Dec 16, 2011 
7 videos 
Optimization for Machine Learning
This workshop builds on precedent established the previous OPT workshops:
(@NIPS*08): http://opt2008.kyb.tuebingen.mpg.de/
(@NIPS*09): http://opt.kyb.tuebingen.mpg.de/opt09/
(@NIPS*10): http://opt.kyb.tuebingen.mpg.de/opt10/
Both these workshops had packed (often overpacked) attendance almost throughout the day. This enthusiastic reception reflects the strong interest, relevance, and importance enjoyed by optimization in the greater ML community.
One could ask why does optimization attract such continued interest? The answer is simple but telling: optimization lies at the heart of almost every ML algorithm. For some algorithms textbook methods suffice, but the majority requires tailoring algorithmic tools from optimization; moreover, this tailoring depends on a deeper understanding of the ML requirements. In fact, ML applications and researchers are driving some of the most cutting-edge developments in optimization today. The intimate relation of optimization with ML is the key motivation for our workshop, which aims to foster discussion, discovery, and dissemination of the state-of-the-art in optimization, especially in the context of ML.
Workshop homepage: http://opt.kyb.tuebingen.mpg.de/index.html
Invited Talks
Alternating Direction Method of Multipliers
Jan 25, 2012 51428 views
Lock-Free Approaches to Parallelizing Stochastic Gradient Descent
Jan 25, 2012 7843 views
Lectures
Making Gradient Descent Optimal for Strongly Convex Stochastic Optimization
Jan 25, 2012 4278 views
Fast first-order methods for convex optimization with line search
Jan 25, 2012 5035 views
Steppest descent analysis for unregularized linear prediction with strictly conv...
Jan 25, 2012 4441 views
Path coding penalties for directed acyclic graphs
Jan 25, 2012 4562 views
Stochastic optimization with non-i.id. noise
Jan 25, 2012 4000 views