-
1
Low-Rank Gradient Descent
Published 2023-01-01“…In this article, we leverage such low-rank structure to reduce the high computational cost of canonical gradient-based methods such as gradient descent (<monospace>GD</monospace>). Our proposed <italic>Low-Rank Gradient Descent</italic> (<monospace>LRGD</monospace>) algorithm finds an <inline-formula><tex-math notation="LaTeX">$\epsilon$</tex-math></inline-formula>-approximate stationary point of a <inline-formula><tex-math notation="LaTeX">$p$</tex-math></inline-formula>-dimensional function by first identifying <inline-formula><tex-math notation="LaTeX">$r \leq p$</tex-math></inline-formula> significant directions, and then estimating the true <inline-formula><tex-math notation="LaTeX">$p$</tex-math></inline-formula>-dimensional gradient at every iteration by computing directional derivatives only along those <inline-formula><tex-math notation="LaTeX">$r$</tex-math></inline-formula> directions. …”
Get full text
Article -
2
On-manifold projected gradient descent
Published 2024-02-01“…The tools are applied to the setting of neural network image classifiers, where we generate novel, on-manifold data samples and implement a projected gradient descent algorithm for on-manifold adversarial training. …”
Get full text
Article -
3
-
4
Carathéodory sampling for stochastic gradient descent
Published 2020“…Many problems require to optimize empirical risk functions over large data sets. Gradient descent methods that calculate the full gradient in every descent step do not scale to such datasets. …”
Internet publication -
5
Carathéodory sampling for stochastic gradient descent
Published 2020“…Many problems require to optimize empirical risk functions over large data sets. Gradient descent methods that calculate the full gradient in every descent step do not scale to such datasets. …”
Internet publication -
6
Dual space preconditioning for gradient descent
Published 2021“…Thus, in principle our method is capable of improving the conditioning of gradient descent on problems with a non-Lipschitz gradient or nonstrongly convex structure. …”
Journal article -
7
Pipelined Stochastic Gradient Descent with Taylor Expansion
Published 2023-10-01Subjects: Get full text
Article -
8
Accelerated Gradient Descent Driven by Lévy Perturbations
Published 2024-03-01Subjects: “…accelerated gradient descent…”
Get full text
Article -
9
Gradient Descent Batch Clustering for Image Classification
Published 2023-07-01Subjects: Get full text
Article -
10
Stochastic gradient descent for optimization for nuclear systems
Published 2023-05-01“…ADAM is a gradient descent method that accounts for gradients with a stochastic nature. …”
Get full text
Article -
11
Stochastic gradient descent for wind farm optimization
Published 2023-08-01“…This study presents stochastic gradient descent (SGD) for wind farm optimization, which is an approach that estimates the gradient of the AEP using Monte Carlo simulation, allowing for the consideration of an arbitrarily large number of atmospheric conditions. …”
Get full text
Article -
12
-
13
The complexity of gradient descent: CLS = PPAD∩PLS
Published 2022“…We study search problems that can be solved by performing Gradient Descent on a bounded convex polytopal domain and show that this class is equal to the intersection of two well-known classes: PPAD and PLS. …”
Journal article -
14
The Improved Stochastic Fractional Order Gradient Descent Algorithm
Published 2023-08-01Subjects: Get full text
Article -
15
Recent Advances in Stochastic Gradient Descent in Deep Learning
Published 2023-01-01Subjects: “…stochastic gradient descent…”
Get full text
Article -
16
Granular Elastic Network Regression with Stochastic Gradient Descent
Published 2022-07-01“…After that, we conduct the derivative of the granular loss function and design the granular elastic network gradient descent optimization algorithm. Finally, we performed experiments on the UCI datasets to verify the validity of the granular elasticity network. …”
Get full text
Article -
17
Distributed Stochastic Gradient Descent With Compressed and Skipped Communication
Published 2023-01-01Subjects: “…distributed stochastic gradient descent…”
Get full text
Article -
18
Optimization of Gradient Descent Parameters in Attitude Estimation Algorithms
Published 2023-02-01Subjects: Get full text
Article -
19
Gradient-descent-like scheme for the Allen–Cahn equation
Published 2023-08-01“…From a numerical point of view, a linear, unconditionally energy stable splitting scheme is transformed into a gradient-descent-like scheme. Various numerical simulations are illustrated to demonstrate the validity of the proposed scheme. …”
Get full text
Article -
20
Gradient descent with adaptive momentum for active contour models
Published 2014-08-01Subjects: Get full text
Article