Curvature-Weighted Gradient Diversity: A Noise Measure for Geometry-Adaptive SGD Schedules
Muhammad Hamza, Ayush Goel
Indian Institute of Technology Kharagpur · Indian Institute of Technology Kharagpur
cs.LG, math.OC, stat.ML
Submitted: 2026-06-29
Comments: 15 pages, 3 figures, code available
Code: https://github.com/Hamza-Faarooq/cwgd-optimizer
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training
- Large Batch Training of Convolutional Networks
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks