Results 61 to 70 of about 1,338,397 (280)
A Fixed-Point of View on Gradient Methods for Big Data
Frontiers in Applied Mathematics and Statistics, 2017 Interpreting gradient methods as fixed-point iterations, we provide a detailed analysis of those methods for minimizing convex objective functions. Due to their conceptual and algorithmic simplicity, gradient methods are widely used in machine learning ...
Alexander Jung
doaj +1 more source
Adaptive Optical Closed-Loop Control Based on the Single-Dimensional Perturbation Descent Algorithm
Sensors, 2023 Modal-free optimization algorithms do not require specific mathematical models, and they, along with their other benefits, have great application potential in adaptive optics.
Bo Chen +4 more
doaj +1 more source
Stochastic Gradient Descent for Risk Optimization
, 2020 This paper presents an approach for the use of stochastic gradient descent methods for the solution of risk optimization problems. The first challenge is to avoid the high-cost evaluation of the failure probability and its gradient at each iteration of ...
Lopez, Rafael Holdorf +7 more
core +1 more source
An efficient algorithm for data parallelism based on stochastic optimization
Alexandria Engineering Journal, 2022 Deep neural network models can achieve greater performance in numerous machine learning tasks by raising the depth of the model and the amount of training data samples.
Khalid Abdulaziz Alnowibet +3 more
doaj +1 more source
Distributed stochastic gradient descent for link prediction in signed social networks
EURASIP Journal on Advances in Signal Processing, 2019 This paper considers the link prediction problem defined over a signed social network, where the relationship between any two network users can be either positive (friends) or negative (foes).
Han Zhang, Gang Wu, Qing Ling
doaj +1 more source
SSRGD: Simple stochastic recursive gradient descent for escaping saddle points [PDF]
, 2019 We analyze stochastic gradient algorithms for optimizing nonconvex problems. In particular, our goal is to find local minima (second-order stationary points) instead of just finding first-order stationary points which may be some bad unstable saddle ...
Li, Zhize
core
Ligand‐dependent transcriptional heterogeneity in cell cycle gene expression delays G1/S entry
FEBS Letters, EarlyView.EGF and HRG induce distinct G1/S progression programs in ErbB2‐amplified BT474 breast cancer cells. Despite activating the potent ErbB2–ErbB3 heterodimer, HRG does not accelerate cell‐cycle entry. Instead, EGF promotes earlier restriction‐point passage via ERK–FOS signaling, whereas HRG activates the AKT–MYC axis, driving transcriptional heterogeneity ...
Ririn Rahmala Febri +5 more
wiley +1 more source
Adaptive Step Sizes for Stochastic Gradient Descent
, 2023 In this thesis, we first lay some theoretical groundwork before motivating and discussing the stochastic gradient descent method along with its variations. We then analyze some popular step size strategies with a focus on the stochastic Polyak step size,
Karakoc, Dylan
core +1 more source
Stochastic gradient descent algorithm preserving differential privacy in MapReduce framework
Tongxin xuebao, 2018 Aiming at the contradiction between the efficiency and privacy of stochastic gradient descent algorithm in distributed computing environment,a stochastic gradient descent algorithm preserving differential privacy based on MapReduce was proposed.Based on ...
Yihan YU, Yu FU, Xiaoping WU
doaj +2 more sources
On the Generalization of Stochastic Gradient Descent with Momentum
J. Mach. Learn. Res., 2018 While momentum-based accelerated variants of stochastic gradient descent (SGD) are widely used when training machine learning models, there is little theoretical understanding on the generalization error of such methods. In this work, we first show that there exists a convex loss function for which the stability gap for multiple epochs of SGD with ...
Ramezani-Kebrya, Ali +4 more
openaire +4 more sources