Freenet routes with isotonic regression and empirical Bayes, not neural nets
Sanity · x · 2026-11-20
A Freenet developer released a video explaining the ML techniques behind its routing algorithm, including real network data. Key point: the right ML solution often isn't a neural network — routing uses isotonic regression, empirical Bayes and other classic statistical tricks. Leveraging prior knowledge of the problem to constrain the model enables useful predictions even with limited data.
Related event: Freenet Drops Neural Nets for Routing in Favor of Classic Statistics(3 posts)→
More from Infra
- US House Reveals 3.4M Chip Export Applications to China, Including 445,000 NVIDIA H200s — Dan_Jeffries1 · 2026-11-20
- 2DSD Speculative Decoding Speeds Up Looped LMs up to 7.64x With Lower KV Memory — LucaAmb · 2026-11-20
- Quantum Computing Takes Aim at AI Workloads as IBM and QuEra Map Fault-Tolerant Roadmaps — mikeflache · 2026-11-20
- Tencent Earnings Call: Latest Chip Restrictions Will Accelerate China's Domestic Semiconductor Supply Chain — basedjensen · 2026-11-20
- Chorus paper: shared n-gram tables cut memory 87% while beating DeepSeek's Engram — brown2green · 2026-11-20
- px0: A 20MB browser-based IDE for AI-generated code, built by chopping layers with first-principles thinking — arpit_bhayani · 2026-11-20