Minimal Exploration in Structured Stochastic Bandits
Richard Combes, Stefan Magureanu, Alexandre Proutiere
This paper introduces and addresses a wide class of stochastic bandit problems where the function mapping the arm to the corresponding reward exhibits some known structural properties.
Near-Optimal Edge Evaluation in Explicit Generalized Binomial Graphs
Sanjiban Choudhury, Shervin Javdani, Siddhartha Srinivasa, Sebastian Scherer
Neural Information Processing Systems http://nips.cc/
Noise-Tolerant Interactive Learning Using Pairwise Comparisons
Yichong Xu, Hongyang Zhang, Kyle Miller, Aarti Singh, Artur Dubrawski
Neural Information Processing Systems http://nips.cc/
Efficient Use of Limited-Memory Accelerators for Linear Learning on Heterogeneous Systems
Celestine Dรผnner, Thomas Parnell, Martin Jaggi
Neural Information Processing Systems http://nips.cc/
Collapsed variational Bayes for Markov jump processes
Boqian Zhang, Jiangwei Pan, Vinayak A. Rao
Neural Information Processing Systems http://nips.cc/
Formal Guarantees on the Robustness of a Classifier against Adversarial Manipulation
Matthias Hein, Maksym Andriushchenko
Recent work has shown that state-of-the-art classifiers are quite brittle, in the sense that a small adversarial change of an originally with high confidence correctly classified input leads to a wrong classification again with high confidence. This raises concerns that such classifiers are vulnerable to attacks and calls into question their usage in safety-critical systems. We show in this paper for the first time formal guarantees on the robustness of a classifier by giving instance-specific lower bounds on the norm of the input manipulation required to change the classifier decision. Based on this analysis we propose the Cross-Lipschitz regularization functional. We show that using this form of regularization in kernel methods resp.
Learning Graph Representations with Embedding Propagation
Forward messages consist of label representations such as representations of words and other attributes associated with the nodes. Backward messages consist of gradients that result from aggregating the label representations and applying a reconstruction loss. Node representations are finally computed from the representation of their labels.
Learning ReLUs via Gradient Descent
Neural Information Processing Systems http://nips.cc/
Efficient and Flexible Inference for Stochastic Systems
Stefan Bauer, Nico S. Gorbach, Djordje Miladinovic, Joachim M. Buhmann
Many real world dynamical systems are described by stochastic differential equations. Thus parameter inference is a challenging and important problem in many disciplines. We provide a grid free and flexible algorithm offering parameter and state inference for stochastic systems and compare our approch based on variational approximations to state of the art methods showing significant advantages both in runtime and accuracy.