English
Related papers

Related papers: Partial Optimality of Dual Decomposition for MAP I…

200 papers

Lagrangian Relaxation (LR) is a powerful technique for solving large-scale Mixed Integer Linear Programming (MILP), particularly those with decomposable structures, such as vehicle routing or unit commitment problems. By relaxing the…

Machine Learning · Statistics 2026-05-27 Tung Quoc Le , Anh Tuan Nguyen , Viet Anh Nguyen

We consider the MAP-inference problem for graphical models, which is a valued constraint satisfaction problem defined on real numbers with a natural summation operation. We propose a family of relaxations (different from the famous…

Computer Vision and Pattern Recognition · Computer Science 2020-04-15 Stefan Haller , Paul Swoboda , Bogdan Savchynskyy

Multitrace formulations (MTFs) are based on a decomposition of the problem domain into subdomains, and thus domain decomposition solvers are of interest. The fully rigorous mathematical MTF can however be daunting for the non-specialist. We…

Numerical Analysis · Mathematics 2016-05-17 X. Claeys , V. Dolean , M. J. Gander

We consider the problem of learning the optimal policy for infinite-horizon Markov decision processes (MDPs). For this purpose, some variant of Stochastic Mirror Descent is proposed for convex programming problems with Lipschitz-continuous…

Optimization and Control · Mathematics 2022-03-01 Daniil Tiapkin , Alexander Gasnikov

Multi-agent proximal policy optimization (MAPPO) has recently demonstrated state-of-the-art performance on challenging multi-agent reinforcement learning tasks. However, MAPPO still struggles with the credit assignment problem, wherein the…

Multiagent Systems · Computer Science 2025-02-10 Aditya Kapoor , Benjamin Freed , Howie Choset , Jeff Schneider

The Minimum Cost Multicut Problem (MP) is a popular way for obtaining a graph decomposition by optimizing binary edge labels over edge costs. While the formulation of a MP from independently estimated costs per edge is highly flexible and…

Computer Vision and Pattern Recognition · Computer Science 2021-12-13 Steffen Jung , Sebastian Ziegler , Amirhossein Kardoost , Margret Keuper

While Markov Random Fields (MRFs) are widely used in computer vision, they present a quite challenging inference problem. MRF inference can be accelerated by pre-processing techniques like Dead End Elimination (DEE) or QPBO-based approaches…

Computer Vision and Pattern Recognition · Computer Science 2017-08-10 Chen Wang , Charles Herrmann , Ramin Zabih

Dense conditional random fields (CRF) with Gaussian pairwise potentials have emerged as a popular framework for several computer vision applications such as stereo correspondence and semantic segmentation. By modeling long-range…

Computer Vision and Pattern Recognition · Computer Science 2016-08-23 Alban Desmaison , Rudy Bunel , Pushmeet Kohli , Philip H. S. Torr , M. Pawan Kumar

Joint object matching, also known as multi-image matching, namely, the problem of finding consistent partial maps among all pairs of objects within a collection, is a crucial task in many areas of computer vision. This problem subsumes…

Optimization and Control · Mathematics 2022-11-29 Antonio De Rosa , Aida Khajavirad

Learning Markov decision processes (MDPs) in the presence of the adversary is a challenging problem in reinforcement learning (RL). In this paper, we study RL in episodic MDPs with adversarial reward and full information feedback, where the…

Machine Learning · Computer Science 2022-04-21 Jiafan He , Dongruo Zhou , Quanquan Gu

Soft demodulation of received symbols into bit log-likelihood ratios (LLRs) is at the very heart of multiple-input-multiple-output (MIMO) detection. However, the optimal maximum a posteriori (MAP) detector is complicated and infeasible to…

Signal Processing · Electrical Eng. & Systems 2022-08-18 Jiankun Zhang , Hao Wang , Jing Qian , Zhenxing Gao

We prove that the $\alpha$-expansion algorithm for MAP inference always returns a globally optimal assignment for Markov Random Fields with Potts pairwise potentials, with a catch: the returned assignment is only guaranteed to be optimal…

Machine Learning · Statistics 2021-06-16 Hunter Lang , David Sontag , Aravindan Vijayaraghavan

Stereo matching is a core task for many computer vision and robotics applications. Despite their dominance in traditional stereo methods, the hand-crafted Markov Random Field (MRF) models lack sufficient modeling accuracy compared to…

Computer Vision and Pattern Recognition · Computer Science 2024-10-24 Tongfan Guan , Chen Wang , Yun-Hui Liu

MAP inference for general energy functions remains a challenging problem. While most efforts are channeled towards improving the linear programming (LP) based relaxation, this work is motivated by the quadratic programming (QP) relaxation.…

Machine Learning · Computer Science 2012-06-22 Patrick Pletscher , Sharon Wulff

We study reinforcement learning (RL) with linear function approximation. For episodic time-inhomogeneous linear Markov decision processes (linear MDPs) whose transition probability can be parameterized as a linear function of a given…

Machine Learning · Computer Science 2023-11-07 Jiafan He , Heyang Zhao , Dongruo Zhou , Quanquan Gu

We propose a novel compact linear programming (LP) relaxation for binary sub-modular MRF in the context of object segmentation. Our model is obtained by linearizing an $l_1^+$-norm derived from the quadratic programming (QP) form of the MRF…

Computer Vision and Pattern Recognition · Computer Science 2014-04-10 Junyan Wang , Sai-Kit Yeung

Markov Decision Process (MDP) is the underlying model for optimal planning for decision-theoretic agents in stochastic environments. Although much research focuses on solving MDP problems both in tabular form or using factored…

Artificial Intelligence · Computer Science 2021-03-02 Daniela Kuinchtner , Afonso Sales , Felipe Meneguzzi

Integer Linear Programming (ILP) formulations of Markov random fields (MRFs) models with global connectivity priors were investigated previously in computer vision, e.g., \cite{globalinter,globalconn}. In these works, only Linear Programing…

Computer Vision and Pattern Recognition · Computer Science 2018-03-21 Ruobing Shen , Eric Kendinibilir , Ismail Ben Ayed , Andrea Lodi , Andrea Tramontani , Gerhard Reinelt

To overcome the curses of dimensionality and modeling of Dynamic Programming (DP) methods to solve Markov Decision Process (MDP) problems, Reinforcement Learning (RL) methods are adopted in practice. Contrary to traditional RL algorithms…

Machine Learning · Computer Science 2021-08-24 Arghyadip Roy , Vivek Borkar , Abhay Karandikar , Prasanna Chaporkar

We consider the structured-output prediction problem through probabilistic approaches and generalize the "perturb-and-MAP" framework to more challenging weighted Hamming losses, which are crucial in applications. While in principle our…

Machine Learning · Statistics 2018-11-22 Tatiana Shpakova , Francis Bach , Anton Osokin
‹ Prev 1 4 5 6 7 8 10 Next ›