Research map / Learning theory and algorithms / Matrix and tensor methods
PRISM: Distribution-free Adaptive Computation of Matrix Functions for Accelerating Neural Network Training
Shenghao Yang, Zhichao Wang, Oleg Balabanov, N. Benjamin Erichson, Michael W. Mahoney
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| replace PolarExpress with PRISM-5 polar decomposition inside Muon | Muon (GPT-2 Large) · GPT-2 Large (10 layers) on FineWeb 200M tokens, Muon | final validation loss: 5.4523 -> 5.0251 | Improved |
| use degree-3 instead of degree-5 PRISM polynomial | Muon (GPT-2 Large) · GPT-2 Large (10 layers) on FineWeb 200M tokens, Muon | final validation loss: 5.0251 -> 4.9886 | Improved |
| replace AdamW with Muon using PRISM-3 | GPT-2 Large · GPT-2 Large (10 layers) on FineWeb 200M tokens, Muon | final validation loss: 6.8689 -> 4.9886 | Improved |
Closest papers by meaning
- Provable Acceleration of Nesterov's Accelerated Gradient for Asymmetric Matrix Factorization and Linear Neural Networks (NeurIPS 2024 · similarity 0.87)
- Kernel Methods Through the Roof: Handling Billions of Points Efficiently (NeurIPS 2020 · similarity 0.86)
- Learning to Discover Iterative Spectral Algorithms (NeurIPS 2026 · similarity 0.86)
- RAPNet: Accelerating Algebraic Multigrid with Learned Sparse Corrections (ICML 2026 · similarity 0.86)
- Searching for Efficient Linear Layers over a Continuous Space of Structured Matrices (NeurIPS 2024 · similarity 0.85)
- Near-optimal Sketchy Natural Gradients for Physics-Informed Neural Networks (ICML 2025 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
