Meta FAIR's e-means beats k-means in 1/10th the epochs with 10-45x GPU speedups
TheTuringPost · x · 2026-11-15
Meta FAIR and ENPC researchers introduce e-means, a mini-batch k-means replacement using exponential moving averages. It beats Lloyd's k-means loss at 25 epochs in 1.4-2.6 epochs, delivers 10x-45x GPU wall-clock speedups, and comes with scaling laws that eliminate hyperparameter tuning. Open-sourced in the FAISS repo; demoed partitioning DINO10B (10B embeddings) into 16M clusters in 2.5 epochs.
More from Research
- Context distillation fixes: relevance gating and 2x strength cut value spillover to 7% — Sauers_ · 2026-11-15
- Epoch AI: post-training enhancements yield gains equal to 5-20x compute at under 1% the cost — CFGeek · 2026-11-15
- Qwen3 at 2.7 bits/weight with Leech lattice quantization beats IQ2_S on quality, loses on speed — Fuzzy-Layer9967 · 2026-11-15
- Steering with Natural-Scale Gaussian Noise in Random 4-Dim Space Sparks Follow-up Research — Sauers_ · 2026-11-15
- What 'Compute Multipliers' Mean: The Under-discussed Algorithmic Efficiency Metric in AI — CFGeek · 2026-11-15
- Researchers push back on Dwarkesh: defining AGI metrics is the hard part — dhadfieldmenell · 2026-11-15