1.5k citations
- Massachusetts Institute of TechnologyUS134 papers
- Purdue University West LafayetteUS128 papers
- Wayne State UniversityUS126 papers
- The Ohio State UniversityUS124 papers
- University of California, DavisUS124 papers
- University of California, Los AngelesUS124 papers
- Texas A&M UniversityUS122 papers
- University of RochesterUS110 papers
- Joint Institute for Nuclear ResearchRU109 papers
- University of FloridaUS109 papers
- Institute for High Energy PhysicsES106 papers
- Fermi National Accelerator LaboratoryUS105 papers
124 papers · 1 filter
Alternating Directions Dual Decomposition
Andre F. T. Martins, Mario A. T. Figueiredo, Pedro M. Q. Aguiar +2
We propose AD3, a new algorithm for approximate maximum a posteriori (MAP) inference on factor graphs based on the alternating directions method of multipliers. Like dual decomposi…
Omitting types and AF algebras
Kevin Carlson, Enoch Cheung, Ilijas Farah +5
We give model-theoretic characterizations of UHF algebras and of AF algebras as C*-algebras that omit certain sets of types.
Real-valued All-Dimensions search: Low-overhead rapid searching over subsets of attributes
Andrew Moore, Jeff Schneider
This paper is about searching the combinatorial space of contingency tables during the inner loop of a nonlinear statistical optimization. Examples of this operation in various dat…
Distributed Planning in Hierarchical Factored MDPs
Carlos E. Guestrin, Geoffrey Gordon
We present a principled and efficient planning algorithm for collaborative multiagent dynamical systems. All computation, during both the planning and the execution phases, is dist…
Interpolating Conditional Density Trees
Scott Davies, Andrew Moore
Joint distributions over many variables are frequently modeled by decomposing them into products of simpler, lower-dimensional conditional distributions, such as in sparsely connec…
Learning with Scope, with Application to Information Extraction and Classification
David Blei, J Andrew Bagnell, Andrew McCallum
In probabilistic approaches to classification and information extraction, one typically builds a statistical model of words under the assumption that future data will exhibit the s…