English
Related papers

Related papers: Simplifying Optimal Transport through Schatten-$p$…

200 papers

Policy optimization is among the most popular and successful reinforcement learning algorithms, and there is increasing interest in understanding its theoretical guarantees. In this work, we initiate the study of policy optimization for the…

Machine Learning · Computer Science 2022-02-08 Liyu Chen , Haipeng Luo , Aviv Rosenberg

We investigate the approximation of Monge--Kantorovich problems on general compact metric spaces, showing that optimal values, plans and maps can be effectively approximated via a fully discrete method. First we approximate optimal values…

Numerical Analysis · Mathematics 2024-01-29 Maximiliano Frungillo

We consider convex relaxations for recovering low-rank tensors based on constrained minimization over a ball induced by the tensor nuclear norm, recently introduced in \cite{tensor_tSVD}. We build on a recent line of results that considered…

Optimization and Control · Mathematics 2023-08-04 Dan Garber , Atara Kaplan

We study the problem of estimating low-rank matrices from linear measurements (a.k.a., matrix sensing) through nonconvex optimization. We propose an efficient stochastic variance reduced gradient descent algorithm to solve a nonconvex…

Machine Learning · Statistics 2017-01-17 Xiao Zhang , Lingxiao Wang , Quanquan Gu

Scaling algorithms for entropic transport-type problems have become a very popular numerical method, encompassing Wasserstein barycenters, multi-marginal problems, gradient flows and unbalanced transport. However, a standard implementation…

Optimization and Control · Mathematics 2019-02-12 Bernhard Schmitzer

Transport maps have become a popular mechanic to express complicated probability densities using sample propagation through an optimized push-forward. Beside their broad applicability and well-known success, transport maps suffer from…

Numerical Analysis · Mathematics 2020-08-11 Martin Eigel , Robert Gruhlke , Manuel Marschall

We propose a novel framework for learning stabilizable nonlinear dynamical systems for continuous control tasks in robotics. The key contribution is a control-theoretic regularizer for dynamics fitting rooted in the notion of…

Optimization and Control · Mathematics 2019-08-01 Sumeet Singh , Spencer M. Richards , Vikas Sindhwani , Jean-Jacques E. Slotine , Marco Pavone

The need to reason about uncertainty in large, complex, and multi-modal datasets has become increasingly common across modern scientific environments. The ability to transform samples from one distribution $P$ to another distribution $Q$…

Machine Learning · Statistics 2018-11-30 Diego A. Mesa , Justin Tantiongloc , Marcela Mendoza , Todd P. Coleman

In this paper, we study the trace regression when a matrix of parameters B* is estimated via the convex relaxation of a rank-regularized regression or via regularized non-convex optimization. It is known that these estimators satisfy…

Machine Learning · Computer Science 2023-08-31 Nima Hamidi , Mohsen Bayati

Recovering a large matrix from limited measurements is a challenging task arising in many real applications, such as image inpainting, compressive sensing and medical imaging, and this kind of problems are mostly formulated as low-rank…

Computer Vision and Pattern Recognition · Computer Science 2014-06-12 Yilun Wang , Xinhua Su

The low-rank approximation is a complexity reduction technique to approximate a tensor or a matrix with a reduced rank, which has been applied to the simulation of high dimensional problems to reduce the memory required and computational…

Computational Physics · Physics 2020-08-26 Zhuogang Peng , Ryan McClarren , Martin Frank

Traffic-density matrices from different days exhibit both low rank and stable correlations in their singular-vector subspaces. Leveraging this, we introduce SATORIS-N, a framework for imputing partially observed traffic-density by informed…

Machine Learning · Computer Science 2026-02-04 Sampad Mohanty , Bhaskar Krishnamachari

Estimation of low-rank matrices is of significant interest in a range of contemporary applications. In this paper, we introduce a rank-one projection model for low-rank matrix recovery and propose a constrained nuclear norm minimization…

Statistics Theory · Mathematics 2014-12-10 T. Tony Cai , Anru Zhang

We present new policy mirror descent (PMD) methods for solving reinforcement learning (RL) problems with either strongly convex or general convex regularizers. By exploring the structural properties of these overall highly nonconvex…

Machine Learning · Computer Science 2022-04-08 Guanghui Lan

The quadratically regularized optimal transport problem is empirically known to have sparse solutions: its optimal coupling $\pi_{\varepsilon}$ has sparse support for small regularization parameter $\varepsilon$, in contrast to entropic…

Optimization and Control · Mathematics 2026-02-25 Alberto González-Sanz , Marcel Nutz

Many applications require recovering a matrix of minimal rank within an affine constraint set, with matrix completion a notable special case. Because the problem is NP-hard in general, it is common to replace the matrix rank with the…

Machine Learning · Computer Science 2015-07-08 Bo Xin , David Wipf

Matrix-valued optimization tasks, including those involving symmetric positive definite (SPD) matrices, arise in a wide range of applications in machine learning, data science and statistics. Classically, such problems are solved via…

Optimization and Control · Mathematics 2024-10-15 Andrew Cheng , Melanie Weber

We propose a novel end-to-end non-minimax algorithm for training optimal transport mappings for the quadratic cost (Wasserstein-2 distance). The algorithm uses input convex neural networks and a cycle-consistency regularization to…

Machine Learning · Computer Science 2020-12-11 Alexander Korotin , Vage Egiazarian , Arip Asadulaev , Alexander Safin , Evgeny Burnaev

We present Spartan, a method for training sparse neural network models with a predetermined level of sparsity. Spartan is based on a combination of two techniques: (1) soft top-k masking of low-magnitude parameters via a regularized optimal…

Machine Learning · Computer Science 2022-10-18 Kai Sheng Tai , Taipeng Tian , Ser-Nam Lim

The current best practice for computing optimal transport (OT) is via entropy regularization and Sinkhorn iterations. This algorithm runs in quadratic time as it requires the full pairwise cost matrix, which is prohibitively expensive for…

Machine Learning · Computer Science 2022-04-06 Johannes Gasteiger , Marten Lienen , Stephan Günnemann
‹ Prev 1 8 9 10 Next ›