Zobrazeno 1 - 6
of 6
pro vyhledávání: '"Mancino-Ball, Gabriel"'
Autor:
Dürholt, Johannes P., Asche, Thomas S., Kleinekorte, Johanna, Mancino-Ball, Gabriel, Schiller, Benjamin, Sung, Simon, Keupp, Julian, Osburg, Aaron, Boyne, Toby, Misener, Ruth, Eldred, Rosona, Costa, Wagner Steuer, Kappatou, Chrysoula, Lee, Robert M., Linzner, Dominik, Walz, David, Wulkow, Niklas, Shafei, Behrang
Our open-source Python package BoFire combines Bayesian Optimization (BO) with other design of experiments (DoE) strategies focusing on developing and optimizing new chemistry. Previous BO implementations, for example as they exist in the literature
Externí odkaz:
http://arxiv.org/abs/2408.05040
We propose a novel single-loop decentralized algorithm called DGDA-VR for solving the stochastic nonconvex strongly-concave minimax problem over a connected network of $M$ agents. By using stochastic first-order oracles to estimate the local gradient
Externí odkaz:
http://arxiv.org/abs/2307.09421
Autor:
Mancino-Ball, Gabriel, Xu, Yangyang
In this paper, we consider the decentralized, stochastic nonconvex strongly-concave (NCSC) minimax problem with nonsmooth regularization terms on both primal and dual variables, wherein a network of $m$ computing agents collaborate via peer-to-peer c
Externí odkaz:
http://arxiv.org/abs/2307.07113
Consider a network of $N$ decentralized computing agents collaboratively solving a nonconvex stochastic composite problem. In this work, we propose a single-loop algorithm, called DEEPSTORM, that achieves optimal sample complexity for this setting. U
Externí odkaz:
http://arxiv.org/abs/2211.11954
In this work, we introduce ADAPD, $\textbf{A}$ $\textbf{D}$ecentr$\textbf{A}$lized $\textbf{P}$rimal-$\textbf{D}$ual algorithmic framework for solving non-convex and smooth consensus optimization problems over a network of distributed agents. The pro
Externí odkaz:
http://arxiv.org/abs/2107.11321
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.