ml报告
RT @askalphaxiv: One of the most used algorithms in ML just got a major upgrade after nearly 70 years, as Meta researchers found a way to outperform k-means with 1/10 the training passes, while achieving even lower clustering error.
This paper proposes e-means, which updates cluster centers using smaller batches and exponential moving averages instead. It also uses scaling laws to automatically choose the batch size and learning rate, enabling it to converge faster without additional hyperparameter tuning.
Across embedding datasets, e-means achieves lower clustering error in just 1.4-2.6 epochs compared to 25 epochs for traditional k-means, providing 10-45x GPU speedups. It can even cluster 10 billion embeddings into 16 million groups in just 2.5 epochs.
https://t.co/lUTfawgQpc