Fast and Scalable Caputo Fractional Gradient Descent via Perturbation-Preserving Memory Compression (Q7284145)
From MaRDI portal
!
This is the item page for this Wikibase entity, intended for internal use and editing purposes. Please use the normal view instead:
No description defined
| Language | Label | Description | Also known as |
|---|---|---|---|
| default for all languages | No label defined |
||
| English | Fast and Scalable Caputo Fractional Gradient Descent via Perturbation-Preserving Memory Compression |
No description defined |
Statements
Fast and Scalable Caputo Fractional Gradient Descent via Perturbation-Preserving Memory Compression (English)
0 references
16 July 2026
0 references
math.OC
0 references
cs.LG
0 references
cs.NE
0 references
math.NA
0 references
Hwanseo Lee
0 references
Junseo Lee
0 references
Hyunju Kim
0 references
We propose a fast and scalable variant of Caputo fractional gradient descent that combines efficient memory compression with perturbation-preserving properties. Our new dyadic hierarchical discrete convolution (DHDC) method provides a principled way to reduce the computational cost while maintaining convergence guarantees under standard assumptions.
0 references
Fractional Gradient
0 references
Caputo Operator
0 references
Memory Compression
0 references
Optimization
0 references
