activity
20242026
most citedCurvature-Adaptive Perturbation and Subspace Descent for Robust Saddle Point Escape in High-Dimensional Optimization

1 citations · 1 across the 6 of their papers we have counts for

collaborators
Showing 2024Show all

2 papers · 1 filter

cs.LG2024

Adaptive Error-Bounded Hierarchical Matrices for Efficient Neural Network Compression

John Mango, Ronald Katende

This paper introduces a dynamic, error-bounded hierarchical matrix (H-matrix) compression method tailored for Physics-Informed Neural Networks (PINNs). The proposed approach reduce…

math.OC2024★ 1 cited

Curvature-Adaptive Perturbation and Subspace Descent for Robust Saddle Point Escape in High-Dimensional Optimization

Ronald Katende, Henry Kasumba

High-dimensional non-convex optimization problems in engineering design, control, and learning are often hindered by saddle points, flat plateaus, and strongly anisotropic curvatur…