Negar Kiyavash

• Swiss Federal Institute of Technology in Lausanne

We study the problem of closeness testing for continuous distributions and its implications for causal discovery. Specifically, we analyze the sample complexity of distinguishing whether two multidimensional continuous distributions are identical or differ by at least $\epsilon$ in terms of Kullback-Leibler (KL) divergence under non-parametric assu...

Multi-armed bandits (MABs) are frequently used for online sequential decision-making in applications ranging from recommending personalized content to assigning treatments to patients. A recurring challenge in the applicability of the classic MAB framework to real-world settings is ignoring \textit{interference}, where a unit's outcome depends on t...

The triple difference causal inference framework is an extension of the well-known difference-in-differences framework. It relaxes the parallel trends assumption of the difference-in-differences framework through leveraging data from an auxiliary domain. Despite being commonly applied in empirical research, the triple difference framework has recei...

We introduce the problem of best arm identification (BAI) with post-action context, a new BAI problem in a stochastic multi-armed bandit environment and the fixed-confidence setting. The problem addresses the scenarios in which the learner receives a $\textit{post-action context}$ in addition to the reward after playing each action. This post-actio...

While significant progress has been made in designing algorithms that minimize regret in online decision-making, real-world scenarios often introduce additional complexities, perhaps the most challenging of which is missing outcomes. Overlooking this aspect or simply assuming random missingness invariably leads to biased estimates of the rewards an...

Causal discovery is essential for understanding relationships among variables of interest in many scientific domains. In this paper, we focus on permutation-based methods for learning causal graphs in Linear Gaussian Acyclic Models (LiGAMs), where the permutation encodes a causal ordering of the variables. Existing methods in this setting are not s...

This work investigates the performance limits of projected stochastic first-order methods for minimizing functions under the $(\alpha,\tau,\mathcal{X})$-projected-gradient-dominance property, that asserts the sub-optimality gap $F(\mathbf{x})-\min_{\mathbf{x}'\in \mathcal{X}}F(\mathbf{x}')$ is upper-bounded by $\tau\cdot\|\mathcal{G}_{\eta,\mathcal...

The presence of unobserved common causes and the presence of measurement error are two of the most limiting challenges in the task of causal structure learning. Ignoring either of the two challenges can lead to detecting spurious causal links among variables of interest. In this paper, we study the problem of causal discovery in systems where these...

The renowned difference-indifferences (DiD) estimator relies on the assumption of 'parallel trends,' which may not hold in many practical applications. To address this issue, economists are increasingly considering the triple difference estimator as a more credible alternative. Both DiD and triple difference are limited to assessing average effects...

Identifying causal effects is a key problem of interest across many disciplines. The two long-standing approaches to estimate causal effects are observational and experimental (randomized) studies. Observational studies can suffer from unmeasured confounding, which may render the causal effects unidentifiable. On the other hand, direct experiments...

We study the generic identifiability of causal effects in linear non-Gaussian acyclic models (LiNGAM) with latent variables. We consider the problem in two main settings: When the causal graph is known a priori, and when it is unknown. In both settings, we provide a complete graphical characterization of the identifiable direct or total causal effe...

The s-ID problem seeks to compute a causal effect in a specific sub-population from the observational data pertaining to the same sub population (Abouei et al., 2023). This problem has been addressed when all the variables in the system are observable. In this paper, we consider an extension of the s-ID problem that allows for the presence of laten...

Causal inference in a sub-population involves identifying the causal effect of an intervention on a specific subgroup, which is distinguished from the whole population through the influence of systematic biases in the sampling process. However, ignoring the subtleties introduced by sub-populations can either lead to erroneous inference or limit the...

We propose a nonparametric and time-varying directed information graph (TV-DIG) framework to estimate the evolving causal structure in time series networks, thereby addressing the limitations of traditional econometric models in capturing high-dimensional, nonlinear, and time-varying interconnections among series. This framework employs an informat...

We develop a data-driven framework to identify the interconnections between firms using an information-theoretic measure. This measure generalizes Granger causality and is capable of detecting nonlinear relationships within a network. Moreover, we develop an algorithm using recurrent neural networks and the aforementioned measure to identify the in...

Causal inference in a sub-population involves identifying the causal effect of an intervention on a specific subgroup within a larger population. However, ignoring the subtleties introduced by sub-populations can either lead to erroneous inference or limit the applicability of existing methods. We introduce and advocate for a causal inference probl...

