numerical-optimization

Tag

Cards List
#numerical-optimization

Z-Loss Backward Geometry in Dense Output Heads and Sparse Routers

arXiv cs.LG ↗ · 2026-09-16 Cached

This paper analyzes the backward-pass geometry of Z-loss in AI model training, providing a framework for understanding and optimizing gradients in dense output heads and sparse mixture-of-experts routers, with evaluations on GPT-2 and Pythia models.

0 favorites 0 likes
#numerical-optimization

Basin: Efficient and Extensible Numerical Optimization in Rust

arXiv cs.LG ↗ · 2026-08-13 Cached

Basin is a numerical optimization library for Rust that provides a broad catalog of solvers, first-class constraint support, and a WebAssembly-ready default build.

0 favorites 0 likes
← Back to home

Submit Feedback