English
Related papers

Related papers: Sinkhorn Barycenters with Free Support via Frank-W…

200 papers

It is known that the gradient descent algorithm converges linearly when applied to a strongly convex function with Lipschitz gradient. In this case the algorithm's rate of convergence is determined by the condition number of the function.…

Optimization and Control · Mathematics 2016-12-28 Javier Pena , Daniel Rodriguez

Ensembles of random stochastic and bistochastic matrices are investigated. While all columns of a random stochastic matrix can be chosen independently, the rows and columns of a bistochastic matrix have to be correlated. We evaluate the…

Exactly Solvable and Integrable Systems · Physics 2009-09-29 V. Cappellini , H. -J. Sommers , W. Bruzda , K. Zyczkowski

We propose a novel and efficient training method for RNNs by iteratively seeking a local minima on the loss surface within a small region, and leverage this directional vector for the update, in an outer-loop. We propose to utilize the…

Machine Learning · Computer Science 2020-10-16 Yun Yue , Ming Li , Venkatesh Saligrama , Ziming Zhang

We study Frank-Wolfe methods for nonconvex stochastic and finite-sum optimization problems. Frank-Wolfe methods (in the convex case) have gained tremendous recent interest in machine learning and optimization communities due to their…

Optimization and Control · Mathematics 2016-08-01 Sashank J. Reddi , Suvrit Sra , Barnabas Poczos , Alex Smola

In this paper, we consider Frank-Wolfe-based algorithms for composite convex optimization problems with objective involving a logarithmically-homogeneous, self-concordant functions. Recent Frank-Wolfe-based methods for this class of…

Optimization and Control · Mathematics 2023-10-24 Nimita Shinde , Vishnu Narayanan , James Saunderson

Many problems in machine learning can be formulated as optimizing a convex functional over a vector space of measures. This paper studies the convergence of the mirror descent algorithm in this infinite-dimensional setting. Defining Bregman…

Optimization and Control · Mathematics 2022-10-12 Pierre-Cyril Aubin-Frankowski , Anna Korba , Flavien Léger

Erwin Schroedinger posed, and to a large extent solved in 1931/32 the problem of finding the most likely random evolution between two continuous probability distributions. This article considers this problem in the case when only samples of…

Optimization and Control · Mathematics 2018-06-07 Michele Pavon , Esteban G Tabak , Giulio Trigila

One of the beauties of the projected gradient descent method lies in its rather simple mechanism and yet stable behavior with inexact, stochastic gradients, which has led to its wide-spread use in many machine learning applications.…

Optimization and Control · Mathematics 2019-10-11 Mingrui Zhang , Zebang Shen , Aryan Mokhtari , Hamed Hassani , Amin Karbasi

We extend the Frank-Wolfe (FW) optimization algorithm to solve constrained smooth convex-concave saddle point (SP) problems. Remarkably, the method only requires access to linear minimization oracles. Leveraging recent advances in FW…

Optimization and Control · Mathematics 2017-03-07 Gauthier Gidel , Tony Jebara , Simon Lacoste-Julien

We study the problem of model aggregation within the Wasserstein space for probability measures on the real line. Given a fixed finite collection of candidate probability models, we consider the associated class of Wasserstein barycenters…

This work considers the problem of sampling from a probability distribution known up to a normalization constant while satisfying a set of statistical constraints specified by the expected values of general nonlinear functions. This problem…

Machine Learning · Statistics 2025-01-08 Luiz F. O. Chamon , Mohammad Reza Karimi , Anna Korba

We propose a novel approach to the problem of multilevel clustering, which aims to simultaneously partition data in each group and discover grouping patterns among groups in a potentially large hierarchically structured corpus of data. Our…

Machine Learning · Statistics 2021-05-26 Viet Huynh , Nhat Ho , Nhan Dam , XuanLong Nguyen , Mikhail Yurochkin , Hung Bui , and Dinh Phung

Randomized zeroth-order methods are classically analyzed in expectation, but a black-box Markov conversion can give misleading high-probability guarantees, in particular by forcing the finite-difference smoothing radius to shrink with the…

Optimization and Control · Mathematics 2026-05-27 Haishan Ye

We present and analyze a new generalized Frank-Wolfe method for the composite optimization problem $(P):{\min}_{x\in\mathbb{R}^n}\; f(\mathsf{A} x) + h(x)$, where $f$ is a $\theta$-logarithmically-homogeneous self-concordant barrier,…

Optimization and Control · Mathematics 2021-12-07 Renbo Zhao , Robert M. Freund

In this paper, we propose new sampling approaches for the Shrinkage Inverse-Wishart (SIW) distribution, a generalized family of the Inverse-Wishart distribution originally proposed by Berger et al. (2020, Annals of Statistics). It offers a…

Methodology · Statistics 2025-11-14 Yiye Jiang

Variational inference is a popular technique to approximate a possibly intractable Bayesian posterior with a more tractable one. Recently, boosting variational inference has been proposed as a new paradigm to approximate the posterior by a…

Machine Learning · Computer Science 2018-03-08 Francesco Locatello , Rajiv Khanna , Joydeep Ghosh , Gunnar Rätsch

We provide statistical guarantees for Bayesian variational boosting by proposing a novel small bandwidth Gaussian mixture variational family. We employ a functional version of Frank-Wolfe optimization as our variational algorithm and study…

Machine Learning · Statistics 2020-10-23 Biraj Subhra Guha , Anirban Bhattacharya , Debdeep Pati

Divide-and-conquer based methods for Bayesian inference provide a general approach for tractable posterior inference when the sample size is large. These methods divide the data into smaller subsets, sample from the posterior distribution…

Methodology · Statistics 2018-06-21 Sanvesh Srivastava , Cheng Li , David B. Dunson

This paper addresses the study of derivative-free smooth optimization problems, where the gradient information on the objective function is unavailable. Two novel general derivative-free methods are proposed and developed for minimizing…

Optimization and Control · Mathematics 2023-11-29 Pham Duy Khanh , Boris S. Mordukhovich , Dat Ba Tran

Online optimization has been a successful framework for solving large-scale problems under computational constraints and partial information. Current methods for online convex optimization require either a projection or exact gradient…

Machine Learning · Statistics 2018-06-15 Lin Chen , Christopher Harshaw , Hamed Hassani , Amin Karbasi