Accelerated convergence to equilibrium and reduced asymptotic variance for Langevin dynamics using Stratonovich perturbations

Publications associées (27)

À propos
Confidentialité
Mentions légales

Graph Chatbot

A probabilistic finite element method based on random meshes: A posteriori error estimators and Bayesian inverse problems

Assyr Abdulle, Giacomo Garegnani

We present a novel probabilistic finite element method (FEM) for the solution and uncertainty quantification of elliptic partial differential equations based on random meshes, which we call random mesh FEM (RM-FEM). Our methodology allows to introduce a pr ...

ELSEVIER SCIENCE SA2021

Generalization Error Bounds Via Rényi-, f-Divergences and Maximal Leakage

Michael Christoph Gastpar, Amedeo Roberto Esposito, Ibrahim Issa

In this work, the probability of an event under some joint distribution is bounded by measuring it with the product of the marginals instead (which is typically easier to analyze) together with a measure of the dependence between the two random variables. ...

2021

Is there an analog of Nesterov acceleration for gradient-based MCMC?

Nicolas Henri Bernard Flammarion, Xiang Cheng

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 under-damped form of the Langevin algorithm perfor ...

2021

Predicting involuntary hospitalization in psychiatry: A machine learning investigation

Mehdi Gholam

Background Coercion in psychiatry is a controversial issue. Identifying its predictors and their interaction using traditional statistical methods is difficult, given the large number of variables involved. The purpose of this study was to use machine-lear ...

CAMBRIDGE UNIV PRESS2021

A Pareto Dominance Principle for Data-Driven Optimization

Daniel Kuhn, Tobias Sutter

We propose a statistically optimal approach to construct data-driven decisions for stochastic optimization problems. Fundamentally, a data-driven decision is simply a function that maps the available training data to a feasible action. It can always be exp ...

2024

COVID-19: data-driven dynamic asset allocation in times of pandemic

Anna Timonina-Farkas

The COVID-19 pandemic has demonstrated the importance and value of multi-period asset allocation strategies responding to rapid changes in market behavior. In this article, we formulate and solve a multi-stage stochastic optimization problem, choosing the ...

AMER INST MATHEMATICAL SCIENCES-AIMS2021

Unbiased Monte Carlo cluster updates with autoregressive neural networks

Giuseppe Carleo, Riccardo Rossi, Dian Wu

Efficient sampling of complex high-dimensional probability distributions is a central task in computational science. Machine learning methods like autoregressive neural networks, used with Markov chain Monte Carlo sampling, provide good approximations to s ...