搜索结果: 1-8 共查到“运筹学 Convergence”相关记录8条 . 查询时间(0.161 秒)
Academy of Mathematics and Systems Science, CAS Colloquia & Seminars：Convergence and Implicit Regularization of Deep Learning Optimizers
深度学习 优化 收敛 隐式正则化
font style='font-size:12px;'>
2023/4/13
In this talk, I will present our recent work on the convergence/generalization analysis for the popular optimizers in deep learning. (1) We establish the convergence for Adam under (L0,L1 ) smoothness...
Academy of Mathematics and Systems Science, CAS Colloquia & Seminars：Global and Local Convergence-Rate Analysis of an Inexact Newton Augmented Lagrangian Method for Zero-One Composite Optimization
零一复合优化 不精确 牛顿增强拉格朗日方法 收敛率分析
font style='font-size:12px;'>
2023/4/14
Zero-One Composite Optimization (0/1-COP) is a prototype of nonsmooth, non- convex optimization problems and it has attracted much attention recently. Augmented Lagrangian Method (ALM) has stood out a...
Tree Codes Improve Convergence Rate of Consensus Over Erasure Channels
Tree Codes Convergence Rate of Consensus Erasure Channels Optimization and Control
font style='font-size:12px;'>
2012/4/17
We study the problem of achieving average consensus between a group of agents over a network with erasure links. In the context of consensus problems, the unreliability of communication links between ...
Convergence results in continuous-time quantized consensus
Convergence results continuous-time quantized consensus Optimization and Control
font style='font-size:12px;'>
2011/9/15
Abstract: This note studies a network of agents having continuous-time dynamics with quantized interactions and time-varying topology. We show that under a mild connectivity condition, the agents reac...
Convergence of the Gauss-Newton method for convex composite optimization under a majorant condition
the Gauss-Newton method convex composite optimization Optimization and Control
font style='font-size:12px;'>
2011/9/15
Abstract: Under the hypothesis that an initial point is a quasi-regular point, we use a majorant condition to present a new semi-local convergence analysis of an extension of the Gauss-Newton method f...
On the Convergence of a Multi-Agent Projected Stochastic Gradient Algorithm
Multi-Agent Projected Stochastic Gradient Algorithm Optimization and Control
font style='font-size:12px;'>
2011/9/5
Abstract: We introduce a new framework for the convergence analysis of a class of distributed constrained non-convex optimization algorithms in multi-agent systems. The aim is to search for local mini...
Variational Inequalities and Improved Convergence Rates for Tikhonov Regularisation on Banach Spaces
Variational Inequalities Improved Convergence Rates Tikhonov Regularisation Optimization and Control
font style='font-size:12px;'>
2011/9/5
Abstract: In this paper we derive higher order convergence rates in terms of the Bregman distance for Tikhonov like convex regularisation for linear operator equations on Banach spaces. The approach i...
Optimization and Convergence of Observation Channels in Stochastic Control
Stochastic control information theory observation channels optimization
font style='font-size:12px;'>
2010/12/9
This paper studies the optimization of observation channels (stochastic kernels)in partially observed stochastic control problems. In particular, existence, continuity, and convexity
properties are i...