Causal Bandits with General Causal Models and Interventions

This paper considers causal bandits (CBs) for the sequential design of interventions in a causal system. The objective is to optimize a reward function via minimizing a measure of cumulative regret with respect to the best sequence of interventions in hindsight. The paper advances the results on CBs in three directions. First, the structural causal models (SCMs) are assumed to be unknown and drawn arbitrarily from a general class $\mathcal{F}$ of Lipschitz-continuous functions. Existing results are often focused on (generalized) linear SCMs. Second, the interventions are assumed to be generalized soft with any desired level of granularity, resulting in an infinite number of possible interventions. The existing literature, in contrast, generally adopts atomic and hard interventions. Third, we provide general upper and lower bounds on regret. The upper bounds subsume (and improve) known bounds for special cases. The lower bounds are generally hitherto unknown. These bounds are characterized as functions of the (i) graph parameters, (ii) eluder dimension of the space of SCMs, denoted by $\operatorname{dim}(\mathcal{F})$, and (iii) the covering number of the function space, denoted by ${\rm cn}(\mathcal{F})$. Specifically, the cumulative achievable regret over horizon $T$ is $\mathcal{O}(K d^{L-1}\sqrt{T\operatorname{dim}(\mathcal{F}) \log({\rm cn}(\mathcal{F}))})$, where $K$ is related to the Lipschitz constants, $d$ is the graph's maximum in-degree, and $L$ is the length of the longest causal path. The upper bound is further refined for special classes of SCMs (neural network, polynomial, and linear), and their corresponding lower bounds are provided.

Score-based Causal Representation Learning: Linear and General Transformations

This paper addresses intervention-based causal representation learning (CRL) under a general nonparametric latent causal model and an unknown transformation that maps the latent variables to the observed variables. Linear and general transformations are investigated. The paper addresses both the \emph{identifiability} and \emph{achievability} aspects. Identifiability refers to determining algorithm-agnostic conditions that ensure recovering the true latent causal variables and the latent causal graph underlying them. Achievability refers to the algorithmic aspects and addresses designing algorithms that achieve identifiability guarantees. By drawing novel connections between \emph{score functions} (i.e., the gradients of the logarithm of density functions) and CRL, this paper designs a \emph{score-based class of algorithms} that ensures both identifiability and achievability. First, the paper focuses on \emph{linear} transformations and shows that one stochastic hard intervention per node suffices to guarantee identifiability. It also provides partial identifiability guarantees for soft interventions, including identifiability up to ancestors for general causal models and perfect latent graph recovery for sufficiently non-linear causal models. Secondly, it focuses on \emph{general} transformations and shows that two stochastic hard interventions per node suffice for identifiability. Notably, one does \emph{not} need to know which pair of interventional environments have the same node intervened.

Blackout Mitigation via Physics-guided RL

This paper considers the sequential design of remedial control actions in response to system anomalies for the ultimate objective of preventing blackouts. A physics-guided reinforcement learning (RL) framework is designed to identify effective sequences of real-time remedial look-ahead decisions accounting for the long-term impact on the system's stability. The paper considers a space of control actions that involve both discrete-valued transmission line-switching decisions (line reconnections and removals) and continuous-valued generator adjustments. To identify an effective blackout mitigation policy, a physics-guided approach is designed that uses power-flow sensitivity factors associated with the power transmission network to guide the RL exploration during agent training. Comprehensive empirical evaluations using the open-source Grid2Op platform demonstrate the notable advantages of incorporating physical signals into RL decisions, establishing the gains of the proposed physics-guided approach compared to its black box counterparts. One important observation is that strategically~\emph{removing} transmission lines, in conjunction with multiple real-time generator adjustments, often renders effective long-term decisions that are likely to prevent or delay blackouts.

