DeepAI AI Chat
Log In Sign Up

Differentiable Multi-Target Causal Bayesian Experimental Design

by   Yashas Annadani, et al.
University of Oxford

We introduce a gradient-based approach for the problem of Bayesian optimal experimental design to learn causal models in a batch setting – a critical component for causal discovery from finite data where interventions can be costly or risky. Existing methods rely on greedy approximations to construct a batch of experiments while using black-box methods to optimize over a single target-state pair to intervene with. In this work, we completely dispose of the black-box optimization techniques and greedy heuristics and instead propose a conceptually simple end-to-end gradient-based optimization procedure to acquire a set of optimal intervention target-state pairs. Such a procedure enables parameterization of the design space to efficiently optimize over a batch of multi-target-state interventions, a setting which has hitherto not been explored due to its complexity. We demonstrate that our proposed method outperforms baselines and existing acquisition strategies in both single-target and multi-target settings across a number of synthetic datasets.


page 7

page 13


Interventions, Where and How? Experimental Design for Causal Models at Scale

Causal discovery from observational and interventional data is challengi...

Trust Your ∇: Gradient-based Intervention Targeting for Causal Discovery

Inferring causal structure from data is a challenging task of fundamenta...

Active Learning for Optimal Intervention Design in Causal Models

An important problem across disciplines is the discovery of intervention...

Differentiating the Black-Box: Optimization with Local Generative Surrogates

We propose a novel method for gradient-based optimization of black-box s...

Optimal Observation-Intervention Trade-Off in Optimisation Problems with Causal Structure

We consider the problem of optimising an expensive-to-evaluate grey-box ...