computer Science 2026-02-25 Siya Chen , Chee Wei Tan , H. Vincent Poor

Tensors decompositions are a class of tools for analysing datasets of high dimensionality and variety in a natural manner, with the Canonical Polyadic Decomposition (CPD) being a main pillar. While the notion of CPD is closely intertwined…

Signal Processing · Electrical Eng. & Systems 2019-11-15 Giuseppe G. Calvi , Bruno Scalzo Dees , Danilo P. Mandic

It is shown that over-parameterized neural networks can achieve minimax optimal rates of convergence (up to logarithmic factors) for learning functions from certain smooth function classes, if the weights are suitably constrained or…

Machine Learning · Statistics 2024-06-05 Yunfei Yang , Ding-Xuan Zhou

We study binary optimization problems of the form \( \min_{x\in\{-1,1\}^n} f(Ax-b) \) with possibly nonsmooth loss \(f\). Following the lifted rank-one semidefinite programming (SDP) approach\cite{qian2023matrix}, we develop a…

Optimization and Control · Mathematics 2026-01-07 Lianghai Xiao , Yitian Qian , Shaohua Pan