Zobrazeno 1 - 10
of 18
pro vyhledávání: '"Hu, Yuanhan"'
Publikováno v:
Transactions of Machine Learning Research, 2023
Cyclic and randomized stepsizes are widely used in the deep learning practice and can often outperform standard stepsize choices such as constant stepsize in SGD. Despite their empirical success, not much is currently known about when and why they ca
Externí odkaz:
http://arxiv.org/abs/2302.05516
We consider the constrained sampling problem where the goal is to sample from a target distribution $\pi(x)\propto e^{-f(x)}$ when $x$ is constrained to lie on a convex body $\mathcal{C}$. Motivated by penalty methods from continuous optimization, we
Externí odkaz:
http://arxiv.org/abs/2212.00570
Autor:
Chen, Fujia, Xue, Haoran, Pan, Yuang, Wang, Maoren, Hu, Yuanhan, Zhang, Li, Chen, Qiaolu, Han, Song, Liu, Gui-geng, Gao, Zhen, Zhou, Peiheng, Yin, Wenyan, Chen, Hongsheng, Zhang, Baile, Yang, Yihao
Slow-light devices are able to significantly enhance light-matter interaction due to the reduced group velocity of light, but a very low group velocity is usually achieved in a narrow bandwidth, accompanied by extreme sensitivity to imperfections tha
Externí odkaz:
http://arxiv.org/abs/2208.07228
Recent theoretical studies have shown that heavy-tails can emerge in stochastic optimization due to `multiplicative noise', even under surprisingly simple settings, such as linear regression with Gaussian data. While these studies have uncovered seve
Externí odkaz:
http://arxiv.org/abs/2205.06689
Stochastic gradient Langevin dynamics (SGLD) and stochastic gradient Hamiltonian Monte Carlo (SGHMC) are two popular Markov Chain Monte Carlo (MCMC) algorithms for Bayesian inference that can scale to large datasets, allowing to sample from the poste
Externí odkaz:
http://arxiv.org/abs/2007.00590
Autor:
Gurbuzbalaban, Mert, Hu, Yuanhan
A traditional approach to initialization in deep neural networks (DNNs) is to sample the network weights randomly for preserving the variance of pre-activations. On the other hand, several studies show that during the training process, the distributi
Externí odkaz:
http://arxiv.org/abs/2005.11878
Stochastic Gradient Langevin Dynamics (SGLD) is a powerful algorithm for optimizing a non-convex objective, where a controlled and properly scaled Gaussian noise is added to the stochastic gradients to steer the iterates towards a global minimum. SGL
Externí odkaz:
http://arxiv.org/abs/2004.02823
Autor:
Gürbüzbalaban, Mert1 (AUTHOR) mg1366@rutgers.edu, Hu, Yuanhan1 (AUTHOR), Şimşekli, Umut2 (AUTHOR), Yuan, Kun3 (AUTHOR), Zhu, Lingjiong4 (AUTHOR)
Publikováno v:
IISE Transactions. Oct2024, p1-23. 23p. 5 Illustrations.
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Cyclic and randomized stepsizes are widely used in the deep learning practice and can often outperform standard stepsize choices such as constant stepsize in SGD. Despite their empirical success, not much is currently known about when and why they ca
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8b62241fd8f20779848ab700f7199303
http://arxiv.org/abs/2302.05516
http://arxiv.org/abs/2302.05516