Proceedings of the Twenty Third International Conference on Artificial Intelligence and Statistics, PMLR 108

Eduard Gorbunov; Hanzely Filip; Richtarik Peter

Публикации

Книга

Proceedings of the Twenty Third International Conference on Artificial Intelligence and Statistics, PMLR 108

Iss. 108. PMLR, 2020.

Eduard Gorbunov, Hanzely F., Richtarik P.

Deterministic Decoding for Discrete Data in Variational Autoencoders

Polykovskiy D., Vetrov D. In bk.: Proceedings of the Twenty Third International Conference on Artificial Intelligence and Statistics, PMLR 108. Iss. 108. PMLR, 2020. P. 3046-3056.

Добавлено: 5 февраля 2021

Язык: английский

Полный текст (PDF, 5.47 Мб)

Текст на другом сайте

Ключевые слова: convex optimization stochastic optimization

Proceedings of the Twenty Third International Conference on Artificial Intelligence and Statistics, PMLR 108

Mapping of enclosed buildings using mobile radio tomography

Ingacheva A., Kokhan V., Osipov D. In bk.: Proceedings of the 32nd European Conference on Modelling and Simulation (ECMS 2018),Wilhelmshaven, Germany 22 – 25 May 2018. NY: Curran Associates, Inc., 2018. P. 183-189.

Добавлено: 6 апреля 2019

On greedy approximation algorithms for a class of two-stage stochastic assignment problems

Karademir S., Kong N., Prokopyev O. Optimization Methods and Software. 2014. Vol. 29. No. 1. P. 42-67.

Добавлено: 19 октября 2016

A Superlinearly-Convergent Proximal Newton-Type Method for the Optimization of Finite Sums

Rodomanov A., Kropotov D. Journal of Machine Learning Research. 2016. Vol. 48. P. 2597-2605.

We consider the problem of optimizing the strongly convex sum of a finite number of convex functions. Standard algorithms for solving this problem in the class of incremental/stochastic methods have at most a linear convergence rate. We propose a new incremental method whose convergence rate is superlinear – the Newton-type incremental method (NIM). The idea of the method is to introduce a model of the objective with the same sum-of-functions structure and further update a single component of the model per iteration. We prove that NIM has a superlinear local convergence rate and linear global convergence rate. Experiments show that the method is very effective for problems with a large number of functions and a small number of variables.

Добавлено: 11 марта 2017

A Superlinearly-Convergent Proximal Newton-type Method for the Optimization of Finite Sums

Rodomanov A., Kropotov D. In bk.: Proceedings of Machine Learning Research. Proceedings of the International Conference on Machine Learning (ICML 2016). Vol. 48. NY: 2016. P. 2597-2605.

Добавлено: 10 декабря 2018

Robust Control Design for Suppressing Random Exogenous Disturbances in Parametrically Uncertain Linear Systems

Belov A. A., Andrianova O. Automation and Remote Control. 2020. Vol. 81. No. 4. P. 649-661.

Добавлено: 21 октября 2020

Optimal Tensor Methods in Smooth Convex and Uniformly Convex Optimization

Gasnikov A. In bk.: Proceedings of Machine Learning Research Vol. 99: Conference on Learning Theory, 25-28 June 2019, Phoenix, AZ, USA. PMLR, 2019.. PMLR, 2019.

Добавлено: 13 июня 2019