7k citations
- University of California, Santa BarbaraUS71 papers
- University of Maryland, College ParkUS21 papers
- ETH ZurichCH18 papers
- University of California, BerkeleyUS18 papers
- California Institute of TechnologyUS17 papers
- University of California, Los AngelesUS13 papers
- Board of the Swiss Federal Institutes of TechnologyCH11 papers
- Microsoft Research (United Kingdom)GB10 papers
- Oak Ridge National LaboratoryUS8 papers
- Princeton UniversityUS8 papers
- University of Tennessee at KnoxvilleUS8 papers
- RWTH Aachen UniversityDE7 papers
4 papers · 2 filters
Optimal amortized regret in every interval
Rina Panigrahy, Preyas Popat
Consider the classical problem of predicting the next bit in a sequence of bits. A standard performance measure is {\em regret} (loss in payoff) with respect to a set of experts. F…
Models and Selection Criteria for Regression and Classification
David Heckerman, Christopher Meek
When performing regression or classification, we are interested in the conditional probability distribution for an outcome or class variable Y given a set of explanatoryor input va…
Mixture Representations for Inference and Learning in Boltzmann Machines
Neil D. Lawrence, Christopher M. Bishop, Michael I. Jordan
Boltzmann machines are undirected graphical models with two-state stochastic variables, in which the logarithms of the clique potentials are quadratic functions of the node states.…
Graphical Models and Exponential Families
Dan Geiger, Christopher Meek
We provide a classification of graphical models according to their representation as subfamilies of exponential families. Undirected graphical models with no hidden variables are l…