22 accepted papers
Causal representation learning (CRL) is the process of disentangling the *latent* low-dimensional causally-related generating factors underlying high-dimensional observable data. Extensive recent studies have characterized CRL identifiability and *perfect* recovery of the latent variables and their…
This paper introduces a general framework for risk-sensitive bandits that integrates the notions of risk-sensitive objectives by adopting a rich class of {\em distortion riskmetrics}. The introduced framework subsumes the various existing risk-sensitive models. An important and hitherto unknown obse…
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…
This paper focuses on causal representation learning (CRL) under a general nonparametric latent causal model and a general transformation model that maps the latent data to the observational data. It establishes identifiability and achievability results using two hard uncoupled interventions per nod…
Causal interactions among a group of variables are often modeled by a single causal graph. In some domains, however, these interactions are best described by multiple co-existing causal graphs, e.g., in dynamical systems or genomics. This paper addresses the hitherto unknown role of interventions in…
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 o…
Despite the multifaceted recent advances in interventional causal representation learning (CRL), they primarily focus on the stylized assumption of single-node interventions. This assumption is not valid in a wide range of applications, and generally, the subset of nodes intervened in an interventio…
Consider a data-generation process that transforms low-dimensional _latent_ causally-related variables to high-dimensional _observed_ variables. Causal representation learning (CRL) is the process of using the observed data to recover the latent causal variables and the causal structure among them.…
Domain generalization (DG) aims to train a model to perform well in unseen domains under different distributions. This paper considers a more realistic yet more challenging scenario, namely Single Domain Generalization (Single-DG), where only a single source domain is available for training. To tack…
A wide range of multi-agent decision-making problems can be abstracted as a federated multi-armed bandit (FMAB) problem. A key challenge of the FMAB problem is that the exploration-exploitation dichotomy inherited from the multi-armed bandit aspect is compounded with data heterogeneity in federated…
This paper considers the problem of estimating unknown intervention targets in causal directed acyclic graphs from observational and interventional data in the presence of latent variables. The focus is on linear structural equation models with soft interventions. The existing approaches to this pro…
The paper considers the problem of estimating a covariate parameter shared by multiple statistical models. Under the objective of estimating the parameter with target reliability with the fewest number of samples from these models, a fundamental question is how to glean samples from the statistical…
Probabilistic graphical models (PGMs) are effective for capturing the statistical dependencies in stochastic databases. In many domains (e.g., working with multimodal data), one faces multiple information layers that can be modeled by structurally similar PGMs. While learning the structures of PGMs…
This paper investigates the problem of best arm identification in {\sl contaminated} stochastic multi-arm bandits. In this setting, the rewards obtained from any arm are replaced by samples from an adversarial model with probability $\varepsilon$. A fixed confidence (infinite-horizon) setting is con…
This paper considers the problem of estimating the unknown intervention targets in a causal directed acyclic graph from observational and interventional data. The focus is on soft interventions in linear structural equation models (SEMs). Current approaches to causal structure learning either work w…
This paper formalizes a graph-constrained group testing (GT) framework for isolating up to k defective items from a population of p. In contrast to traditional group testing approaches, an underlying graphical model imposes constraints on how the items can be grouped for testing. The existing theori…
This paper considers the problem of jointly recovering the structures of two graphical models with unknown edge structures. It is assumed that both graphs have the same number of nodes and a known subset of nodes have identical structures in both graphs. The classes of Ising models and Gaussian mode…
Graphical models encode the stochastic dependencies among random variables (RVs). The vertices represent the RVs, and the edges signify the conditional dependencies among the RVs. Structure learning is the process of inferring the edges by observing realizations of the RVs, and it has applications…
This paper considers the problem of distributed state estimation in an interconnected network, in which there is uncertainty in the true model. Such uncertainties are due to the possibility of disruptions or changes in the nominal model. The focus is on the setting in which the true network model be…
This paper considers the problem of parameter estimation in a network in which the stochastic model of its measurements can change due to disruption in an unknown subset of sensors. This uncertainty in the measurements model introduces a new dimension to the estimator design. On one hand, the estima…
This paper considers a network of agents generating correlated data according to a known kernel. The correlation structure might undergo a change at an unknown time instant, where the post-change kernel is not fully known. Moreover, due to the data processing and communication costs, only a subset o…
An ordered set of data sequences is given where, broadly, the data sequences are categorized into normal and abnormal ones. The normal sequences consist of random variables generated according to a known distribution, while there exist uncertainties about the distributions of the abnormal sequences.…