Sciweavers

2096 search results - page 33 / 420
» Structured Parameter Elicitation
Sort
View
JAIR
2008
103views more  JAIR 2008»
14 years 9 months ago
ICE: An Expressive Iterative Combinatorial Exchange
We present the design and analysis of the first fully expressive, iterative combinatorial exchange (ICE). The exchange incorporates a tree-based bidding language (TBBL) that is co...
Benjamin Lubin, Adam I. Juda, Ruggiero Cavallo, S&...

Publication
240views
13 years 8 months ago
Bayesian multitask inverse reinforcement learning
We generalise the problem of inverse reinforcement learning to multiple tasks, from multiple demonstrations. Each one may represent one expert trying to solve a different task, or ...
Christos Dimitrakakis, Constantin A. Rothkopf
STOC
2012
ACM
209views Algorithms» more  STOC 2012»
13 years 5 days ago
Nearly optimal solutions for the chow parameters problem and low-weight approximation of halfspaces
The Chow parameters of a Boolean function f : {−1, 1}n → {−1, 1} are its n + 1 degree-0 and degree-1 Fourier coefficients. It has been known since 1961 [Cho61, Tan61] that ...
Anindya De, Ilias Diakonikolas, Vitaly Feldman, Ro...
COLT
2010
Springer
14 years 7 months ago
Hedging Structured Concepts
We develop an online algorithm called Component Hedge for learning structured concept classes when the loss of a structured concept sums over its components. Example classes inclu...
Wouter M. Koolen, Manfred K. Warmuth, Jyrki Kivine...
ICML
2005
IEEE
15 years 10 months ago
Learning as search optimization: approximate large margin methods for structured prediction
Mappings to structured output spaces (strings, trees, partitions, etc.) are typically learned using extensions of classification algorithms to simple graphical structures (eg., li...
Daniel Marcu, Hal Daumé III