Is Local SGD Better than Minibatch SGD?
Jul 12, 2020
Speakers
Blake Woodworth
Speaker · 0 followers
Kumar Kshitij Patel
Speaker · 0 followers
Sebastian Stich
Speaker · 0 followers
Brian Bullins
Speaker · 0 followers
Brendan McMahan
Speaker · 16 followers
Ohad Shamir
Speaker · 0 followers
Nathan Srebro
Speaker · 1 follower
About
We study local SGD (also known as parallel SGD and federated SGD), a natural and frequently used distributed optimization method. Its theoretical foundations are currently lacking and we highlight how all existing error guarantees in the convex setting are dominated by a simple baseline, minibatch SGD. (1) For quadratic objectives we prove that local SGD strictly dominates minibatch SGD and that accelerated local SGD is minmax optimal for quadratics; (2) For general convex objectives we provide the first guarantee that at least sometimes improves over minibatch SGD, but our guarantee does not always improve over, nor even match, minibatch SGD; (3) We show that indeed local SGD does not dominate minibatch SGD by presenting a lower bound on the performance of local SGD that is worse than the minibatch SGD guarantee.We study local SGD (also known as parallel SGD and federated SGD), a natural and frequently used distributed optimization method. Its theoretical foundations are currently lacking and we highlight how all existing error guarantees in the convex setting are dominated by a simple baseline, minibatch SGD. (1) For quadratic objectives we prove that local SGD strictly dominates minibatch SGD and that accelerated local SGD is minmax optimal for quadratics; (2) For general convex objectives we provide…
Categories
AI & Data Science
Category · 10.8k presentations
Leadership & Management
Category · 805 presentations
About ICML 2020
The International Conference on Machine Learning (ICML) is the premier gathering of professionals dedicated to the advancement of the branch of artificial intelligence known as machine learning. ICML is globally renowned for presenting and publishing cutting-edge research on all aspects of machine learning used in closely related areas like artificial intelligence, statistics and data science, as well as important application areas such as machine vision, computational biology, speech recognition, and robotics. ICML is one of the fastest growing artificial intelligence conferences in the world. Participants at ICML span a wide range of backgrounds, from academic and industrial researchers, to entrepreneurs and engineers, to graduate students and postdocs.
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
Learning the Valuations of a k-demand Agent
Watch later
Hanrui Zhang, …
A quantile-based approach for hyperparameter transfer learning
Watch later
Circuit-Based Intrinsic Methods to Detect Overfitting
Watch later
Learning Speech Representations from Raw Audio by Joint Audiovisual Self-Superision
Watch later
