mlsanityData to 7 Oct 2026

Fuzzy hyperparameters update in a second order optimization

arXiv 2403.15416 ↗First posted 8 Mar 2024cs.LG cs.AI math.OCcited by 0

Not on the map. Why?

Abstract (arXiv)

This research will present a hybrid approach to accelerate convergence in a second order optimization. An online finite difference approximation of the diagonal Hessian matrix will be introduced, along with fuzzy inferencing of several hyperparameters. Competitive results have been achieved

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 7 of its 18 references that are in the map. First posted on arXiv 8 Mar 2024.

Builds on

7 of 18 references.

References · 7

  1. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
  2. 2020ADAHESSIAN: An Adaptive Second Order Optimizer for Machine Learningcited by 201
  3. 2020Hyper-Parameter Optimization: A Review of Algorithms and Applicationscited by 114
  4. 2019A Survey of Optimization Methods from a Machine Learning Perspectivecited by 90
  5. 2017Sub-sampled Cubic Regularization for Non-convex Optimizationcited by 63
  6. 2017Block-diagonal Hessian-free Optimization for Training Neural Networkscited by 10
  7. 2021Approximating the diagonal of a Hessian: which sample set of points should be usedcited by 1

Built on by

Not cited yet.