English
Related papers

Related papers: Linear Convergence of Gradient Descent for Quadrat…

200 papers

Weight decay is one of the most widely used forms of regularization in deep learning, and has been shown to improve generalization and robustness. The optimization objective driving weight decay is a sum of losses plus a term proportional…

Machine Learning · Computer Science 2023-07-07 Liu Yang , Jifan Zhang , Joseph Shenouda , Dimitris Papailiopoulos , Kangwook Lee , Robert D. Nowak

Neural networks have shown tremendous potential for reconstructing high-resolution images in inverse problems. The non-convex and opaque nature of neural networks, however, hinders their utility in sensitive applications such as medical…

Machine Learning · Computer Science 2020-12-10 Arda Sahiner , Morteza Mardani , Batu Ozturkler , Mert Pilanci , John Pauly

Optimal Transport is a useful metric to compare probability distributions and to compute a pairing given a ground cost. Its entropic regularization variant (eOT) is crucial to have fast algorithms and reflect fuzzy/noisy matchings. This…

Statistics Theory · Mathematics 2024-03-12 Francisco Andrade , Gabriel Peyre , Clarice Poon

Bilevel optimization has been developed for many machine learning tasks with large-scale and high-dimensional data. This paper considers a constrained bilevel optimization problem, where the lower-level optimization problem is convex with…

Machine Learning · Computer Science 2023-08-22 Siyuan Xu , Minghui Zhu

In this paper, we consider the decentralized optimization problems with generalized orthogonality constraints, where both the objective function and the constraint exhibit a distributed structure. Such optimization problems, albeit…

Optimization and Control · Mathematics 2024-09-10 Lei Wang , Nachuan Xiao , Xin Liu

We study the existing algorithms that solve the multidimensional martingale optimal transport. Then we provide a new algorithm based on entropic regularization and Newton's method. Then we provide theoretical convergence rate results and we…

Probability · Mathematics 2018-12-31 Hadrien De March

Recently, there has been a great interest in analysing dynamical flows, where the stationary limit is the minimiser of a convex energy. Particular flows of great interest have been continuous limits of Nesterov's algorithm and the Fast…

Optimization and Control · Mathematics 2021-06-29 Radu Boţ , Guozhi Dong , Peter Elbau , Otmar Scherzer

This paper considers smooth convex optimization problems with many functional constraints. To solve this general class of problems we propose a new stochastic perturbed augmented Lagrangian method, called SGDPA, where a perturbation is…

Optimization and Control · Mathematics 2025-04-01 Nitesh Kumar Singh , Ion Necoara

We propose an adaptive refinement algorithm to solve total variation regularized measure optimization problems. The method iteratively constructs dyadic partitions of the unit cube based on i) the resolution of discretized dual problems and…

Optimization and Control · Mathematics 2023-01-19 Axel Flinth , Frédéric de Gournay , Pierre Weiss

Dual decomposition approaches in nonconvex optimization may suffer from a duality gap. This poses a challenge when applying them directly to nonconvex problems such as MAP-inference in a Markov random field (MRF) with continuous state…

Optimization and Control · Mathematics 2022-05-17 Hartmut Bauermeister , Emanuel Laude , Thomas Möllenhoff , Michael Moeller , Daniel Cremers

This paper introduces a novel double regularization scheme for bilevel optimization problems whose lower-level problem is composite and convex, but not necessarily strongly convex, in the lower-level variable. The analysis focuses on the…

Optimization and Control · Mathematics 2026-02-06 Mattia Solla , Johannes O. Royset

Gradient-flow analyses show that simplified linear transformers can learn the in-context linear-regression algorithm, but they do not explain the finite-step behavior of gradient descent at large learning rates. Motivated by empirical work…

Machine Learning · Statistics 2026-05-21 Krishnakumar Balasubramanian

The convergence of policy gradient algorithms hinges on the optimization landscape of the underlying optimal control problem. Theoretical insights into these algorithms can often be acquired from analyzing those of linear quadratic control.…

Optimization and Control · Mathematics 2023-11-02 Jingliang Duan , Wenhan Cao , Yang Zheng , Lin Zhao

Recent work by Mania et al. has proved that certainty equivalent control achieves nearly optimal regret for linear systems with quadratic costs. However, when parameter uncertainty is large, certainty equivalence cannot be relied upon to…

Optimization and Control · Mathematics 2020-01-01 Jack Umenberger , Thomas B. Schon

In this paper we consider the cubic regularization (CR) method for minimizing a twice continuously differentiable function. While the CR method is widely recognized as a globally convergent variant of Newton's method with superior iteration…

Optimization and Control · Mathematics 2018-01-30 Man-Chung Yue , Zirui Zhou , Anthony Man-Cho So

The stochastic gradient descent has been widely used for solving composite optimization problems in big data analyses. Many algorithms and convergence properties have been developed. The composite functions were convex primarily and…

Machine Learning · Statistics 2020-03-03 Takayuki Kawashima , Hironori Fujisawa

We study the quadratically regularized optimal transport (QOT) problem for quadratic cost and compactly supported marginals $\mu$ and $\nu$. It has been empirically observed that the optimal coupling $\pi_\epsilon$ for the QOT problem has…

Optimization and Control · Mathematics 2024-10-07 Johannes Wiesel , Xingyu Xu

In this paper, we consider a discrete-time stochastic control problem with uncertain initial and target states. We first discuss the connection between optimal transport and stochastic control problems of this form. Next, we formulate a…

This paper presents a regularization technique incorporating a non-convex and non-smooth term, $\ell_{1}^{2}-\eta\ell_{2}^{2}$, with parameters $0<\eta\leq 1$ designed to address ill-posed linear problems that yield sparse solutions. We…

Optimization and Control · Mathematics 2025-06-16 Long Li , Liang Ding

This paper studies binary quadratic programs in which the objective is defined by a Euclidean distance matrix, subject to a general polyhedral constraint set. This class of nonconcave maximisation problems includes the capacitated,…

Optimization and Control · Mathematics 2023-09-19 Hoa T. Bui , Sandy Spiers , Ryan Loxton