arXiv subjects

Negar Kiyavash

Publications and source records attributed to Negar Kiyavash.

At least 91 records · Page 5Linked to original sources

arXiv2018

Budgeted Experiment Design for Causal Structure Learning

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 corresponding objective function is submodular and a greedy algorithm suffices to achieve $(1-\frac{1}{e})$-approximation of the optimal value. We further present an accelerated variant of the greedy algorithm, which can lead to orders of magnitude performance speedup. We validate our proposed approach on synthetic and real graphs. The results show that compared to the purely observational setting, our algorithm orients the majority of the edges through a considerably small number of interventions.

cs.LG↗

arXiv2018

Fairness in Supervised Learning: An Information Theoretic Approach

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 cultural/historical discriminatory practices against a certain demographic, the system could continue discrimination in decisions by including the said bias in its decision rule. We present an information theoretic framework for designing fair predictors from data, which aim to prevent discrimination against a specified sensitive attribute in a supervised learning setting. We use equalized odds as the criterion for discrimination, which demands that the prediction should be independent of the protected attribute conditioned on the actual label. To ensure fairness and generalization simultaneously, we compress the data to an auxiliary variable, which is used for the prediction task. This auxiliary variable is chosen such that it is decontaminated from the discriminatory attribute in the sense of equalized odds. The final predictor is obtained by applying a Bayesian decision rule to the auxiliary variable.

cs.LG↗

arXiv2018

A Covert Queueing Channel in FCFS Schedulers

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 example of such a channel is the cross-virtual network covert channel in data center networks, resulting from the queueing effects of the shared resource. First, we study a system comprising a transmitter and a receiver that share a deterministic and work-conserving FCFS scheduler, and we compute the capacity of this channel. We also consider the effect of the presence of other users on the information transmission rate of this channel. The achievable information transmission rates obtained in this study demonstrate the possibility of significant information leakage and great privacy threats brought by CQCs in FCFS schedulers.

cs.IT↗

arXiv2018

A Covert Queueing Channel in Round Robin Schedulers

We study a covert queueing channel (CQC) 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 capacity of this channel, for both noiseless and noisy setups. Our results show that seemingly isolated users can communicate with a high rate over the covert channel and demonstrate the possibility of significant information leakage and privacy threats brought by CQCs in round robin schedulers. Moreover, we propose practical finite-length code constructions, which achieve the capacity limit.

cs.IT↗

arXiv2018

Exact alignment recovery for correlated Erdős-Rényi graphs

We consider the problem of perfectly recovering the vertex correspondence between two correlated Erdős-Rényi (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 which the entire vertex correspondence can be correctly recovered given unbounded computational resources.

cs.IT↗

arXiv2018

Fundamental Limits of Database Alignment

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. Additionally, there is an efficient algorithm for database alignment that achieves this information theoretic threshold.

cs.IT↗

arXiv2018

Nonparametric Hawkes Processes: Online Estimation and Generalization Bounds

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 regularization of the objective function, nonparametric estimation faces the challenges of (i) inefficient evaluation of the gradient, (ii) lack of representer theorem, and (iii) computationally expensive projection necessary to guarantee positivity of the triggering functions. In this paper, we offer solutions to the above challenges, and design an online estimation algorithm named NPOLE-MHP that outputs estimations with a $\mathcal{O}(1/T)$ regret, and a $\mathcal{O}(1/T)$ stability. Furthermore, we design an algorithm, NPOLE-MMHP, for estimation of multivariate marked Hawkes processes. We test the performance of NPOLE-MHP on various synthetic and real datasets, and demonstrate, under different evaluation metrics, that NPOLE-MHP performs as good as the optimal maximum likelihood estimation (MLE), while having a run time as little as parametric online algorithms.

stat.ML↗

arXiv2017

Learning Vector Autoregressive Models with Latent Processes

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 concerned with identifying the influences among the observed processes, those between the latent ones, and those from the latent to the observed ones. We show that the support of transition matrix among the observed processes and lengths of all latent paths between any two observed processes can be identified successfully under some conditions on the VAR model. From the lengths of latent paths, we reconstruct the latent subgraph (representing the influences among the latent processes) with a minimum number of variables uniquely if its topology is a directed tree. Furthermore, we propose an algorithm that finds all possible minimal latent graphs under some conditions on the lengths of latent paths. Our results apply to both non-Gaussian and Gaussian cases, and experimental results on various synthetic and real-world datasets validate our theoretical results.

cs.LG↗

arXiv2017

Significance of Side Information in the Graph Matching Problem

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 two correlated graphs when an attacker has access to side information, either in the form of community labels or an imperfect initial matching. In the former case, we propose a naive graph matching algorithm by introducing the community degree vectors which harness the information from community labels in an efficient manner. Furthermore, we analyze a variant of the basic percolation algorithm proposed in literature for graphs with community structure. In the latter case, we propose a novel percolation algorithm with two thresholds which uses an imperfect matching as input to match correlated graphs. We evaluate the proposed algorithms on synthetic as well as real world datasets using various experiments. The experimental results demonstrate the importance of communities as side information especially when the number of seeds is small and the networks are weakly correlated.

