Learning Graphical Models
Improving Explorability in Variational Inference with Annealed Variational Objectives Chin-Wei Huang,?, 1 Shawn Tan
In our experiments, we demonstrate our method's
Smoothed Analysis of Discrete Tensor Decomposition and Assemblies of Neurons
Nima Anari, Constantinos Daskalakis, Wolfgang Maass, Christos Papadimitriou, Amin Saberi, Santosh Vempala
We analyze linear independence of rank one tensors produced by tensor powers of randomly perturbed vectors. This enables efficient decomposition of sums of high-order tensors. Our analysis builds upon Bhaskara et al.
Negotiable Reinforcement Learning for Pareto Optimal Sequential Decision-Making
Nishant Desai, Andrew Critch, Stuart J. Russell
Harsanyi's theorem shows that when the principals have a
Posterior Concentration for Sparse Deep Learning
Veronika Rockova, nicholas polson
Deep learning constructs are powerful tools for pattern matching and prediction.
Forecasting Treatment Responses Over Time Using Recurrent Marginal Structural Networks
Electronic health records provide a rich source of data for machine learning methods to learn dynamic treatment responses over time.
Monte-Carlo Tree Search for Constrained POMDPs
Jongmin Lee, Geon-hyeong Kim, Pascal Poupart, Kee-Eung Kim
However, many real-world problems inherently have multiple goals, where multi-objective formulations are more natural.
From Stochastic Planning to Marginal MAP
Hao(Jackson) Cui, Radu Marinescu, Roni Khardon
Neural Information Processing Systems http://nips.cc/
Completing State Representations using Spectral Learning
Nan Jiang, Alex Kulesza, Satinder Singh
Neural Information Processing Systems http://nips.cc/
A Lyapunov-based Approach to Safe Reinforcement Learning
Yinlam Chow, Ofir Nachum, Edgar Duenez-Guzman, Mohammad Ghavamzadeh
In many real-world reinforcement learning (RL) problems, besides optimizing the main objective function, an agent must concurrently avoid violating a number of constraints. In particular, besides optimizing performance, it is crucial to guarantee the safety of an agent during training as well as deployment (e.g., a robot should avoid taking actions - exploratory or not - which irrevocably harm its hardware). To incorporate safety in RL, we derive algorithms under the framework of constrained Markov decision processes (CMDPs), an extension of the standard Markov decision processes (MDPs) augmented with constraints on expected cumulative costs.