Database alignment is a variant of the graph alignment problem: Given a pair of anonymized databases containing separate yet correlated features for a set of users, the problem is to identify the correspondence between the features and align the anonymized user sets based on correlation alone. This closely relates to planted matching, where given a...

We propose ordering-based approaches for learning the maximal ancestral graph (MAG) of a structural equation model (SEM) up to its Markov equivalence class (MEC) in the presence of unobserved variables. Existing ordering-based methods in the literature recover a graph through learning a causal order (c-order). We advocate for a novel order called r...

We address the problem of identifiability of an arbitrary conditional causal effect given both the causal graph and a set of any observational and/or interventional distributions of the form $Q[S]:=P(S|do(V\setminus S))$, where $V$ denotes the set of all observed variables and $S\subseteq V$. We call this problem conditional generalized identifiabi...

We consider the problem of estimating the causal effect of a treatment on an outcome in linear structural causal models (SCM) with latent confounders when we have access to a single proxy variable. Several methods (such as difference-in-difference (DiD) estimator or negative outcome control) have been proposed in this setting in the literature. How...

Drawbacks of ignoring the causal mechanisms when performing imitation learning have recently been acknowledged. Several approaches both to assess the feasibility of imitation and to circumvent causal confounding and causal misspecifications have been proposed in the literature. However, the potential benefits of the incorporation of additional info...

We study the causal bandit problem when the causal graph is unknown and develop an efficient algorithm for finding the parent node of the reward node using atomic interventions. We derive the exact equation for the expected number of interventions performed by the algorithm and show that under certain graphical conditions it could perform either lo...

Causal determinism, is deeply ingrained with our ability to understand the physical sciences and their explanatory ambitions. Besides understanding phenomena, identifying causal networks is important for effective policy design in nearly any avenue of interest, be it epidemiology, financial regulation, management of climate, etc. This special issue...

We focus on causal discovery in the presence of measurement error in linear systems where the mixing matrix, i.e., the matrix indicating the independent exogenous noise terms pertaining to the observed variables, is identified up to permutation and scaling of the columns. We demonstrate a somewhat surprising connection between this problem and caus...

We study the complexity of finding the global solution to stochastic nonconvex optimization when the objective function satisfies global Kurdyka-Lojasiewicz (KL) inequality and the queries from stochastic gradient oracles satisfy mild expected smoothness assumption. We first introduce a general framework to analyze Stochastic Gradient Descent (SGD)...

We propose ordering-based approaches for learning the maximal ancestral graph (MAG) of a structural equation model (SEM) up to its Markov equivalence class (MEC) in the presence of unobserved variables. Existing ordering-based methods in the literature recover a graph through learning a causal order (c-order). We advocate for a novel order called r...

Causal identification is at the core of the causal inference literature, where complete algorithms have been proposed to identify causal queries of interest. The validity of these algorithms hinges on the restrictive assumption of having access to a correctly specified causal structure. In this work, we study the setting where a probabilistic model...

We study the problem of learning a Bayesian network (BN) of a set of variables when structural side information about the system is available. It is well known that learning the structure of a general BN is both computationally and statistically challenging. However, often in many applications, side information about the underlying structure can po...

We revisit the problem of general identifiability originally introduced in [Lee et al., 2019] for causal inference and note that it is necessary to add positivity assumption of observational distribution to the original definition of the problem. We show that without such an assumption the rules of do-calculus and consequently the proposed algorith...

Measuring conditional dependencies among the variables of a network is of great interest to many disciplines. This paper studies some shortcomings of the existing dependency measures in detecting direct causal influences or their lack of ability for group selection to capture strong dependencies and accordingly introduces a new statistical dependen...

We study the performance of Stochastic Cubic Regularized Newton (SCRN) on a class of functions satisfying gradient dominance property which holds in a wide range of applications in machine learning and signal processing. This condition ensures that any first-order stationary point is a global optimum. We prove that SCRN improves the best-known samp...

We study experiment design for the unique identification of the causal graph of a system where the graph may contain cycles. The presence of cycles in the structure introduces major challenges for experiment design. Unlike the case of acyclic graphs, learning the skeleton of the causal graph from observational distribution may not be possible. Furt...

The variance reduced gradient estimators for policy gradient methods has been one of the main focus of research in the reinforcement learning in recent years as they allow acceleration of the estimation process. We propose a variance reduced policy gradient method, called SGDHess-PG, which incorporates second-order information into stochastic gradi...

