Results 71 to 80 of about 1,273 (111)

Stochastic Gradient Descent with Strategic Querying

2025 IEEE 64th Conference on Decision and Control (CDC)
18 pages, 2 figures. Accepted to IEEE Conference on Decision and Control (CDC) 2025.
Nanfei Jiang, Hoi-To Wai, Mahnoosh Alizadeh   +2 more
openaire   +3 more sources

Scaling of hardware-compatible perturbative training algorithms

APL Machine Learning
In this work, we explore the capabilities of multiplexed gradient descent (MGD), a scalable and efficient perturbative zeroth-order training method for estimating the gradient of a loss function in hardware and training it via stochastic gradient descent.
B. G. Oripov, A. Dienstfrey, A. N. McCaughan, S. M. Buckley   +3 more
doaj   +1 more source

Stochastic Gradient Descent with Adaptive Data

Operations Research
Stochastic Gradient Descent with Adaptive Data Stochastic gradient descent (SGD) is a central tool in modern optimization, but its classical theory relies on the assumption that data are independent of the decisions being optimized. In many operations research settings, this assumption fails: policies influence system dynamics, and ...
Ethan Che, Jing Dong, Xin T. Tong
openaire   +3 more sources

A novel deep learning technique for medical image analysis using improved optimizer

Health Informatics Journal
Application of Convolutional neural network in spectrum of Medical image analysis are providing benchmark outputs which converges the interest of many researchers to explore it in depth.
Vertika Agarwal, MC Lohani, Ankur Singh Bist   +2 more
doaj   +1 more source

Random coordinate descent: A simple alternative for optimizing parameterized quantum circuits

Physical Review Research
Variational quantum algorithms rely on the optimization of parameterized quantum circuits in noisy settings. The commonly used back-propagation procedure in classical machine learning is not directly applicable in this setting due to the collapse of ...
Zhiyan Ding, Taehee Ko, Jiahao Yao, Lin Lin, Xiantao Li   +4 more
doaj   +1 more source

Performance Analysis of an Optical System for FSO Communications Utilizing Combined Stochastic Gradient Descent Optimization Algorithm

Applied System Innovation
Wavefront aberrations caused by thermal flows or arising from the quality of optical components can significantly impair wireless communication links. Such aberrations may result in an increased error rate in the received signal, leading to data loss in ...
Ilya Galaktionov, Vladimir Toporovsky
doaj   +1 more source

Stochastic Modified Flows for Riemannian Stochastic Gradient Descent

SIAM Journal on Control and Optimization
We give quantitative estimates for the rate of convergence of Riemannian stochastic gradient descent (RSGD) to Riemannian gradient flow and to a diffusion process, the so-called Riemannian stochastic modified flow (RSMF). Using tools from stochastic differential geometry we show that, in the small learning rate regime, RSGD can be approximated by the ...
Benjamin Gess, Sebastian Kassing, Nimit Rana   +2 more
openaire   +5 more sources

Non-Iterative Phase-Only Hologram Generation via Stochastic Gradient Descent Optimization

Photonics
In this work, we explored, for the first time, to the best of our knowledge, the potential of stochastic gradient descent (SGD) to optimize random phase functions for application in non-iterative phase-only hologram generation.
Alejandro Velez-Zea, John Fredy Barrera-Ramírez   +1 more
doaj   +1 more source

A Novel Sophia-SPGD (Stochastic Parallel Gradient Descent) Optimization Method for Wavefront Correction in WFS-Less AO (Wavefront Sensorless Adaptive Optics) Systems

Photonics
In wavefront sensorless adaptive optics (WFS-less AO) systems, stochastic parallel gradient descent (SPGD) is the primary optimization method for correcting wavefront distortions. However, as the intensity of atmospheric turbulence interference increases,
Peng Chen, Wenjie Yang, Yongqi Ge, Zhiguang Zhang, Xianshuo Li, Zhengqing Qi, Huizhen Yang   +6 more
doaj   +1 more source

Dual Stochastic Natural Gradient Descent

CoRR, 2020
[EN] Although theoretically appealing, Stochastic Natural Gradient Descent (SNGD) is computationally expensive, it has been shown to be highly sensitive to the learning rate, and it is not guaranteed to be convergent. Convergent Stochastic Natural Gradient Descent (CSNGD) aims at solving the last two problems.
Sánchez-López, Borja, Cerquides, Jesús   +1 more
openaire   +2 more sources