OPT 2015 - 8th NIPS Workshop on Optimization for Machine Learning

OPT 2015 - 8th NIPS Workshop on Optimization for Machine Learning
December 11th 2015, Montreal, Quebec, Canada
http://opt-ml.org/
IMPORTANT DATES:
---
Submission deadline: 20th October, 2015
Acceptance decisions: 2nd November, 2015
Submission URL: http://www.easychair.org/conferences/?conf=opt2015
Format: NIPS 2015 format; double blind
INVITED TALKS:
---
* Jorge Nocedal (Northwestern University, US)
* Guanghui Lan (University of Florida, US)
* Elad Hazan (Princeton, US)
OVERVIEW
---
Optimization lies at the heart of many machine learning algorithms and enjoys great interest in our community. Indeed, this intimate relation of optimization with ML is the key motivation for the OPT series of workshops. We aim to foster discussion, discovery, and dissemination of the state-of-the-art in optimization relevant to ML.
A key focus for the workshop is non-convex optimization, with contributions spanning both the challenges (hardness results) and the opportunities (modeling flexibility). Contributions on fundamental result and progress in convex optimization are highly encouraged too.
We invite participation in the 8th International Workshop on "Optimization for Machine Learning", to be held as a part of the NIPS 2015 conference. This year we invite two types of submissions to the workshop:
(i) contributed talks and/or posters
(ii) open problems
For the latter, we request the authors to prepare a few slides that clearly present, motivate, and explain an important open problem --- the main aim here is to foster active discussion. Our call for open problems is modeled after a similar session that takes place at COLT. The topics of interest for the open problem session are the same as those for regular submissions; please see below for details.
In addition to open problems, we invite high quality submissions for presentation as talks or poster presentations during the workshop. We are especially interested in participants who can contribute theory / algorithms, applications, or implementations with a machine learning focus.
The main topics are, including, but not limited to:
Nonconvex Optimization:
Theoretical investigations, global optimality
Training of deep architectures and large hidden variable models
Nonconvex quadratic programming, including binary QPs
Convex Concave Decompositions, D.C. Programming
EM, majorization-minimization and alternating optimization
Approximation Algorithms
Nonsmooth optimization
Stochastic, Parallel and Online Optimization:
Large-scale learning, massive data sets
Distributed algorithms
Distributed optimization algorithms, and parallel architectures
Optimization using GPUs, Streaming algorithms
Decomposition for large-scale, message-passing, and online optimization
Stochastic approximations
Algorithms and Techniques (application oriented):
Global and Lipschitz optimization
Algorithms for nonsmooth optimization
Linear and higher-order relaxations
Polyhedral combinatorics applications to ML problems
Optimization with Sparsity constraints
Combinatorial and greedy methods for L0 norm optimization
L1, Lasso, Group Lasso, sparse PCA, sparse Gaussians
Rank minimization methods
Feature and subspace selection
Nonconvex sparse problems
Combinatorial Optimization
Optimization in Graphical Models
Structure learning
MAP estimation in continuous and discrete random fields
Clustering and graph-partitioning
Semi-supervised and multiple-instance learning
Other discrete optimization models and algorithms
Advanced optimization techniques
Core set based approximation schemes
Hashing based optimization
Optimization in statistics, statistical/computational tradeoffs
Optimization on manifolds, metric spaces
Problems on cones
Polynomials, sums-of-squares, moment problems
Numerical optimization
Optimization software
Crucial implementation details (architecture, language, etc.)
Submission Instructions:
????????????
Submission website: http://www.easychair.org/conferences/?conf=opt2015
Page limit: 4 pages (without references)
Please use the NIPS 2015 submission format
Please make submission double blind
If you are doing a dual submission, please contact us first
Please note that at least one author of each accepted paper must be available to present the paper at the workshop.
Looking forward to another great OPT workshop!
Organizing Committee:
Alekh Agarwal, MSR New York, US
Leon Bottou, Facebook AI Research, US
Sashank J. Reddi, Carnegie Mellon University, US
Suvrit Sra, MIT, US
With advisory support from Arkadi Nemirovskii and Francis Bach.