Pearl's do calculus is a complete axiomatic approach to learn the identifiable causal effects from observational data. When such an effect is not identifiable, it is necessary to perform a collection of often costly interventions in the system to learn the causal effect. In this work, we consider the problem of designing the collection of intervent...

We study the problem of learning a Bayesian network (BN) of a set of variables when structural side information about the system is available. It is well known that learning the structure of a general BN is both computationally and statistically challenging. However, often in many applications, side information about the underlying structure can po...

Linear structural causal models (SCMs) -- in which each observed variable is generated by a subset of the other observed variables as well as a subset of the exogenous sources -- are pervasive in causal inference and casual discovery. However, for the task of causal discovery, existing work almost exclusively focus on the submodel where each observ...

We consider the problem of learning the causal MAG of a system from observational data in the presence of latent variables and selection bias. Constraint-based methods are one of the main approaches for solving this problem, but the existing methods are either computationally impractical when dealing with large graphs or lacking completeness guaran...

We study the problem of causal effect identification from observational distribution given the causal graph and some context-specific independence (CSI) relations. It was recently shown that this problem is NP-hard, and while a sound algorithm to learn the causal effects is proposed in Tikka et al. (2019), no complete algorithm for the task exists....

Machine earning algorithms are increasingly used for consequential decision making regarding individuals based on their relevant features. Features that are relevant for accurate decisions may however lead to either explicit or implicit forms of discrimination against unprivileged groups, such as those of certain race or gender. This happens due to...

This paper studies the complexity for finding approximate stationary points of nonconvex-strongly-concave (NC-SC) smooth minimax problems, in both general and averaged smooth finite-sum settings. We establish nontrivial lower complexity bounds of $\Omega(\sqrt{\kappa}\Delta L\epsilon^{-2})$ and $\Omega(n+\sqrt{n\kappa}\Delta L\epsilon^{-2})$ for th...

We study the impact of pre and post processing for reducing discrimination in data-driven decision makers. We first analyze the fundamental trade-off between fairness and accuracy in a pre-processing approach, and propose a design for a pre-processing module based on a convex optimization program, which can be added before the original classifier....

We consider a learning system based on the conventional multiplicative weight (MW) rule that combines experts’ advice to predict a sequence of true outcomes. It is assumed that one of the experts is malicious and aims to impose the maximum loss on the system. The system’s loss is naturally defined to be the aggregate absolute difference between the...

The articles in this special section focus on graph signal processing. Generically, the networks that sustain our societies can be understood as complex systems formed by multiple nodes, where global network behavior arises from local interactions between connected nodes. More succinctly, a network or a graph can be defined as a structure that enco...

One of the main approaches for causal structure learning is constraint-based methods. These methods are particularly valued as they are guaranteed to asymptotically find a structure which is statistically equivalent to the ground truth. However, they may require exponentially large number of conditional independence (CI) tests in the number of vari...

We determine information theoretic conditions under which it is possible to partially recover the alignment used to generate a pair of sparse, correlated Erdős-Rényi graphs. To prove our achievability result, we introduce the k-core alignment estimator. This estimator searches for an alignment in which the intersection of the correlated graphs usin...

The causal relationships among a set of random variables are commonly represented by a Directed Acyclic Graph (DAG), where there is a directed edge from variable $X$ to variable $Y$ if $X$ is a direct cause of $Y$. From the purely observational data, the true causal graph can be identified up to a Markov Equivalence Class (MEC), which is a set of D...

Nonconvex minimax problems appear frequently in emerging machine learning applications, such as generative adversarial networks and adversarial learning. Simple algorithms such as the gradient descent ascent (GDA) are the common practice for solving these nonconvex games and receive lots of empirical success. Yet, it is known that these vanilla GDA...

We consider a learning system based on the conventional multiplicative weight (MW) rule that combines experts' advice to predict a sequence of true outcomes. It is assumed that one of the experts is malicious and aims to impose the maximum loss on the system. The loss of the system is naturally defined to be the aggregate absolute difference betwee...

We determine information theoretic conditions under which it is possible to partially recover the alignment used to generate a pair of sparse, correlated Erdos-Renyi graphs. To prove our achievability result, we introduce the k-core alignment estimator. This estimator searches for an alignment in which the intersection of the correlated graphs usin...

Graph alignment in two correlated random graphs refers to the task of identifying the correspondence between vertex sets of the graphs. Recent results have characterized the exact informationtheoretic threshold for graph alignment in correlated Erdős-Rényi graphs. However, very little is known about the existence of efficient algorithms to achieve...

