Conditioning Score-Based Generative Models by Neuro-Symbolic Constraints

Score-based and diffusion models have emerged as effective approaches for both conditional and unconditional generation. Still conditional generation is based on either a specific training of a conditional model or classifier guidance, which requires training a noise-dependent classifier, even when the classifier for uncorrupted data is given. We propose an approach to sample from unconditional score-based generative models enforcing arbitrary logical constraints, without any additional training. Firstly, we show how to manipulate the learned score in order to sample from an un-normalized distribution conditional on a user-defined constraint. Then, we define a flexible and numerically stable neuro-symbolic framework for encoding soft logical constraints. Combining these two ingredients we obtain a general, but approximate, conditional sampling algorithm. We further developed effective heuristics aimed at improving the approximation. Finally, we show the effectiveness of our approach for various types of constraints and data: tabular data, images and time series.

Multi-Objective reward generalization: Improving performance of Deep Reinforcement Learning for selected applications in stock and cryptocurrency trading

We investigate the potential of Multi-Objective, Deep Reinforcement Learning for stock and cryptocurrency trading. More specifically, we build on the generalized setting \`a la Fontaine and Friedman arXiv:1809.06364 (where the reward weighting mechanism is not specified a priori, but embedded in the learning process) by complementing it with computational speed-ups, and adding the cumulative reward's discount factor to the learning process. Firstly, we verify that the resulting Multi-Objective algorithm generalizes well, and we provide preliminary statistical evidence showing that its prediction is more stable than the corresponding Single-Objective strategy's. Secondly, we show that the Multi-Objective algorithm has a clear edge over the corresponding Single-Objective strategy when the reward mechanism is sparse (i.e., when non-null feedback is infrequent over time). Finally, we discuss the generalization properties of the discount factor. The entirety of our code is provided in open source format.