English
Related papers

Related papers: Multilevel Stein variational gradient descent with…

200 papers

Gradient-based dimension reduction decreases the cost of Bayesian inference and probabilistic modeling by identifying maximally informative (and informed) low-dimensional projections of the data and parameters, allowing high-dimensional…

Computation · Statistics 2025-06-02 Ricardo Baptista , Michael Brennan , Youssef Marzouk

We propose a mini-batching scheme for improving the theoretical complexity and practical performance of semi-stochastic gradient descent applied to the problem of minimizing a strongly convex composite function represented as the sum of an…

Machine Learning · Computer Science 2014-10-20 Jakub Konečný , Jie Liu , Peter Richtárik , Martin Takáč

Policy gradient methods have been successfully applied to many complex reinforcement learning problems. However, policy gradient methods suffer from high variance, slow convergence, and inefficient exploration. In this work, we introduce a…

Machine Learning · Computer Science 2017-04-11 Yang Liu , Prajit Ramachandran , Qiang Liu , Jian Peng

This paper presents an improved implicit sampling method for hierarchical Bayesian inverse problems. A widely used approach for sampling posterior distribution is based on Markov chain Monte Carlo (MCMC). However, the samples generated by…

Numerical Analysis · Mathematics 2018-11-27 Xiaoyan Song , Lijian Jiang , Guanghui Zheng

There are several challenges associated with inverse problems in which we seek to reconstruct a piecewise constant field, and which we model using multiple level sets. Adopting a Bayesian viewpoint, we impose prior distributions on both the…

Numerical Analysis · Mathematics 2021-12-01 William Reese , Arvind K. Saibaba , Jonghyun Lee

Insights into complex, high-dimensional data can be obtained by discovering features of the data that match or do not match a model of interest. To formalize this task, we introduce the "data selection" problem: finding a lower-dimensional…

Methodology · Statistics 2021-09-10 Eli N. Weinstein , Jeffrey W. Miller

We consider a latent space model for dynamic networks, where our objective is to estimate the pairwise inner products plus the intercept of the latent positions. To balance posterior inference and computational scalability, we consider a…

Machine Learning · Statistics 2024-10-16 Peng Zhao , Anirban Bhattacharya , Debdeep Pati , Bani K. Mallick

We investigate the convergence rates of variational posterior distributions for statistical inverse problems involving nonlinear partial differential equations (PDEs). Departing from exact Bayesian inference, variational inference…

Statistics Theory · Mathematics 2026-02-10 Shaokang Zu , Junxiong Jia , Deyu Meng

We introduce new multilevel methods for solving large-scale unconstrained optimization problems. Specifically, the philosophy of multilevel methods is applied to Newton-type methods that regularize the Newton sub-problem using second order…

Optimization and Control · Mathematics 2024-07-16 Nick Tsipinakis , Panos Parpas

We propose a novel method for measuring the discrepancy between a set of samples and a desired posterior distribution for Bayesian inference. Classical methods for assessing sample quality like the effective sample size are not appropriate…

Machine Learning · Statistics 2026-05-01 Narayan Srinivasan , Matthew Sutton , Christopher Drovandi , Leah F South

We propose a Stein variational gradient descent method to concurrently sparsify, train, and provide uncertainty quantification of a complexly parameterized model such as a neural network. It employs a graph reconciliation and condensation…

Machine Learning · Computer Science 2024-12-24 Govinda Anantha Padmanabha , Cosmin Safta , Nikolaos Bouklas , Reese E. Jones

Solving a bilevel optimization problem is at the core of several machine learning problems such as hyperparameter tuning, data denoising, meta- and few-shot learning, and training-data poisoning. Different from simultaneous or…

Machine Learning · Computer Science 2021-10-07 Akshay Mehra , Jihun Hamm

The trace of a matrix function f(A), most notably of the matrix inverse, can be estimated stochastically using samples< x,f(A)x> if the components of the random vectors x obey an appropriate probability distribution. However such a…

Numerical Analysis · Mathematics 2021-08-26 Andreas Frommer , Mostafa Nasr Khalil , Gustavo Ramirez-Hidalgo

Bayesian inference is conceptually elegant, but calculating posterior expectations can entail a heavy computational cost. Monte Carlo methods are reliable and supported by strong asymptotic guarantees, but do not leverage smoothness of the…

This paper considers stochastic subgradient mirror-descent method for solving constrained convex minimization problems. In particular, a stochastic subgradient mirror-descent method with weighted iterate-averaging is investigated and its…

Optimization and Control · Mathematics 2013-07-09 Angelia Nedich , Soomin Lee

State estimation in robotic systems presents significant challenges, particularly due to the prevalence of multimodal posterior distributions in real-world scenarios. One effective strategy for handling such complexity is to compute maximum…

Robotics · Computer Science 2026-01-27 Min-Won Seo , Solmaz S. Kia

Bilevel learning has gained prominence in machine learning, inverse problems, and imaging applications, including hyperparameter optimization, learning data-adaptive regularizers, and optimizing forward operators. The large-scale nature of…

Optimization and Control · Mathematics 2025-05-20 Mohammad Sadegh Salehi , Subhadip Mukherjee , Lindon Roberts , Matthias J. Ehrhardt

A wide range of applications arising in machine learning and signal processing can be cast as convex optimization problems. These problems are often ill-posed, i.e., the optimal solution lacks a desired property such as uniqueness or…

Optimization and Control · Mathematics 2019-07-18 Mostafa Amini , Farzad Yousefian

Stein variational gradient decent (SVGD) has been shown to be a powerful approximate inference algorithm for complex distributions. However, the standard SVGD requires calculating the gradient of the target density and cannot be applied…

Machine Learning · Statistics 2018-06-08 Jun Han , Qiang Liu

Gradient descent is the primary workhorse for optimizing large-scale problems in machine learning. However, its performance is highly sensitive to the choice of the learning rate. A key limitation of gradient descent is its lack of natural…

Optimization and Control · Mathematics 2025-07-15 Oscar Smee , Fred Roosta , Stephen J. Wright
‹ Prev 1 8 9 10 Next ›