Markov blanket feature selection, while theoretically optimal, generally is challenging to implement. This is due to the shortcomings of existing approaches to conditional independence (CI) testing, which tend to struggle either with the curse of dimensionality or computational complexity. We propose a novel two-step approach which facilitates Mark...

The main way for defining equivalence among acyclic directed graphs is based on the conditional independencies of the distributions that they can generate. However, it is known that when cycles are allowed in the structure, conditional independence is not a suitable notion for equivalence of two structures, as it does not reflect all the informatio...

It is known that from purely observational data, a causal DAG is identifiable only up to its Markov equivalence class, and for many ground truth DAGs, the direction of a large portion of the edges will be remained unidentified. The golden standard for learning the causal DAG beyond Markov equivalence is to perform a sequence of interventions in the...

We consider the problem of learning causal models from observational data generated by linear non-Gaussian acyclic causal models with latent variables. Without considering the effect of latent variables, one usually infers wrong causal relationships among the observed variables. Under faithfulness assumption, we propose a method to check whether th...

A directed acyclic graph (DAG) is the most common graphical model for representing causal relationships among a set of variables. When restricted to using only observational data, the structure of the ground truth DAG is identifiable only up to Markov equivalence, based on conditional independence relations among the variables. Therefore, the numbe...

Graph alignment in two correlated random graphs refers to the task of identifying the correspondence between vertex sets of the graphs. Recent results have characterized the exact information-theoretic threshold for graph alignment in correlated Erdős-Rényi graphs. However, very little is known about the existence of efficient algorithms to achieve...

Graph alignment in two correlated random graphs refers to the task of identifying the correspondence between vertex sets of the graphs. Recent results have characterized the exact information-theoretic threshold for graph alignment in correlated Erdös-Rényi graphs. However, very little is known about the existence of efficient algorithms to achieve...

We provide an asymptotic analysis of multi-objective sequential stochastic assignment problems (MOSSAP). In MOSSAP, a fixed number of tasks arrive sequentially, with an n-dimensional value vector revealed upon arrival. Each task is assigned to one of a group of known workers immediately upon arrival, with the reward given by an n-dimensional produc...

The problem of constructing reliable systems out of unreliable components is usually dealt with through a combination of redundancy and early retirement. This article assesses the potential of an intelligent failure prediction system that depends more on diagnostic data and analytics than built-in redundancy and costly replacement.

We consider the problem of aligning a pair of databases with jointly Gaussian features. We consider two algorithms, complete database alignment via MAP estimation among all possible database alignments, and partial alignment via a thresholding approach of log likelihood ratios. We derive conditions on mutual information between feature pairs, ident...

We consider a generalized model of learning from expert advice in which experts could abstain from participating at some rounds. Our proposed online algorithm falls into the class of weighted average predictors and uses a time-varying multiplicative weight update rule. This update rule changes the weight of an expert based on his or her relative pe...

We determine information theoretic conditions under which it is possible to partially recover the alignment used to generate a pair of sparse, correlated Erd\H{o}s-R\'{e}nyi graphs. To prove our achievability result, we introduce the $k$-core alignment estimator. This estimator searches for an alignment in which the intersection of the correlated g...

This paper studies a bi-criteria multiple-choice Secretary Problem (BMSP) with full information. A sequence of candidates arrive one at a time, with a two-dimensional attribute vector revealed upon arrival. A decision maker needs to select a total number of η candidates to fill η job openings, based on the attribute vectors of candidates. The objec...

Real-time autonomous control systems are often the core of safety critical systems such as automotive systems, avionic systems, power plants and industrial control systems among others. While safety has traditionally been a focus in the design of these systems, security has often been an afterthought. In this paper we present a novel side-channel i...

Modern real-time systems (RTS) are increasingly the focus of security threats. The design of such systems often aids attackers since RTS are engineered to be predictable. This predictability can be used to mount side-channel attacks, destabilize the system (by denying access to critical resources at important times), etc. In this paper, we propose...

We consider the problem of aligning a pair of databases with correlated entries. We introduce a new measure of correlation in a joint distribution that we call cycle mutual information. This measure has operational significance: it determines whether exact recovery of the correspondence between database entries is possible for any algorithm. Additi...

We study the problem of learning the support of transition matrix between random processes in a Vector Autoregressive (VAR) model from samples when a subset of the processes are latent. It is well known that ignoring the effect of the latent processes may lead to very different estimates of the influences among observed processes, and we are concer...

