Showing cs.LGShow all
2 papers · 1 filter
cs.LG2025
Understanding Outer Optimizers in Local SGD: Learning Rates, Momentum, and Acceleration
Ahmed Khaled, Satyen Kale, Arthur Douillard +3
Modern machine learning often requires training with large batch size, distributed data, and massively parallel compute hardware (like mobile and other edge devices or distributed…
cs.LG2024
A Fresh Take on Stale Embeddings: Improving Dense Retriever Training with Corrector Networks
Nicholas Monath, Will Grathwohl, Michael Boratko +3
In dense retrieval, deep encoders provide embeddings for both inputs and targets, and the softmax function is used to parameterize a distribution over a large number of candidate t…