Difference between revisions of "OPT 2008"
Jump to navigation
Jump to search
(modified through wikirestore by orapi) |
(modified through wikirestore by orapi) |
||
| Line 14: | Line 14: | ||
| Homepage= opt2008.kyb.tuebingen.mpg.de/ | | Homepage= opt2008.kyb.tuebingen.mpg.de/ | ||
| Start date= 2008-12-12 | | Start date= 2008-12-12 | ||
| − | | Title = Optimization for Machine Learning (NIPS Workshop 2008)}} | + | | Title = Optimization for Machine Learning (NIPS Workshop 2008) |
| + | }} | ||
We invite high quality submissions for presentation as talks or posters during the workshop. We are especially interested in participants who can contribute in the following areas: | We invite high quality submissions for presentation as talks or posters during the workshop. We are especially interested in participants who can contribute in the following areas: | ||
Latest revision as of 02:24, 6 December 2021
Event Rating
| median | worst |
|---|---|
List of all ratings can be found at OPT 2008/rating
| OPT 2008 | |
|---|---|
Optimization for Machine Learning (NIPS Workshop 2008)
| |
| Dates | 2008-12-12 (iCal) - 2008-12-13 |
| Homepage: | opt2008.kyb.tuebingen.mpg.de/ |
| Location | |
| Location: | CA/BC/Whistler, CA/BC, CA |
| Important dates | |
| Submissions: | Oct 17, 2008 |
| Notification: | Nov 7, 2008 |
| Camera ready due: | Nov 20, 2008 |
| Table of Contents | |
We invite high quality submissions for presentation as talks or posters during the workshop. We are especially interested in participants who can contribute in the following areas:
- Non-Convex Optimization example problems in ML include
- Problems with sparsity constraints
- Sparse PCA
- Non-negative matrix and tensor approximation
- Non-convex quadratic programming
- Combinatorial and Discrete Optimization example problems in ML include
- Estimating MAP solutions to discrete random fields
- Clustering and graph-partitioning
- Semi-supervised and multiple-instance learning
- Feature and subspace selection
- Stochastic, Parallel and Online Optimization example problems in ML include
- Massive data sets
- Distributed learning algorithms
- Algorithms and Techniques especially with a focus on an underlying application
- Polyhedral combinatorics, polytopes and strong valid inequalities
- Linear and higher-order relaxations
- Semidefinite programming relaxations
- Decomposition for large-scale, message-passing and online learning
- Global and Lipschitz optimization
- Algorithms for non-smooth optimization
- Approximation Algorithms
The above list is not exhaustive, and we welcome submissions on highly related topics too.
- Deadline for submission of papers: 17th October 2008
- Notification of acceptance: 7th November 2008
- Final version of submission: 20th November 2008
- Workshop date: 12th or 13th December 2008