Archive: Hogwild for Machine Learning on Multicore
3,426 views · Published 12 June 2014 · 51:23 · Indexed 12 November 2026
Channel: UW Video · 2014 · Education
This program provides both theoretical and experimental evidence demonstrating the achievement of linear speedups on multicore workstations on several benchmark optimization problems. Stochastic Gradient Descent (SGD) is a popular optimization algorithm for solving data-driven machine learning problems such as classification, model selection, sequence labeling, and recommendation. SGD is well suited to processing large amounts of data due to its robustness against noise, rapid convergence rates, and predictable memory footprint. Learn how SGD can be implemented in parallel with minimal communication, with no locking or synchronization, and with strong spatial locality. Finally, hear a discussion of a challenging problem raised by our implementations relating arithmetic and geometric means of positive definite matrices. Produced 5/3/2012
More from this channel
-
54:45
Archive: Usable Privacy and Security: Protecting People from Online Phishing Scams
-
58:27
Archive: Technology for Long-Term Care: Scaling Elder Care to the Next Billion
-
53:34
Archive: Closing the Innovation Gap
-
52:34
Archive: Hardness Amplification by Repetition
-
54:57
Archive: Network Coded Wireless Architecture
-
56:48
Archive: Computer Science Research for Global Development
-
58:16
Archive: Thinking Historically about Thinking Historically: Identity Politics to Ethical Action
-
27:18
Archive: Eastside Specialty Center: Coordination of Care