Linear Causal Bandits: Unknown Graph and Soft Interventions

• URL: http://arxiv.org/abs/2411.02383v1
• Date: Mon, 04 Nov 2024 18:50:39 GMT
• Title: Linear Causal Bandits: Unknown Graph and Soft Interventions
• Authors: Zirui Yan, Ali Tajer,
• Abstract summary: designing causal bandit algorithms depends on two central categories of assumptions. The problem in its general form, i.e., unknown graph and unknown intervention models, remains open. This paper addresses this problem and establishes that in a graph with $N$ nodes, maximum in-degree $d$ and maximum causal path length $L$, after $T$ interaction rounds the regret upper bound scales.
• Score: 18.412177974475526
• License:
• Abstract: Designing causal bandit algorithms depends on two central categories of assumptions: (i) the extent of information about the underlying causal graphs and (ii) the extent of information about interventional statistical models. There have been extensive recent advances in dispensing with assumptions on either category. These include assuming known graphs but unknown interventional distributions, and the converse setting of assuming unknown graphs but access to restrictive hard/$\operatorname{do}$ interventions, which removes the stochasticity and ancestral dependencies. Nevertheless, the problem in its general form, i.e., unknown graph and unknown stochastic intervention models, remains open. This paper addresses this problem and establishes that in a graph with $N$ nodes, maximum in-degree $d$ and maximum causal path length $L$, after $T$ interaction rounds the regret upper bound scales as $\tilde{\mathcal{O}}((cd)^{L-\frac{1}{2}}\sqrt{T} + d + RN)$ where $c>1$ is a constant and $R$ is a measure of intervention power. A universal minimax lower bound is also established, which scales as $\Omega(d^{L-\frac{3}{2}}\sqrt{T})$. Importantly, the graph size $N$ has a diminishing effect on the regret as $T$ grows. These bounds have matching behavior in $T$, exponential dependence on $L$, and polynomial dependence on $d$ (with the gap $d\ $). On the algorithmic aspect, the paper presents a novel way of designing a computationally efficient CB algorithm, addressing a challenge that the existing CB algorithms using soft interventions face.

Related papers

• Improved Bound for Robust Causal Bandits with Linear Models [16.60875994745622]
  This paper investigates the robustness of causal bandits in the face of temporal model fluctuations. The proposed algorithm achieves nearly optimal $tildemathcalO(sqrtT)$ regret when $C$ is $o(sqrtT)$.
  arXiv  Detail & Related papers  (2024-05-13T14:41:28Z)
• Online Learning with Feedback Graphs: The True Shape of Regret [82.00098840619847]
  We prove that the minimax regret is proportional to $R*$ for any graph and time horizon $T$. Introducing an intricate exploration strategy, we define the mainAlgorithm algorithm that achieves the minimax optimal regret bound.
  arXiv  Detail & Related papers  (2023-06-05T15:35:00Z)
• Tight Bounds for $\gamma$-Regret via the Decision-Estimation Coefficient [88.86699022151598]
  We give a statistical characterization of the $gamma$-regret for arbitrary structured bandit problems. The $gamma$-regret emerges in structured bandit problems over a function class $mathcalF$ where finding an exact optimum of $f in mathcalF$ is intractable.
  arXiv  Detail & Related papers  (2023-03-06T17:54:33Z)
• Detection-Recovery Gap for Planted Dense Cycles [72.4451045270967]
  We consider a model where a dense cycle with expected bandwidth $n tau$ and edge density $p$ is planted in an ErdHos-R'enyi graph $G(n,q)$. We characterize the computational thresholds for the associated detection and recovery problems for the class of low-degree algorithms.
  arXiv  Detail & Related papers  (2023-02-13T22:51:07Z)
• Causal Bandits for Linear Structural Equation Models [58.2875460517691]
  This paper studies the problem of designing an optimal sequence of interventions in a causal graphical model. It is assumed that the graph's structure is known and has $N$ nodes. Two algorithms are proposed for the frequentist (UCB-based) and Bayesian settings.
  arXiv  Detail & Related papers  (2022-08-26T16:21:31Z)
• Verification and search algorithms for causal DAGs [11.038866111306728]
  We give a characterization of a minimal sized set of atomic interventions to check the correctness of a claimed causal graph. We generalize our results to the settings of bounded size interventions and node-dependent interventional costs. Our result is the first known algorithm that gives a non-trivial approximation guarantee to the verifying size on general unweighted graphs.
  arXiv  Detail & Related papers  (2022-06-30T15:52:30Z)
• Inferring Hidden Structures in Random Graphs [13.031167737538881]
  We study the two inference problems of detecting and recovering an isolated community of emphgeneral structure planted in a random graph. We derive lower bounds for detecting/recovering the structure $Gamma_k$ in terms of the parameters $(n,k,q)$, as well as certain properties of $Gamma_k$, and exhibit computationally optimal algorithms that achieve these lower bounds.
  arXiv  Detail & Related papers  (2021-10-05T09:39:51Z)
• Intervention Efficient Algorithms for Approximate Learning of Causal Graphs [22.401163479802094]
  We study the problem of learning the causal relationships between a set of observed variables in the presence of latents. Our goal is to recover the directions of all causal or ancestral relations in $G$, via a minimum cost set of interventions. Our algorithms combine work on efficient intervention design and the design of low-cost separating set systems.
  arXiv  Detail & Related papers  (2020-12-27T17:08:46Z)
• Agnostic Learning of a Single Neuron with Gradient Descent [92.7662890047311]
  We consider the problem of learning the best-fitting single neuron as measured by the expected square loss. For the ReLU activation, our population risk guarantee is $O(mathsfOPT1/2)+epsilon$. For the ReLU activation, our population risk guarantee is $O(mathsfOPT1/2)+epsilon$.
  arXiv  Detail & Related papers  (2020-05-29T07:20:35Z)
• Taking a hint: How to leverage loss predictors in contextual bandits? [63.546913998407405]
  We study learning in contextual bandits with the help of loss predictors. We show that the optimal regret is $mathcalO(minsqrtT, sqrtmathcalETfrac13)$ when $mathcalE$ is known.
  arXiv  Detail & Related papers  (2020-03-04T07:36:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.