Zobrazeno 1 - 10
of 15
pro vyhledávání: '"Shangzhi Zeng"'
Autor:
Xuan Luo, Yanyun Ding, Yi Cao, Zhen Liu, Wenchong Zhang, Shangzhi Zeng, Shuk Han Cheng, Honglin Li, Stephen J. Haggarty, Xin Wang, Jin Zhang, Peng Shi
Publikováno v:
iScience, Vol 27, Iss 10, Pp 110875- (2024)
Summary: In this study, we present an approach to neuropharmacological research by integrating few-shot meta-learning algorithms with brain activity mapping (BAMing) to enhance the discovery of central nervous system (CNS) therapeutics. By utilizing
Externí odkaz:
https://doaj.org/article/278cb6cb166b496e8a1de594942c5c13
Publikováno v:
IEEE Transactions on Pattern Analysis and Machine Intelligence. 45:38-57
In recent years, a variety of gradient-based methods have been developed to solve Bi-Level Optimization (BLO) problems in machine learning and computer vision areas. However, the theoretical correctness and practical effectiveness of these existing a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a84492b738b95d8d9dfdb677497a084a
https://doi.org/10.1109/tpami.2022.3140249
https://doi.org/10.1109/tpami.2022.3140249
We typically construct optimal designs based on a single objective function. To better capture the breadth of an experiment's goals, we could instead construct a multiple objective optimal design based on multiple objective functions. While algorithm
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::fe753b8bf38d2e03e85f5ccb36b6b1f9
http://arxiv.org/abs/2303.04746
http://arxiv.org/abs/2303.04746
Publikováno v:
Set-Valued and Variational Analysis. 29:803-837
We study linear convergence of some first-order methods such as the proximal gradient method (PGM), the proximal alternating linearized minimization (PALM) algorithm and the randomized block coordinate proximal gradient method (R-BCPGM) for minimizin
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8a2259dc44145f1b0e10afed56781d18
https://doi.org/10.1007/s11228-021-00591-3
https://doi.org/10.1007/s11228-021-00591-3
Publikováno v:
IEEE transactions on image processing : a publication of the IEEE Signal Processing Society. 31
This paper firstly proposes a convex bilevel optimization paradigm to formulate and optimize popular learning and vision problems in real-world scenarios. Different from conventional approaches, which directly design their iteration schemes based on
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2bac432bfe55da9318d976b5aad6a09d
https://pubmed.ncbi.nlm.nih.gov/35015638
https://pubmed.ncbi.nlm.nih.gov/35015638
In this paper, we present difference of convex algorithms for solving bilevel programs in which the upper level objective functions are difference of convex functions, and the lower level programs are fully convex. This nontrivial class of bilevel pr
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f580c390593380b40868d039ea1e8ef6
http://arxiv.org/abs/2102.09006
http://arxiv.org/abs/2102.09006
The paper proposes and justifies a new algorithm of the proximal Newton type to solve a broad class of nonsmooth composite convex optimization problems without strong convexity assumptions. Based on advanced notions and techniques of variational anal
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8de94ebd409b873f01ee977f16c5c488
http://arxiv.org/abs/2011.08166
http://arxiv.org/abs/2011.08166
Publikováno v:
Scopus-Elsevier
In recent years, a variety of gradient-based first-order methods have been developed to solve bi-level optimization problems for learning applications. However, theoretical guarantees of these existing approaches heavily rely on the simplification th
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ff5ad11b44f92f582105cc4fed3e5b48
Publikováno v:
SIAM Journal on Numerical Analysis. 56:2095-2123
In the literature, error bound conditions have been widely used to study the linear convergence rates of various first-order algorithms. Most of the literature focuses on how to ensure these error ...
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5cda2354cce08ab6cf899ef9be86959b
https://doi.org/10.1137/17m1144623
https://doi.org/10.1137/17m1144623
We develop new perturbation techniques for conducting convergence analysis of various first-order algorithms for a class of nonsmooth optimization problems. We consider the iteration scheme of an algorithm to construct a perturbed stationary point se
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6b57fe397af2ca2ad7af2a3e459a906c