bispectrum: fast exact lossless symmetry invariants for PyTorch, NeurIPS paper
ninamiolane · x · 2026-11-21
Adele Myers introduces 'bispectrum', a NeurIPS paper and open-source PyTorch library by @johmathe (with Simon Mataigne and Nina Miolane) implementing fast, exact, lossless selective G-bispectra. The SDB's size grows linearly with the number of disk harmonic basis functions, making it compact and practical; code is open-sourced (arXiv 2605.07270).
More from Research
- Anthropic researcher claims Riemann Hypothesis proof with Claude, backed by 17.4M-line Lean formalization — Kyrannio · 2026-11-21
- Anthropic's Levent Alpöge claims a Riemann Hypothesis proof discovered working with Claude — Kyrannio · 2026-11-21
- Stanford AI100 releases 2026 report on the scaling era and mainstream generative AI — stanfordnlp · 2026-11-21
- New Multi-Agent Coordination Bench finds frontier agents coordinate poorly; only Opus gains — AlexGDimakis · 2026-11-21
- Riemann Hypothesis Result's Dramatically Written Intro Draws Attention — lishali88 · 2026-11-21
- Stanford CS329Z Lecture 9 Released: Optimizing AI Agents via Prompts vs. Weights — stanfordnlp · 2026-11-21