English
Related papers

Related papers: Theoretical guarantees for stochastic gradient sam…

200 papers

Langevin algorithms are gradient descent methods with additive noise. They have been used for decades in Markov chain Monte Carlo (MCMC) sampling, optimization, and learning. Their convergence properties for unconstrained non-convex…

Machine Learning · Computer Science 2020-12-23 Andrew Lamperski

Stochastic gradient methods are the workhorse (algorithms) of large-scale optimization problems in machine learning, signal processing, and other computational sciences and engineering. This paper studies Markov chain gradient descent, a…

Optimization and Control · Mathematics 2018-09-13 Tao Sun , Yuejiao Sun , Wotao Yin

Sampling a probability distribution with an unknown normalization constant is a fundamental problem in computational science and engineering. This task may be cast as an optimization problem over all probability measures, and an initial…

Machine Learning · Statistics 2024-09-12 Yifan Chen , Daniel Zhengyu Huang , Jiaoyang Huang , Sebastian Reich , Andrew M. Stuart

Optimal Transport has sparked vivid interest in recent years, in particular thanks to the Wasserstein distance, which provides a geometrically sensible and intuitive way of comparing probability measures. For computational reasons, the…

Machine Learning · Computer Science 2024-03-19 Eloi Tanguy

Stochastic gradient descent with momentum is a popular variant of stochastic gradient descent, which has recently been reported to have a close relationship with the underdamped Langevin diffusion. In this paper, we establish a quantitative…

Machine Learning · Statistics 2024-10-24 Arnaud Guillin , Yu Wang , Lihu Xu , Haoran Yang

In this paper, we deal with a class of time-homogeneous continuous-time Markov processes with transition probabilities bearing a nonparametric uncertainty. The uncertainty is modeled by considering perturbations of the transition…

Probability · Mathematics 2022-04-11 Sven Fuhrmann , Michael Kupper , Max Nendel

We provide a nonasymptotic analysis of the convergence of the stochastic gradient Hamiltonian Monte Carlo (SGHMC) to a target measure in Wasserstein-2 distance without assuming log-concavity. Our analysis quantifies key theoretical…

Optimization and Control · Mathematics 2024-01-30 Ömer Deniz Akyildiz , Sotirios Sabanis

Stein's method has been widely used for probability approximations. However, in the multi-dimensional setting, most of the results are for multivariate normal approximation or for test functions with bounded second- or higher-order…

Probability · Mathematics 2018-08-16 Xiao Fang , Qi-Man Shao , Lihu Xu

In the machine learning literature stochastic gradient descent has recently been widely discussed for its purported implicit regularization properties. Much of the theory, that attempts to clarify the role of noise in stochastic gradient…

Machine Learning · Computer Science 2022-10-21 Alberto Lanconelli , Christopher S. A. Lauria

Discretized Langevin diffusions are efficient Monte Carlo methods for sampling from high dimensional target densities that are log-Lipschitz-smooth and (strongly) log-concave. In particular, the Euclidean Langevin Monte Carlo sampling…

Statistics Theory · Mathematics 2020-02-12 Kelvin Shuangjian Zhang , Gabriel Peyré , Jalal Fadili , Marcelo Pereyra

We prove the convergence, in the small mass limit, of statistically invariant states for a class of semi-linear damped wave equations, perturbed by an additive Gaussian noise, both with Lipschitz-continuous and with polynomial…

Probability · Mathematics 2018-06-15 Sandra Cerrai , Nathan Glatt-Holtz

The autocovariance and cross-covariance functions naturally appear in many time series procedures (e.g., autoregression or prediction). Under assumptions, empirical versions of the autocovariance and cross-covariance are asymptotically…

Statistics Theory · Mathematics 2023-05-09 Andreas Anastasiou , Tobias Kley

The efficiency of a Markov sampler based on the underdamped Langevin diffusion is studied for high dimensional targets with convex and smooth potentials. We consider a classical second-order integrator which requires only one gradient…

Probability · Mathematics 2021-06-21 Pierre Monmarché

Most Kalman filters for non-linear systems, such as the unscented Kalman filter, are based on Gaussian approximations. We use Poincar\'e inequalities to bound the Wasserstein distance between the true joint distribution of the prediction…

Statistics Theory · Mathematics 2026-05-28 Toni Karvonen , Simo Särkkä

Learning algorithms for implicit generative models can optimize a variety of criteria that measure how the data distribution differs from the implicit model distribution, including the Wasserstein distance, the Energy distance, and the…

Machine Learning · Statistics 2019-08-23 Leon Bottou , Martin Arjovsky , David Lopez-Paz , Maxime Oquab

Markov chains and diffusion processes are indispensable tools in machine learning and statistics that are used for inference, sampling, and modeling. With the growth of large-scale datasets, the computational cost associated with simulating…

Statistics Theory · Mathematics 2017-08-31 Jonathan H. Huggins , James Zou

Past research has indicated that the covariance of the Stochastic Gradient Descent (SGD) error done via minibatching plays a critical role in determining its regularization and escape from low potential points. Motivated by some new…

Machine Learning · Statistics 2023-03-02 Riddhiman Bhattacharya , Tiefeng Jiang

Hamiltonian Monte Carlo (HMC) sampling methods provide a mechanism for defining distant proposals with high acceptance probabilities in a Metropolis-Hastings framework, enabling more efficient exploration of the state space than standard…

Methodology · Statistics 2014-05-13 Tianqi Chen , Emily B. Fox , Carlos Guestrin

We study nonparametric density estimation problems where error is measured in the Wasserstein distance, a metric on probability distributions popular in many areas of statistics and machine learning. We give the first minimax-optimal rates…

Statistics Theory · Mathematics 2020-04-30 Jonathan Niles-Weed , Quentin Berthet

This paper investigates the robust optimal control of sampled-data stochastic systems with multiplicative noise and distributional ambiguity. We consider a class of discrete-time optimal control problems where the controller \emph{jointly}…

Optimization and Control · Mathematics 2026-02-05 Chung-Han Hsieh