10.9k citations
- University of WashingtonUS311 papers
- University of MichiganUS102 papers
- Michigan State UniversityUS94 papers
- Brookhaven National LaboratoryUS93 papers
- Fermi National Accelerator LaboratoryUS93 papers
- University of Science and Technology of ChinaCN93 papers
- Czech Academy of SciencesCZ91 papers
- Indiana University BloomingtonUS91 papers
- Joint Institute for Nuclear ResearchRU90 papers
- University of ArizonaUS90 papers
- Czech Technical University in PragueCZ89 papers
- Lancaster UniversityGB88 papers
12 papers · 2 filters
Mo' States Mo' Problems: Emergency Stop Mechanisms from Observation
Samuel Ainsworth, Matt Barnes, Siddhartha Srinivasa
In many environments, only a relatively small subset of the complete state space is necessary in order to accomplish a given task. We develop a simple technique using emergency sto…
Expressiveness and Learning of Hidden Quantum Markov Models
Sandesh Adhikary, Siddarth Srinivasan, Geoff Gordon +1
Extending classical probabilistic reasoning using the quantum mechanical view of probability has been of recent interest, particularly in the development of hidden quantum Markov m…
The Nonstochastic Control Problem
Elad Hazan, Sham M. Kakade, Karan Singh
We consider the problem of controlling an unknown linear dynamical system in the presence of (nonstochastic) adversarial perturbations and adversarial convex loss functions. In con…
Adversarial Fisher Vectors for Unsupervised Representation Learning
Shuangfei Zhai, Walter Talbott, Carlos Guestrin +1
We examine Generative Adversarial Networks (GANs) through the lens of deep Energy Based Models (EBMs), with the goal of exploiting the density model that follows from this formulat…
Learning Transferable Graph Exploration
Hanjun Dai, Yujia Li, Chenglong Wang +3
This paper considers the problem of efficient exploration of unseen environments, a key challenge in AI. We propose a `learning to explore' framework where we learn a policy from a…
Harnessing the Power of Infinitely Wide Deep Nets on Small-data Tasks
Sanjeev Arora, Simon S. Du, Zhiyuan Li +3
Recent research shows that the following two models are equivalent: (a) infinitely wide neural networks (NNs) trained under l2 loss by gradient descent with infinitesimally small l…