Efficient Neural Causal Discovery without Acyclicity Constraints

We present ENCO, an efficient structure learning method that leverages observational and interventional data and scales to graphs with a thousand variables. Published at CausalUAI 2021.

Categorical Normalizing Flows via Continuous Transformations

We explore the application of normalizing flows on categorical data, and propose GraphCNF a permutation-invariant generative model on graphs. Published at ICLR 2021.

Deep Reasoning - Hardware Accelerated Artificial Intelligence

We investigate deep-learning based heuristics for first-order automated theorem provers.