OPT 2011: 4th International Workshop on Optimization for Machine Learning
Schedule: 16th December, 2011.
| Time | Speaker | Title | Slides | Video |
|---|---|---|---|---|
| 7:30-7:40 | Organizers | Opening remarks | ||
| 7:40-8:00 | Alekh Agarwal | Stochastic optimization with non-i.i.d. noise | [Slides] | TBA | 8:00-8:20 | Matus Telgarsky | Steepest Descent Analysis for Unregularized Linear Prediction with Strictly Convex Penalties | [Slides] | TBA |
| 8:20-9:00 | POSTER SPOTLIGHTS | |||
| 9:00-9:30 | Coffee Break (Posters) | |||
| 9:30-10:30 | Stephen Boyd | Invited Talk: Distributed Optimization via the Alternating Direction Method of Multipliers | [Slides] | TBA |
| 10:30-16:00 | Break (POSTERS) | |||
| 16:00-17:00 | Ben Recht | Invited Talk: Lock-Free Approaches to Parallelizing Stochastic Gradient Descent | [Slides] | TBA |
| 17:00-17:30 | Coffee Break (Posters) | |||
| 17:30-17:50 | Ohad Shamir | Making Gradient Descent Optimal for Strongly Convex Stochastic Optimization | [Slides] | |
| 17:50-18:10 | Katya Scheinberg | Fast First-Order Methods for Composite Convex Optimization with Large Steps | [Slides] | |
| 18:10-18:30 | Julien Mairal | Path Coding Penalties for Directed Acyclic Graphs | [Slides] | |
| 18:30-20:00 | Posters Continue | |||
Updates
Workshop Location: TBAWorkshop Date: 16.dec.2011
Poster Spotlights
- Oriol Vinyals. Krylov Subspace Descent for Deep Learning [Slides]
- Raphael Fonteneau. Relaxation Schemes for Min Max Generalization in Deterministic Batch Mode Reinforcement Learning [Slides]
- Gaelle Loosli. Non positive SVM [Slides]
- Matthieu Kowalski. Accelerating ISTA with an active set strategy [Slides]
- Miroslav Dudik. Learning with matrix gauge regularizers [Slides]
- Joris Bierkens. Online solution of the average cost Kullback-Leibler optimization problem [Slides]
- Sue Ann Hong. An Accelerated Gradient Method for Distributed Multi-Agent Planning with Factored MDPs [Slides]
- Dhruv Batra. Group Norm for Learning Latent Structural SVMs [Slides]
