Country
Stochastic Online Greedy Learning with Semi-bandit Feedbacks
In this paper, we address the online learning problem when the input to the greedy algorithm is stochastic with unknown parameters that have to be learned over time.
Conditional Generative Moment-Matching Networks
Yong Ren, Jun Zhu, Jialian Li, Yucen Luo
Neural Information Processing Systems http://nips.cc/
Multi-Step Stochastic ADMM in High Dimensions: Applications to Sparse Optimization and Matrix Decomposition
Hanie Sedghi, Anima Anandkumar, Edmond Jonckheere
In this paper, we consider a multi-step version of the stochastic ADMM method with efficient guarantees for high-dimensional problems. We first analyze the simple setting, where the optimization problem consists of a loss function and asingleregularizer(e.g.
Online Bayesian Moment Matching for Topic Modeling with Unknown Number of Topics
Neural Information Processing Systems http://nips.cc/
Joint distribution optimal transportation for domain adaptation
Nicolas Courty, Rémi Flamary, Amaury Habrard, Alain Rakotomamonjy
However, the generating process can be different in several aspects, such as the conditions and devices used for acquisition, different pre-processing, different compressions, etc. Domain adaptation
Third-Order Edge Statistics: Contour Continuation, Curvature, and Cortical Connections
Matthew Lawlor, Steven W. Zucker
Neural Information Processing Systems http://nips.cc/
Policy Gradient for Coherent Risk Measures
Aviv Tamar, Yinlam Chow, Mohammad Ghavamzadeh, Shie Mannor
Neural Information Processing Systems http://nips.cc/
Tagger: Deep Unsupervised Perceptual Grouping
Klaus Greff, Antti Rasmus, Mathias Berglund, Tele Hao, Harri Valpola, Jürgen Schmidhuber
Neural Information Processing Systems http://nips.cc/
A Locally Adaptive Normal Distribution
Georgios Arvanitidis, Lars K. Hansen, Søren Hauberg
The underlyingmetricis,however,non-parametric.Wedevelopamaximumlikelihood algorithm to infer the distribution parameters that relies on a combination of gradient descent and Monte Carlo integration. We further extend the LAND to mixture models, andprovidethecorresponding EMalgorithm.