Recorded talks
DISCML 2012
- Satoru Fujishige: Submodularity and Discrete Convexity
- Venkat Chandrasekaran: Computational and Statistical Tradeoffs via Convex Relaxation
- Amir Globerson: What cannot be learned with Bethe Approximations
- Alex Smola: The Parameter Server
DISCML 2011
- Jack Edmonds: Polymatroids and Submodularity
- Pushmeet Kohli: Exploiting Problem Structure for Efficient Discrete Optimization
- Francis Bach: Learning with Submodular Functions: A Convex Optimization Perspective
- Nicolo Cesa-Bianchi: Combinatorial prediction games
DISCML 2010
- Satoru Iwata: Submodular Function Minimization
- Jan Vondrak: Multilinear relaxation: a tool for maximization of submodular functions
- Tamir Hazan: Mixing sum-product and max-product type updates to tighten tree-reweighted upper bounds for the log-partiton function
- Stefanie Jegelka: Online submodular minimization with combinatorial constraints
- Yuri Boykov: Energy Minimization with Label costs and Applications in Multi-Model Fitting
- Terry Koo: Dual decomposition for inference in natural language processing
- Joachim Buhmann: Information Theoretic Model Validation by Approximate Optimization
- Carlos Guestrin: Taming Information Overload
- Daniel Golovin: Adaptive Submodularity: A New Approach to Active Learning and Stochastic Optimization