BayesDAG: Gradient-Based Posterior Sampling for Causal Discovery
Dec 10, 2023
Speakers
Yashas Annadani
Speaker · 0 followers
Nick Pawlowski
Speaker · 0 followers
Joel Jennings
Speaker · 0 followers
Stefan Bauer
Speaker · 0 followers
Cheng Zhang
Speaker · 0 followers
Wenbo Gong
Speaker · 0 followers
About
Bayesian causal discovery aims to infer the posterior distribution over causal models from observed data, quantifying epistemic uncertainty and benefiting downstream tasks. However, computational challenges arise due to joint inference over combinatorial space of Directed Acyclic Graphs (DAGs) and nonlinear functions. Despite recent progress towards efficient posterior inference over DAGs, existing methods are either limited to variational inference on node permutation matrices for linear causal models, leading to compromised inference accuracy, or continuous relaxation of adjacency matrices constrained by a DAG regularizer, which cannot ensure resulting graphs are DAGs. In this work, we introduce a scalable Bayesian causal discovery framework based on stochastic gradient Markov Chain Monte Carlo (SG-MCMC) that overcomes these limitations. Our approach directly samples DAGs from the posterior without requiring any DAG regularization, simultaneously draws function parameter samples and is applicable to both linear and nonlinear causal models. To enable our approach, we derive a novel equivalence to the permutation-based DAG learning, which opens up possibilities of using any relaxed gradient estimator defined over permutations. To our knowledge, this is the first framework applying gradient-based MCMC sampling for causal discovery. Empirical evaluations on synthetic and real-world datasets demonstrate our approach's effectiveness compared to state-of-the-art baselines.Bayesian causal discovery aims to infer the posterior distribution over causal models from observed data, quantifying epistemic uncertainty and benefiting downstream tasks. However, computational challenges arise due to joint inference over combinatorial space of Directed Acyclic Graphs (DAGs) and nonlinear functions. Despite recent progress towards efficient posterior inference over DAGs, existing methods are either limited to variational inference on node permutation matrices for linear causal…
Organizer
NeurIPS 2023
Account · 648 followers
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
On the Constrained Time-Series Generation Problem
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Adversarial Examples Might be Avoidable: The Role of Data Concentration in Adversarial Robustness
Watch later
Ambar Pal, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Bandit-Driven Batch Selection for Robust Learning under Label Noise
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Generative Signed Graph Models for Gene Regulatory Networks
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Asset Bundling for Wind Power Forecasting
Watch later
Hanyu Zhang, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Multi-channel speech enhancement for moving sources
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%