English
Related papers

Related papers: Weak Convergence and Optimal Tuning of the Reversi…

200 papers

Coordinate descent methods employ random partial updates of decision variables in order to solve huge-scale convex optimization problems. In this work, we introduce new adaptive rules for the random selection of their updates. By adaptive,…

Machine Learning · Computer Science 2017-03-08 Dmytro Perekrestenko , Volkan Cevher , Martin Jaggi

This study proposes a trainable sampling-based solver for combinatorial optimization problems (COPs) using a deep-learning technique called deep unfolding. The proposed solver is based on the Ohzeki method that combines Markov-chain…

Disordered Systems and Neural Networks · Physics 2024-05-03 Ryo Hagiwara , Satoshi Takabe

We consider a recursive algorithm to construct an aggregated estimator from a finite number of base decision rules in the classification problem. The estimator approximately minimizes a convex risk functional under the l1-constraint. It is…

Statistics Theory · Mathematics 2007-06-13 Anatoli Juditsky , Alexander Nazin , Alexandre Tsybakov , Nicolas Vayatis

In this paper, we propose a new threshold-kernel jump-detection method for jump-diffusion processes, which iteratively applies thresholding and kernel methods in an approximately optimal way to achieve improved finite-sample performance. We…

Statistics Theory · Mathematics 2020-04-07 José E. Figueroa-López , Cheng Li , Jeffrey Nisen

We propose a novel sparse sliced inverse regression method based on random projections in a large $p$ small $n$ setting. Embedded in a generalized eigenvalue framework, the proposed approach finally reduces to parallel execution of…

Methodology · Statistics 2023-08-04 Jia Zhang , Runxiong Wu , Xin Chen

This paper presents a novel stochastic gradient descent algorithm for constrained optimization. The proposed algorithm randomly samples constraints and components of the finite sum objective function and relies on a relaxed logarithmic…

Optimization and Control · Mathematics 2025-05-13 Naum Dimitrieski , Jing Cao , Christian Ebenbauer

The choice of transition kernel critically influences the performance of the Markov chain Monte Carlo method. Despite the importance of kernel choice, guiding principles for optimal kernels have not been established. Here, we propose a…

Statistical Mechanics · Physics 2023-11-28 Hidemaro Suwa

An important step in the design of autonomous systems is to evaluate the probability that a failure will occur. In safety-critical domains, the failure probability is extremely small so that the evaluation of a policy through Monte Carlo…

Machine Learning · Computer Science 2022-11-23 Anthony Corso , Kyu-Young Kim , Shubh Gupta , Grace Gao , Mykel J. Kochenderfer

Equilibrium sampling of the configuration space in disordered systems requires algorithms that bypass the glassy slowing down of the physical dynamics. Irreversible Monte Carlo algorithms breaking detailed balance successfully accelerate…

Disordered Systems and Neural Networks · Physics 2024-07-15 Federico Ghimenti , Ludovic Berthier , Frédéric van Wijland

The radiative transfer equation models various physical processes ranging from plasma simulations to radiation therapy. In practice, these phenomena are often subject to uncertainties. Modeling and propagating these uncertainties requires…

Numerical Analysis · Mathematics 2025-06-02 Chinmay Patwardhan , Pia Stammer , Emil Løvbak , Jonas Kusch , Sebastian Krumscheid

Markov decision processes are useful models of concurrency optimisation problems, but are often intractable for exhaustive verification methods. Recent work has introduced lightweight approximative techniques that sample directly from…

Logic in Computer Science · Computer Science 2015-03-24 Axel Legay , Sean Sedwards , Louis-Marie Traonouez

We give computable bounds on the rate of convergence of the transition probabilities to the stationary distribution for a certain class of geometrically ergodic Markov chains. Our results are different from earlier estimates of Meyn and…

Probability · Mathematics 2007-05-23 Peter H. Baxendale

In this paper, we consider continuous-time stochastic optimal control problems where the cost is evaluated through a coherent risk measure. We provide an explicit gradient descent-ascent algorithm which applies to problems subject to…

Optimization and Control · Mathematics 2023-06-23 Gabriel Velho , Jean Auriol , Riccardo Bonalli

We formulate gradient-based Markov chain Monte Carlo (MCMC) sampling as optimization on the space of probability measures, with Kullback-Leibler (KL) divergence as the objective functional. We show that an underdamped form of the Langevin…

Machine Learning · Statistics 2019-10-23 Yi-An Ma , Niladri Chatterji , Xiang Cheng , Nicolas Flammarion , Peter Bartlett , Michael I. Jordan

We investigate the properties of the Hybrid Monte-Carlo algorithm (HMC) in high dimensions. HMC develops a Markov chain reversible w.r.t. a given target distribution $\Pi$ by using separable Hamiltonian dynamics with potential $-\log\Pi$.…

A resampling scheme provides a way to switch low-weight particles for sequential Monte Carlo with higher-weight particles representing the objective distribution. The less the variance of the weight distribution is, the more concentrated…

Computation · Statistics 2023-09-19 Xiongming Dai , Gerald Baumgartner

Dropping tolerance criteria play a central role in Sparse Approximate Inverse preconditioning. Such criteria have received, however, little attention and have been treated heuristically in the following manner: If the size of an entry is…

Numerical Analysis · Mathematics 2015-03-17 Zhongxiao Jia , Qian Zhang

We study Markov Chain Monte Carlo (MCMC) methods operating in primary sample space and their interactions with multiple sampling techniques. We observe that incorporating the sampling technique into the state of the Markov Chain, as done in…

Graphics · Computer Science 2017-04-25 Benedikt Bitterli , Wenzel Jakob , Jan Novák , Wojciech Jarosz

This note extends some results of Nishiyama [Ann. Probab. 28 (2000) 685--712]. A maximal inequality for stochastic integrals with respect to integer-valued random measures which may have infinitely many jumps on compact time intervals is…

Probability · Mathematics 2011-11-10 Yoichi Nishiyama

Adaptive sampling algorithms are modern and efficient methods that dynamically adjust the sample size throughout the optimization process. However, they may encounter difficulties in risk-averse settings, particularly due to the challenge…

Optimization and Control · Mathematics 2025-02-17 Sandra Pieraccini , Tommaso Vanzan