Solving optimization problems is the key to decision making in many real-life analytics applications. However, the coefficients of the optimization problems are often uncertain and dependent on external factors, such as future demand or energy or stock prices. Machine learning (ML) models, especially neural networks, are increasingly being used to estimate these coefficients in a data-driven way.

Neural Information Processing Systems http://nips.cc/

Designing and discovering new molecules is key for addressing some of world's most pressing

By invoking ideas from non-equilibrium statistical mechanics we derive an efficient training procedure by which both the sampler's and the flow's parameters can be optimized end-to-end, and by which we can compute

However, recommendations can easily violate preferences of users from their past natural-language feedback, since the recommender needs to explore new items for further improvement.

First provide a summary of the paper, and then address the following criteria: Quality, clarity, originality and significance. The paper under review, Optimizing Energy Production Using Policy Search describes a policy search algorithm for optimizing the energy production in a hydroelectric power plant. First, the problem is specified with a model of the system, the goal and the constraints. Afterwards, a predictive state representation is introduced for the inflow process. Finally, a policy search algorithm based on a random local search is presented and evaluated on a dataset of a real power-plant.

We introduce a convolutional neural network that operates directly on graphs. These networks allow end-to-end learning of prediction pipelines whose inputs are graphs of arbitrary size and shape. The architecture we present generalizes standard molecular feature extraction methods based on circular fingerprints. We show that these data-driven features are more interpretable, and have better predictive performance on a variety of tasks.

This paper addresses the problem of time series forecasting for non-stationary signals and multiple future steps prediction.

Neural Information Processing Systems http://nips.cc/