Robust Causal Bandits for Linear Models

Sequential design of experiments for optimizing a reward function in causal systems can be effectively modeled by the sequential design of interventions in causal bandits (CBs). In the existing literature on CBs, a critical assumption is that the causal models remain constant over time. However, this assumption does not necessarily hold in complex systems, which constantly undergo temporal model fluctuations. This paper addresses the robustness of CBs to such model fluctuations. The focus is on causal systems with linear structural equation models (SEMs). The SEMs and the time-varying pre- and post-interventional statistical models are all unknown. Cumulative regret is adopted as the design criteria, based on which the objective is to design a sequence of interventions that incur the smallest cumulative regret with respect to an oracle aware of the entire causal model and its fluctuations. First, it is established that the existing approaches fail to maintain regret sub-linearity with even a few instances of model deviation. Specifically, when the number of instances with model deviation is as few as $T^\frac{1}{2L}$, where $T$ is the time horizon and $L$ is the longest causal path in the graph, the existing algorithms will have linear regret in $T$. Next, a robust CB algorithm is designed, and its regret is analyzed, where upper and information-theoretic lower bounds on the regret are established. Specifically, in a graph with $N$ nodes and maximum degree $d$, under a general measure of model deviation $C$, the cumulative regret is upper bounded by $\tilde{\mathcal{O}}(d^{L-\frac{1}{2}}(\sqrt{NT} + NC))$ and lower bounded by $\Omega(d^{\frac{L}{2}-2}\max\{\sqrt{T},d^2C\})$. Comparing these bounds establishes that the proposed algorithm achieves nearly optimal $\tilde{\mathcal{O}}(\sqrt{T})$ regret when $C$ is $o(\sqrt{T})$ and maintains sub-linear regret for a broader range of $C$.

General Identifiability and Achievability for Causal Representation Learning

This paper focuses on causal representation learning (CRL) under a general nonparametric causal latent model and a general transformation model that maps the latent data to the observational data. It establishes \textbf{identifiability} and \textbf{achievability} results using two hard \textbf{uncoupled} interventions per node in the latent causal graph. Notably, one does not know which pair of intervention environments have the same node intervened (hence, uncoupled environments). For identifiability, the paper establishes that perfect recovery of the latent causal model and variables is guaranteed under uncoupled interventions. For achievability, an algorithm is designed that uses observational and interventional data and recovers the latent causal model and variables with provable guarantees for the algorithm. This algorithm leverages score variations across different environments to estimate the inverse of the transformer and, subsequently, the latent variables. The analysis, additionally, recovers the existing identifiability result for two hard \textbf{coupled} interventions, that is when metadata about the pair of environments that have the same node intervened is known. It is noteworthy that the existing results on non-parametric identifiability require assumptions on interventions and additional faithfulness assumptions. This paper shows that when observational data is available, additional faithfulness assumptions are unnecessary.

Optimal Best Arm Identification with Fixed Confidence in Restless Bandits

We study best arm identification in a restless multi-armed bandit setting with finitely many arms. The discrete-time data generated by each arm forms a homogeneous Markov chain taking values in a common, finite state space. The state transitions in each arm are captured by an ergodic transition probability matrix (TPM) that is a member of a single-parameter exponential family of TPMs. The real-valued parameters of the arm TPMs are unknown and belong to a given space. Given a function $f$ defined on the common state space of the arms, the goal is to identify the best arm -- the arm with the largest average value of $f$ evaluated under the arm's stationary distribution -- with the fewest number of samples, subject to an upper bound on the decision's error probability (i.e., the fixed-confidence regime). A lower bound on the growth rate of the expected stopping time is established in the asymptote of a vanishing error probability. Furthermore, a policy for best arm identification is proposed, and its expected stopping time is proved to have an asymptotic growth rate that matches the lower bound. It is demonstrated that tracking the long-term behavior of a certain Markov decision process and its state-action visitation proportions are the key ingredients in analyzing the converse and achievability bounds. It is shown that under every policy, the state-action visitation proportions satisfy a specific approximate flow conservation constraint and that these proportions match the optimal proportions dictated by the lower bound under any asymptotically optimal policy. The prior studies on best arm identification in restless bandits focus on independent observations from the arms, rested Markov arms, and restless Markov arms with known arm TPMs. In contrast, this work is the first to study best arm identification in restless bandits with unknown arm TPMs.

