Výsledky vyhľadávania - stochastic/gradient-based optimization algorithm*

Fed-DeepONet: Stochastic Gradient-Based Federated Training of Deep Operator Networks Autor Moya, Christian, Lin, Guang

“…The Deep Operator Network (DeepONet) framework is a different class of neural network architecture that one trains to learn nonlinear operators, i.e., mappings…”
Získať plný text

Topology optimization under uncertainty using a stochastic gradient-based approach Autor De, Subhayan, Hampton, Jerrad, Maute, Kurt, Doostan, Alireza

“… Most traditional TOuU methods use gradient-based optimization algorithms and rely on accurate estimates of the statistical moments and their gradients, e.g…”
Získať plný text

A Stochastic-Gradient-based Interior-Point Algorithm for Solving Smooth Bound-Constrained Optimization Problems Autor Curtis, Frank E, Kungurtsev, Vyacheslav, Robinson, Daniel P, Wang, Qi

“…A stochastic-gradient-based interior-point algorithm for minimizing a continuously differentiable objective function…”
Získať plný text

Stochastic gradient-based fast distributed multi-energy management for an industrial park with temporally-coupled constraints Autor Zhu, Dafeng, Yang, Bo, Ma, Chengbin, Wang, Zhaojian, Zhu, Shanying, Ma, Kai, Guan, Xinping

“… Specifically to achieve charging/discharging constraints due to storage and short-term energy balancing, a fast distributed algorithm based on stochastic gradient with two-timescale implementation…”
Získať plný text

Stochastic Gradient-Based Optimal Signal Control With Energy Consumption Bounds Autor Bin Al Islam, S. M. A., Abdul Aziz, H. M., Hajbabaie, Ali

“…This paper develops a stochastic gradient-based optimization model for traffic signal control with bounds on network-level vehicular energy consumption…”
Získať plný text

A stochastic gradient-based two-step sparse identification algorithm for multivariate ARX systems Autor Fu, Yanxin, Zhao, Wenxiao

“… We propose a two-step algorithm, where in the first step the stochastic gradient (SG) algorithm is applied to obtain initial estimates of the unknown parameter matrix…”
Získať plný text

Quasi-Newton optimised Kolmogorov-Arnold Networks for wind farm power prediction Autor Mubarak, Auwalu Saleh, Ameen, Zubaida Said, Mati, Sagiru, Lasisi, Ayodele, Naveed, Quadri Noorulhasan, Abdulkadir, Rabiu Aliyu

“…Having accurate and effective wind energy forecasting that can be easily incorporated into smart networks is important. Appropriate planning and energy…”
Získať plný text

Improving Deep Neural Networks' Training for Image Classification With Nonlinear Conjugate Gradient-Style Adaptive Momentum Autor Wang, Bao, Ye, Qiang

“…Momentum is crucial in stochastic gradient-based optimization algorithms for accelerating or improving training deep neural networks (DNNs…”
Získať plný text

Cross-Entropy Optimization for Hyperparameter Optimization in Stochastic Gradient-based Approaches to Train Deep Neural Networks Autor Li, Kevin, Li, Fulu

“…In this paper, we present a cross-entropy optimization method for hyperparameter optimization in stochastic gradient-based approaches to train deep neural networks…”
Získať plný text

DS-UI: Dual-Supervised Mixture of Gaussian Mixture Models for Uncertainty Inference in Image Recognition Autor Xie, Jiyang, Ma, Zhanyu, Xue, Jing-Hao, Zhang, Guoqiang, Sun, Jian, Zheng, Yinhe, Guo, Jun

“… In addition, we propose a dual-supervised stochastic gradient-based variational Bayes (DS-SGVB) algorithm for the MoGMM-FC layer optimization…”
Získať plný text

Step Size Adaptation for Accelerated Stochastic Momentum Algorithm Using SDE Modeling and Lyapunov Drift Minimization Autor Yuan, Yulan, Tsang, Danny H. K., Lau, Vincent K. N.

“…Training machine learning models often involves solving high-dimensional stochastic optimization problems, where stochastic gradient-based algorithms are hindered by slow convergence…”
Získať plný text

Stochastic Gradient-Based LMS Algorithm for Reliable and Adaptive 5G Systems Autor Kouki, Adel, Ghayoula, Ridha, Latrach, Lassaad, Ayed, Leila Ben, Fattahi, Jaouhar, Mejri, Mohamed

“… The mathematics of the LMS algorithm is demonstrated before applying this to lead to optimization and full-wave electromagnetic validation of the LMS applied to a patch antenna array prototype built…”
Získať plný text

Stochastic Gradient-Based Extremum Seeking Control Under Multi-Input and Output System Delays Autor Souza Silva, Paulo Cesar, Cesar Pellanda, Paulo, Oliveira, Tiago Roux

“…This paper presents a novel multivariable gradient-based stochastic extremum seeking control strategy capable of addressing systems with multiple inputs and…”
Získať plný text

A similarity-based Bayesian mixture-of-experts model Autor Zhang, Tianfang, Bokrantz, Rasmus, Olsson, Jimmy

“… Posterior inference is performed on the parameters of the mixture components as well as the distance metric using a mean-field variational Bayes algorithm accompanied with a stochastic gradient-based…”
Získať plný text

Unbiased MLMC stochastic gradient-based optimization of Bayesian experimental designs Autor Goda, Takashi, Hironaka, Tomohiko, Kitade, Wataru, Foster, Adam

“…In this paper we propose an efficient stochastic optimization algorithm to search for Bayesian experimental designs such that the expected information gain is maximized…”
Získať plný text

Lyapunov-based Optimization of Edge Resources for Energy-Efficient Adaptive Federated Learning Autor Battiloro, Claudio, Lorenzo, Paolo Di, Merluzzi, Mattia, Barbarossa, Sergio

“… We consider a set of devices collecting local data and uploading processed information to an edge server, which runs stochastic gradient-based algorithms to perform continuous learning and adaptation…”
Získať plný text

On the Adaptivity of Stochastic Gradient-Based Optimization Autor Lei, Lihua, Jordan, Michael I

“…Stochastic-gradient-based optimization has been a core enabling methodology in applications to large-scale problems in machine learning and related areas…”
Získať plný text

Real-time image recognition using weighted spatial pyramid networks Autor Zhu, Xiaoning, Meng, Qingyue, Gu, Lize

“… In this paper, the adaptive multipoint moment estimation (AMME) stochastic optimization algorithm is proposed for the first time by using the finite lower-order moments and adding the estimating points…”
Získať plný text

Multi-stage stochastic gradient method with momentum acceleration Autor Luo, Zhijian, Chen, Siyu, Qian, Yuntao, Hou, Yueen

“… Momentum acceleration technique is famously known for building gradient-based algorithms with fast convergence in large-scale optimization…”
Získať plný text

Stochastic Gradient-based Fast Distributed Multi-Energy Management for an Industrial Park with Temporally-Coupled Constraints Autor Zhu, Dafeng, Yang, Bo, Ma, Chengbin, Wang, Zhaojian, Zhu, Shanying, Ma, Kai, Guan, Xinping

“… Specifically to achieve charging/discharging constraints due to storage and short-term energy balancing, a fast distributed algorithm based on stochastic gradient with two-timescale implementation…”
Získať plný text