English
Related papers

Related papers: Decomposition Bounds for Marginal MAP

200 papers

Model merging has emerged as an effective approach to combine multiple single-task models into a multitask model. This process typically involves computing a weighted average of the model parameters without any additional training. Existing…

Machine Learning · Computer Science 2025-04-28 Lu Li , Tianyu Zhang , Zhiqi Bu , Suyuchen Wang , Huan He , Jie Fu , Yonghui Wu , Jiang Bian , Yong Chen , Yoshua Bengio

This paper is about how to partition decision variables while decomposing a large-scale optimization problem for the best performance of distributed solution methods. Solving a large-scale optimization problem sequen- tially can be…

Optimization and Control · Mathematics 2017-10-26 Yuchen Zheng , Ilbin Lee , Nicoleta Serban

In the distributed optimization problem for a multi-agent system, each agent knows a local function and must find a minimizer of the sum of all agents' local functions by performing a combination of local gradient evaluations and…

Optimization and Control · Mathematics 2022-06-16 Bryan Van Scoy , Laurent Lessard

Structured prediction requires searching over a combinatorial number of structures. To tackle it, we introduce SparseMAP: a new method for sparse structured inference, and its natural loss function. SparseMAP automatically selects only a…

Machine Learning · Statistics 2018-06-21 Vlad Niculae , André F. T. Martins , Mathieu Blondel , Claire Cardie

We study two-stage stochastic optimization models with mixed-integer decision variables appearing in both stages. For these models, dual decomposition enables parallel computing implementation and can quickly provide a lower bound for the…

Optimization and Control · Mathematics 2026-05-15 Pengyu Zhang , Ruiwei Jiang

Image denoising can be described as the problem of mapping from a noisy image to a noise-free image. The best currently available denoising methods approximate this mapping with cleverly engineered algorithms. In this work we attempt to…

Computer Vision and Pattern Recognition · Computer Science 2012-11-12 Harold Christopher Burger , Christian J. Schuler , Stefan Harmeling

In this paper, we propose a distributed algorithm for solving large-scale separable convex problems using Lagrangian dual decomposition and the interior-point framework. By adding self-concordant barrier terms to the ordinary Lagrangian, we…

Optimization and Control · Mathematics 2013-02-14 I. Necoara , J. A. K. Suykens

Existing results on decomposition methods and algorithms for nonconvex problems are minimal. Parallel decomposition algorithms do not exist for nonconvex problems with coupling nonlinear equality constraints. Besides, decomposition…

Optimization and Control · Mathematics 2026-05-18 Yiqing Zhai , Ying Cui , Danny H. K. Tsang

We attempt image restoration in the framework of the Baysian inference. Recently, it has been shown that under a certain criterion the MAP (Maximum A Posterior) estimate, which corresponds to the minimization of energy, can be outperformed…

Disordered Systems and Neural Networks · Physics 2009-11-07 Hayaru Shouno , Koji Wada , Masato Okada

In recent years, end-to-end autonomous driving has attracted increasing attention for its ability to jointly model perception, prediction, and planning within a unified framework. However, most existing approaches underutilize the online…

Robotics · Computer Science 2025-09-18 Huilin Yin , Yiming Kan , Daniel Watzenig

This study develops an algorithm for distributed computing of linear programming problems of huge-scales. Global consensus with single common variable, multiblocks, and augmented Lagrangian are adopted. The consensus is used to partition…

Optimization and Control · Mathematics 2025-08-07 Luoyi Tao

In this paper we develop random block coordinate gradient descent methods for minimizing large scale linearly constrained separable convex problems over networks. Since we have coupled constraints in the problem, we devise an algorithm that…

Optimization and Control · Mathematics 2015-12-14 I. Necoara , Yu. Nesterov , F. Glineur

The maximum a-posteriori (MAP) perturbation framework has emerged as a useful approach for inference and learning in high dimensional complex models. By maximizing a randomly perturbed potential function, MAP perturbations generate unbiased…

Machine Learning · Computer Science 2013-10-17 Francesco Orabona , Tamir Hazan , Anand D. Sarwate , Tommi Jaakkola

A fruitful approach for solving signal deconvolution problems consists of resorting to a frame-based convex variational formulation. In this context, parallel proximal algorithms and related alternating direction methods of multipliers have…

Other Computer Science · Computer Science 2015-05-28 Nelly Pustelnik , Jean-Christophe Pesquet , Caroline Chaux

We introduce a new overlapping Domain Decomposition Method (DDM) to solve the fully nonlinear Monge-Amp\`ere equation. While DDMs have been extensively studied for linear problems, their application to fully nonlinear partial differential…

Numerical Analysis · Mathematics 2023-06-05 Yassine Boubendir , Jake Brusca , Brittany Froese Hamfeldt , Tadanaga Takahashi

The paper considers the problem of network-based computation of global minima in smooth nonconvex optimization problems. It is known that distributed gradient-descent-type algorithms can achieve convergence to the set of global minima by…

Optimization and Control · Mathematics 2019-10-24 Brian Swenson , Anirudh Sridhar , H. Vincent Poor

MapReduce (and its open source implementation Hadoop) has become the de facto platform for processing large data sets. MapReduce offers a streamlined computational framework by interleaving sequential and parallel computation while hiding…

Computational Complexity · Computer Science 2019-04-22 Sungjin Im , Benjamin Moseley

We consider the task of decentralized minimization of the sum of smooth strongly convex functions stored across the nodes of a network. For this problem, lower bounds on the number of gradient computations and the number of communication…

Optimization and Control · Mathematics 2020-11-16 Dmitry Kovalev , Adil Salim , Peter Richtárik

Convergence guarantees for optimization over bounded-rank matrices are delicate to obtain because the feasible set is a non-smooth and non-convex algebraic variety. Existing techniques include projected gradient descent, fixed-rank…

Optimization and Control · Mathematics 2024-06-21 Quentin Rebjock , Nicolas Boumal

While convergence of the Alternating Direction Method of Multipliers (ADMM) on convex problems is well studied, convergence on nonconvex problems is only partially understood. In this paper, we consider the Gaussian phase retrieval problem,…

Information Theory · Computer Science 2017-12-07 David Barmherzig , Ju Sun