Fault tolerance is an important issue for large machines with tens or hundreds of thousands of processors. Checkpoint-based methods, currently used on most machines, rollback all ...
We present Policy Gradient Actor-Critic (PGAC), a new model-free Reinforcement Learning (RL) method for creating limited-memory stochastic policies for Partially Observable Markov ...
We introduce a modified Kalman filter that performs robust, real-time outlier detection, without the need for manual parameter tuning by the user. Systems that rely on high quali...
Abstract. Robustly estimating the state-transition probabilities of highorder Markov processes is an essential task in many applications such as natural language modeling or protei...
Abstract. Clustering has recently enjoyed progress via spectral methods which group data using only pairwise affinities and avoid parametric assumptions. While spectral clustering ...