cs.SI↗

arXiv2017

A New Measure of Conditional Dependence

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 dependency measure to overcome them. This measure is inspired by Dobrushin's coefficients and based on the fact that there is no dependency between $X$ and $Y$ given another variable $Z$, if and only if the conditional distribution of $Y$ given $X=x$ and $Z=z$ does not change when $X$ takes another realization $x'$ while $Z$ takes the same realization $z$. We show the advantages of this measure over the related measures in the literature. Moreover, we establish the connection between our measure and the integral probability metric (IPM) that helps to develop estimators of the measure with lower complexity compared to other relevant information theoretic based measures. Finally, we show the performance of this measure through numerical simulations.

stat.ML↗

arXiv2017

Learning Causal Structures Using Regression Invariance

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 set of environments. We define a notion of completeness for a causal inference algorithm in this setting and prove the existence of such algorithm by proposing the baseline algorithm. Additionally, we present an alternate algorithm that has significantly improved computational and sample complexity compared to the baseline algorithm. The experiment results show that the proposed algorithm outperforms the other existing algorithms.

cs.LG↗

arXiv2017

A Reconnaissance Attack Mechanism for Fixed-Priority Real-Time Systems

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-time systems designed using fixed priority scheduling algorithms. The attack is demonstrated on both a real hardware platform and a simulator, with a high success rate. Our evaluation results show that the algorithm is robust even in the presence of execution time variation.

cs.CR↗

arXiv2017

Optimal Experiment Design for Causal Discovery from Fixed Number of Experiments

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 and minimax setting. We characterize the theoretical optimal solution and propose an algorithm, which designs the experiments efficiently in terms of time complexity. We show that for bounded degree graphs, in the minimax case and in the Bayesian case with uniform priors, our proposed algorithm is a $ρ$-approximation algorithm, where $ρ$ is independent of the order of the underlying graph. Simulations on both synthetic and real data show that the performance of our algorithm is very close to the optimal solution.

cs.LG↗

arXiv2017

Interaction Information for Causal Inference: The Case of Directed Triangle

Interaction information is one of the multivariate generalizations of mutual information, which expresses the amount information shared among a set of variables, beyond the information, which is shared in any proper subset of those variables. Unlike (conditional) mutual information, which is always non-negative, interaction information can be negative. We utilize this property to find the direction of causal influences among variables in a triangle topology under some mild assumptions.

cs.AI↗

arXiv2017

Identifying Nonlinear 1-Step Causal Influences in Presence of Latent Variables

We propose an approach for learning the causal structure in stochastic dynamical systems with a $1$-step functional dependency in the presence of latent variables. We propose an information-theoretic approach that allows us to recover the causal relations among the observed variables as long as the latent variables evolve without exogenous noise. We further propose an efficient learning method based on linear regression for the special sub-case when the dynamics are restricted to be linear. We validate the performance of our approach via numerical simulations.

cs.IT↗

arXiv2016

On the Vulnerability of Digital Fingerprinting Systems to Finite Alphabet Collusion Attacks

This paper proposes a novel, non-linear collusion attack on digital fingerprinting systems. The attack is proposed for fingerprinting systems with finite alphabet but can be extended to continuous alphabet. We analyze the error probability of the attack for some classes of proposed random and deterministic schemes and obtain a bound on the number of colluders necessary to correctly estimate the host signal. That is, it requires fewer number of colluders to defeat the fingerprinting scheme. Our simulation results show that our attack is more powerful in practice than predicted by the theoretical bound.

cs.CR↗

arXiv2016

On the Simultaneous Preservation of Privacy and Community Structure in Anonymized Networks

We consider the problem of performing community detection on a network, while maintaining privacy, assuming that the adversary has access to an auxiliary correlated network. We ask the question "Does there exist a regime where the network cannot be deanonymized perfectly, yet the community structure could be learned?." To answer this question, we derive information theoretic converses for the perfect deanonymization problem using the Stochastic Block Model and edge sub-sampling. We also provide an almost tight achievability result for perfect deanonymization. We also evaluate the performance of percolation based deanonymization algorithm on Stochastic Block Model data-sets that satisfy the conditions of our converse. Although our converse applies to exact deanonymization, the algorithm fails drastically when the conditions of the converse are met. Additionally, we study the effect of edge sub-sampling on the community structure of a real world dataset. Results show that the dataset falls under the purview of the idea of this paper. There results suggest that it may be possible to prove stronger partial deanonymizability converses, which would enable better privacy guarantees.

cs.LG↗

arXiv2016

Learning Network of Multivariate Hawkes Processes: A Time Series Approach

Learning the influence structure of multiple time series data is of great interest to many disciplines. This paper studies the problem of recovering the causal structure in network of multivariate linear Hawkes processes. In such processes, the occurrence of an event in one process affects the probability of occurrence of new events in some other processes. Thus, a natural notion of causality exists between such processes captured by the support of the excitation matrix. We show that the resulting causal influence network is equivalent to the Directed Information graph (DIG) of the processes, which encodes the causal factorization of the joint distribution of the processes. Furthermore, we present an algorithm for learning the support of excitation matrix (or equivalently the DIG). The performance of the algorithm is evaluated on synthesized multivariate Hawkes networks as well as a stock market and MemeTracker real-world dataset.

cs.LG↗