Archive: Towards Provable and Practical Machine Learning
1,010 views · Published 1 May 2015 · 58:25 · Indexed 16 November 2026
Channel: UW Video · 2015 · Education
Many problems, especially machine learning problems like sparse coding or topic modeling, are hard in the worst-case, but nevertheless solved in practice by algorithms whose convergence properties are not understood. In this talk, Rong Ge of Princeton University shows how we can identify natural properties of "real-life" instances that allow us to design scalable algorithms for a host of well-known machine learning problems. Most of the talk will be focused on the sparse coding problem: a basic task in many fields, including signal processing, neuroscience and machine learning, where the goal is to learn a basis that enables a sparse representation of a given set of data, if one exists. Here we give a general framework for understanding alternating minimization which we leverage to analyze existing heuristics and to design new ones also with provable guarantees. Rong Ge, post-doctoral researcher, Microsoft Research 04/21/2015 http://www.cs.washington.edu/events/colloquia/search/details?id=2695 https://uw.edu/video The University of Washington is committed to ensuring digital accessibility in our services, programs, and activities. If you encounter accessibility barriers using videos found on this channel, please contact UW Video at uwvideo [at] uw [dot] edu.
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