Learning Good Interventions in Causal Graphs via Covering

Sawarni, A and Madhavan, R and Sinha, G and Barman, S (2023) Learning Good Interventions in Causal Graphs via Covering. In: 39th Conference on Uncertainty in Artificial Intelligence, UAI 2023, 31 July - 4 August 2023, Pittsburgh, pp. 1827-1836.

PDF UAI_216_1827-1836_2023.pdf - Published Version Restricted to Registered users only Download (310kB) | Request a copy

Abstract

We study the causal bandit problem that entails identifying a near-optimal intervention from a specified set A of (possibly non-atomic) interventions over a given causal graph. Here, an optimal intervention in A is one that maximizes the expected value for a designated reward variable in the graph, and we use the standard notion of simple regret to quantify near optimality. Considering Bernoulli random variables and for causal graphs on N vertices with constant in-degree, prior work has achieved a worst case guarantee of Oe(N/�T) for simple regret. The current work utilizes the idea of covering interventions (which are not necessarily contained within A) and establishes a simple regret guarantee of Oe(pN/T). Notably, and in contrast to prior work, our simple regret bound depends only on explicit parameters of the problem instance. We also go beyond prior work and achieve a simple regret guarantee for causal graphs with unobserved variables. Further, we perform experiments to show improvements over baselines in this setting. © UAI 2023. All rights reserved.

Item Type:	Conference Paper
Publication:	Proceedings of Machine Learning Research
Publisher:	ML Research Press
Additional Information:	The copyright for this article belongs to the ML Research Press.
Keywords:	'current; Bandit problems; Bernoulli random variables; Causal graph; Expected values; In-Degree; Near optimality; Near-optimal; Optimal intervention; Simple++
Department/Centre:	Division of Electrical Sciences > Electrical Communication Engineering
Date Deposited:	28 Oct 2023 09:43
Last Modified:	28 Oct 2023 09:43
URI:	https://eprints.iisc.ac.in/id/eprint/83147

Actions (login required)

View Item