Graph matching in two correlated random graphs refers to the task of identifying the correspondence between vertex sets of the graphs. Recent results have characterized the exact information-theoretic threshold for graph matching in correlated Erd\H{o}s-R\'enyi graphs. However, very little is known about the existence of efficient algorithms to ach...

A directed acyclic graph (DAG) is the most common graphical model for representing causal relationships among a set of variables. When restricted to using only observational data, the structure of the ground truth DAG is identifiable only up to Markov equivalence, based on conditional independence relations among the variables. Therefore, the numbe...

In this paper, we design a nonparametric online algorithm for estimating the triggering functions of multivariate Hawkes processes. Unlike parametric estimation, where evolutionary dynamics can be exploited for fast computation of the gradient, and unlike typical function learning, where representer theorem is readily applicable upon proper regular...

Automated decision making systems are increasingly being used in real-world applications. In these systems for the most part, the decision rules are derived by minimizing the training error on the available historical data. Therefore, if there is a bias related to a sensitive attribute such as gender, race, religion, etc. in the data, say, due to c...

We consider the problem of perfectly recovering the vertex correspondence between two correlated \ER (ER) graphs on the same vertex set. The correspondence between the vertices can be obscured by randomly permuting the vertex labels of one of the graphs. We determine the information-theoretic threshold for exact recovery, i.e. the conditions under...

We study the problem of causal structure learning when the experimenter is limited to perform at most $k$ non-adaptive experiments of size $1$. We formulate the problem of finding the best intervention target set as an optimization problem, which aims to maximize the average number of edges whose directions are resolved. We prove that the objective...

We study covert queueing channels (CQCs), which are a kind of covert timing channel that may be exploited in shared queues across supposedly isolated users. In our system model, a user modulates messages to another user via his pattern of access to the shared resource scheduled in a first-come-first-served (FCFS) manner. One example of such a chann...

We study covert queueing channels (CQCs), which are a kind of covert timing channel that may be exploited in shared queues across supposedly isolated users. In our system model, a user sends messages to another user via his pattern of access to the shared resource, which serves the users according to a first come first served (FCFS) policy. One exa...

Percolation based graph matching algorithms rely on the availability of seed vertex pairs as side information to efficiently match users across networks. Although such algorithms work well in practice, there are other types of side information available which are potentially useful to an attacker. In this paper, we consider the problem of matching...

Motivated by many real world examples such as recommendation systems or sensor fusion, and aiming to capture the influence of malicious experts who intentionally degrade the performance of learning systems, we analyze optimal adversarial strategies against the weighted average prediction algorithm in the learning with expert advice framework. All b...

We study causal inference in a multi-environment setting, in which the functional relations for producing the variables from their direct causes remain the same across environments, while the distribution of exogenous noises may vary. We introduce the idea of using the invariance of the functional relations of the variables to their causes across a...

In real-time embedded systems (RTS), failures due to security breaches can cause serious damage to the system, the environment and/or injury to humans. Therefore, it is very important to understand the potential threats and attacks against these systems. In this paper we present a novel reconnaissance attack that extracts the exact schedule of real...

Measuring the dependencies among the variables of a network is of great interest to many disciplines. This paper studies the limitations of the existing dependencies measures such as their shortcomings in detecting direct influences or their lack of ability for group selection in order to have effective interventions and introduces a new statistica...

Financial instability and its destructive effects on the economy can lead to financial crises due to its contagion or spillover effects to other parts of the economy. Having an accurate measure of systemic risk gives central banks and policy makers the ability to take proper policies in order to stabilize financial markets. Much work is currently b...

We study the problem of learning the dependency graph between random processes in a vector auto regressive (VAR) model from samples when a subset of the variables are latent. We show that the dependencies among the observed processes can be identified successfully under some conditions on the VAR model. Moreover, we can recover the length of all di...

We study the problem of causal structure learning over a set of random variables when the experimenter is allowed to perform at most $M$ experiments in a non-adaptive manner. We consider the optimal learning strategy in terms of minimizing the portions of the structure that remains unknown given the limited number of experiments in both Bayesian an...

We study a covert queueing channel between two users sharing a round robin scheduler. Such a covert channel can arise when users share a resource such as a computer processor or a router arbitrated by a round robin policy. We present an information-theoretic framework to model and derive the maximum reliable data transmission rate, i.e., the capaci...