Spectral Adversarial MixUp for Few-Shot Unsupervised Domain Adaptation

Domain shift is a common problem in clinical applications, where the training images (source domain) and the test images (target domain) are under different distributions. Unsupervised Domain Adaptation (UDA) techniques have been proposed to adapt models trained in the source domain to the target domain. However, those methods require a large number of images from the target domain for model training. In this paper, we propose a novel method for Few-Shot Unsupervised Domain Adaptation (FSUDA), where only a limited number of unlabeled target domain samples are available for training. To accomplish this challenging task, first, a spectral sensitivity map is introduced to characterize the generalization weaknesses of models in the frequency domain. We then developed a Sensitivity-guided Spectral Adversarial MixUp (SAMix) method to generate target-style images to effectively suppresses the model sensitivity, which leads to improved model generalizability in the target domain. We demonstrated the proposed method and rigorously evaluated its performance on multiple tasks using several public datasets.

GRNN-based Real-time Fault Chain Prediction

This paper proposes a data-driven graphical framework for the real-time search of risky cascading fault chains (FCs). While identifying risky FCs is pivotal to alleviating cascading failures, the complex spatio-temporal dependencies among the components of the power system render challenges to modeling and analyzing FCs. Furthermore, the real-time search of risky FCs faces an inherent combinatorial complexity that grows exponentially with the size of the system. The proposed framework leverages the recent advances in graph recurrent neural networks to circumvent the computational complexities of the real-time search of FCs. The search process is formalized as a partially observable Markov decision process (POMDP), which is subsequently solved via a time-varying graph recurrent neural network (GRNN) that judiciously accounts for the inherent temporal and spatial structures of the data generated by the system. The key features of this structure include (i) leveraging the spatial structure of the data induced by the system topology, (ii) leveraging the temporal structure of data induced by system dynamics, and (iii) efficiently summarizing the system's history in the latent space of the GRNN. The proposed framework's efficiency is compared to the relevant literature on the IEEE 39-bus New England system and the IEEE 118-bus system.

Score-based Causal Representation Learning with Interventions

This paper studies causal representation learning problem when the latent causal variables are observed indirectly through an unknown linear transformation. The objectives are: (i) recovering the unknown linear transformation (up to scaling and ordering), and (ii) determining the directed acyclic graph (DAG) underlying the latent variables. Since identifiable representation learning is impossible based on only observational data, this paper uses both observational and interventional data. The interventional data is generated under distinct single-node randomized hard and soft interventions. These interventions are assumed to cover all nodes in the latent space. It is established that the latent DAG structure can be recovered under soft randomized interventions via the following two steps. First, a set of transformation candidates is formed by including all inverting transformations corresponding to which the \emph{score} function of the transformed variables has the minimal number of coordinates that change between an interventional and the observational environment summed over all pairs. Subsequently, this set is distilled using a simple constraint to recover the latent DAG structure. For the special case of hard randomized interventions, with an additional hypothesis testing step, one can also uniquely recover the linear transformation, up to scaling and a valid causal ordering. These results generalize the recent results that either assume deterministic hard interventions or linear causal relationships in the latent space.

Best Arm Identification in Stochastic Bandits: Beyond $β-$optimality

This paper focuses on best arm identification (BAI) in stochastic multi-armed bandits (MABs) in the fixed-confidence, parametric setting. In such pure exploration problems, the accuracy of the sampling strategy critically hinges on the sequential allocation of the sampling resources among the arms. The existing approaches to BAI address the following question: what is an optimal sampling strategy when we spend a $\beta$ fraction of the samples on the best arm? These approaches treat $\beta$ as a tunable parameter and offer efficient algorithms that ensure optimality up to selecting $\beta$, hence $\beta-$optimality. However, the BAI decisions and performance can be highly sensitive to the choice of $\beta$. This paper provides a BAI algorithm that is agnostic to $\beta$, dispensing with the need for tuning $\beta$, and specifies an optimal allocation strategy, including the optimal value of $\beta$. Furthermore, the existing relevant literature focuses on the family of exponential distributions. This paper considers a more general setting of any arbitrary family of distributions parameterized by their mean values (under mild regularity conditions).