English
Related papers

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

200 papers

We study offline Reinforcement Learning in large infinite-horizon discounted Markov Decision Processes (MDPs) when the reward and transition models are linearly realizable under a known feature map. Starting from the classic linear-program…

Machine Learning · Computer Science 2024-05-24 Gergely Neu , Nneka Okolo

We develop a general framework for MAP estimation in discrete and Gaussian graphical models using Lagrangian relaxation techniques. The key idea is to reformulate an intractable estimation problem as one defined on a more tractable graph,…

Artificial Intelligence · Computer Science 2007-10-02 Jason K. Johnson , Dmitry M. Malioutov , Alan S. Willsky

The typical approach for recovery of spatially correlated signals is regularized least squares with a coupled regularization term. In the Bayesian framework, this algorithm is seen as a maximum-a-posterior estimator whose postulated prior…

Information Theory · Computer Science 2018-05-31 Ali Bereyhi , Saeid Haghighatshoar , Ralf R. Müller

We study entropy-regularized constrained Markov decision processes (CMDPs) under the soft-max parameterization, in which an agent aims to maximize the entropy-regularized value function while satisfying constraints on the expected total…

Machine Learning · Computer Science 2023-04-10 Donghao Ying , Yuhao Ding , Javad Lavaei

We present a randomized maximum a posteriori (rMAP) method for generating approximate samples of posteriors in high dimensional Bayesian inverse problems governed by large-scale forward problems. We derive the rMAP approach by: 1) casting…

Computation · Statistics 2016-02-12 Kainan Wang , Tan Bui-Thanh , Omar Ghattas

Most popular dimension reduction (DR) methods like t-SNE and UMAP are based on minimizing a cost between input and latent pairwise similarities. Though widely used, these approaches lack clear probabilistic foundations to enable a full…

Probability · Mathematics 2023-10-06 Hugues Van Assel , Thibault Espinasse , Julien Chiquet , Franck Picard

Lagrangian relaxation stands among the most efficient approaches for solving a Mixed Integer Linear Programs (MILP) with difficult constraints. Given any duals for these constraints, called Lagrangian Multipliers (LMs), it returns a bound…

Machine Learning · Computer Science 2024-10-21 Francesco Demelas , Joseph Le Roux , Mathieu Lacroix , Axel Parmentier

Approximate dynamic programming is a popular method for solving large Markov decision processes. This paper describes a new class of approximate dynamic programming (ADP) methods- distributionally robust ADP-that address the curse of…

Machine Learning · Statistics 2012-05-22 Marek Petrik

In this contribution, we are concerned with parameter optimization problems that are constrained by multiscale PDE state equations. As an efficient numerical solution approach for such problems, we introduce and analyze a new relaxed and…

Numerical Analysis · Mathematics 2023-04-13 Tim Keil , Mario Ohlberger

Markov decision processes (MDPs) with large number of states are of high practical interest. However, conventional algorithms to solve MDP are computationally infeasible in this scenario. Approximate dynamic programming (ADP) methods tackle…

Systems and Control · Computer Science 2014-11-19 Chandrashekar Lakshminarayanan , Shalabh Bhatnagar

We consider the problem of jointly estimating the parameters as well as the structure of binary valued Markov Random Fields, in contrast to earlier work that focus on one of the two problems. We formulate the problem as a maximization of…

Machine Learning · Statistics 2008-11-11 M. Kolar , E. P. Xing

Efficient representations and solutions for large decision problems with continuous and discrete variables are among the most important challenges faced by the designers of automated decision support systems. In this paper, we describe a…

Artificial Intelligence · Computer Science 2011-10-04 C. Guestrin , M. Hauskrecht , B. Kveton

Reinforcement learning (RL) is an important field of research in machine learning that is increasingly being applied to complex optimization problems in physics. In parallel, concepts from physics have contributed to important advances in…

Machine Learning · Computer Science 2023-05-11 Argenis Arriojas , Jacob Adamczyk , Stas Tiomkin , Rahul V. Kulkarni

Conditional Random Fields (CRF) have been widely used in a variety of computer vision tasks. Conventional CRFs typically define edges on neighboring image pixels, resulting in a sparse graph such that efficient inference can be performed.…

Computer Vision and Pattern Recognition · Computer Science 2016-11-17 Peng Wang , Chunhua Shen , Anton van den Hengel

The pursuit of robustness has recently been a popular topic in reinforcement learning (RL) research, yet the existing methods generally suffer from efficiency issues that obstruct their real-world implementation. In this paper, we introduce…

Machine Learning · Computer Science 2024-04-15 Yang Hu , Haitong Ma , Bo Dai , Na Li

Markov Decision Processes (MDP) is an useful framework to cast optimal sequential decision making problems. Given any MDP the aim is to find the optimal action selection mechanism i.e., the optimal policy. Typically, the optimal policy…

Systems and Control · Computer Science 2014-03-18 Chandrashekar Lakshminarayanan , Shalabh Bhatnagar

Aligning Large Language Models (LLMs) with human feedback is crucial for their development. Existing preference optimization methods such as DPO and KTO, while improved based on Reinforcement Learning from Human Feedback (RLHF), are…

Computation and Language · Computer Science 2024-12-23 Shuo Xie , Fangzhi Zhu , Jiahui Wang , Lulu Wen , Wei Dai , Xiaowei Chen , Junxiong Zhu , Kai Zhou , Bo Zheng

Marginal MAP inference involves making MAP predictions in systems defined with latent variables or missing information. It is significantly more difficult than pure marginalization and MAP tasks, for which a large class of efficient and…

Machine Learning · Computer Science 2015-11-10 Wei Ping , Qiang Liu , Alexander Ihler

Many problems in real-world applications involve predicting several random variables which are statistically related. Markov random fields (MRFs) are a great mathematical tool to encode such relationships. The goal of this paper is to…

Machine Learning · Computer Science 2015-04-29 Liang-Chieh Chen , Alexander G. Schwing , Alan L. Yuille , Raquel Urtasun

We propose and study a general framework for regularized Markov decision processes (MDPs) where the goal is to find an optimal policy that maximizes the expected discounted total reward plus a policy regularization term. The extant…

Machine Learning · Statistics 2019-10-22 Xiang Li , Wenhao Yang , Zhihua Zhang
‹ Prev 1 3 4 5 6 7 10 Next ›