Statistical Learning
A Novel Framework for Policy Mirror Descent with General Parameterization and Linear Convergence Carlo Alfano Department of Statistics University of Oxford
In this work, we introduce a framework for policy optimization based on mirror descent that naturally accommodates general parameterizations. The policy class induced by our scheme recovers known classes, e.g., softmax, and generates new ones depending on the choice of mirror map.
Approximation algorithms for stochastic clustering
David Harris, Shi Li, Aravind Srinivasan, Khoa Trinh, Thomas Pensyl
Neural Information Processing Systems http://nips.cc/
Transfer Anomaly Detection by Inferring Latent Domain Representations
Atsutoshi Kumagai, Tomoharu Iwata, Yasuhiro Fujiwara
Neural Information Processing Systems http://nips.cc/
Early Stopping for Nonparametric Testing
Neural Information Processing Systems http://nips.cc/
Scalable Laplacian K-modes
Imtiaz Ziko, Eric Granger, Ismail Ben Ayed
Furthermore, we show that the density modes can be obtained as byproducts of the assignment variables via simple maximum-value operations whose additional computational cost is linear in the number of data points.
