Searcharxiv⌕ Search

arXiv subjects

Ioannis Ch. Paschalidis

Publications and source records attributed to Ioannis Ch. Paschalidis.

72 records · Page 4Linked to original sources
arXiv2018

Clinical Concept Extraction with Contextual Word Embedding

Automatic extraction of clinical concepts is an essential step for turning the unstructured data within a clinical note into structured and actionable information. In this work, we propose a clinical concept extraction model for automatic annotation of clinical problems, treatments, and tests in clinical notes utilizing domain-specific contextual word embedding. A contextual word embedding model is first trained on a corpus with a mixture of clinical reports and relevant Wikipedia pages in the clinical domain. Next, a bidirectional LSTM-CRF model is trained for clinical concept extraction using the contextual word embedding model. We tested our proposed model on the I2B2 2010 challenge dataset. Our proposed model achieved the best performance among reported baseline models and outperformed the state-of-the-art models by 3.4% in terms of F1-score.

cs.CL↗
arXiv2018

Learning from Past Bids to Participate Strategically in Day-Ahead Electricity Markets

We consider the process of bidding by electricity suppliers in a day-ahead market context where each supplier bids a linear non-decreasing function of her generating capacity with the goal of maximizing her individual profit given other competing suppliers' bids. Based on the submitted bids, the market operator schedules suppliers to meet demand during each hour and determines hourly market clearing prices. Eventually, this game-theoretic process reaches a Nash equilibrium when no supplier is motivated to modify her bid. However, solving the individual profit maximization problem requires information of rivals' bids, which are typically not available. To address this issue, we develop an inverse optimization approach for estimating rivals' production cost functions given historical market clearing prices and production levels. We then use these functions to bid strategically and compute Nash equilibrium bids. We present numerical experiments illustrating our methodology, showing good agreement between bids based on the estimated production cost functions with the bids based on the true cost functions. We discuss an extension of our approach that takes into account network congestion resulting in location-dependent prices.

math.OC↗
arXiv2018

A Robust Learning Algorithm for Regression Models Using Distributionally Robust Optimization under the Wasserstein Metric

We present a Distributionally Robust Optimization (DRO) approach to estimate a robustified regression plane in a linear regression setting, when the observed samples are potentially contaminated with adversarially corrupted outliers. Our approach mitigates the impact of outliers through hedging against a family of distributions on the observed data, some of which assign very low probabilities to the outliers. The set of distributions under consideration are close to the empirical distribution in the sense of the Wasserstein metric. We show that this DRO formulation can be relaxed to a convex optimization problem which encompasses a class of models. By selecting proper norm spaces for the Wasserstein metric, we are able to recover several commonly used regularized regression models. We provide new insights into the regularization term and give guidance on the selection of the regularization coefficient from the standpoint of a confidence region. We establish two types of performance guarantees for the solution to our formulation under mild conditions. One is related to its out-of-sample behavior (prediction bias), and the other concerns the discrepancy between the estimated and true regression planes (estimation bias). Extensive numerical results demonstrate the superiority of our approach to a host of regression models, in terms of the prediction and estimation accuracies. We also consider the application of our robust learning procedure to outlier detection, and show that our approach achieves a much higher AUC (Area Under the ROC Curve) than M-estimation.

stat.ML↗
arXiv2018

The Price of Anarchy in Transportation Networks: Data-Driven Evaluation and Reduction Strategies

Among the many functions a Smart City must support, transportation dominates in terms of resource consumption, strain on the environment, and frustration of its citizens. We study transportation networks under two different routing policies, the commonly assumed selfish user-centric routing policy and a socially-optimal system-centric one. We consider a performance metric of efficiency - the Price of Anarchy (PoA) - defined as the ratio of the total travel latency cost under selfish routing over the corresponding quantity under socially-optimal routing. We develop a data-driven approach to estimate the PoA, which we subsequently use to conduct a case study using extensive actual traffic data from the Eastern Massachusetts road network. To estimate the PoA, our approach learns from data a complete model of the transportation network, including origin-destination demand and user preferences. We leverage this model to propose possible strategies to reduce the PoA and increase efficiency.

math.OC↗
arXiv2018

Predicting Chronic Disease Hospitalizations from Electronic Health Records: An Interpretable Classification Approach

Urban living in modern large cities has significant adverse effects on health, increasing the risk of several chronic diseases. We focus on the two leading clusters of chronic disease, heart disease and diabetes, and develop data-driven methods to predict hospitalizations due to these conditions. We base these predictions on the patients' medical history, recent and more distant, as described in their Electronic Health Records (EHR). We formulate the prediction problem as a binary classification problem and consider a variety of machine learning methods, including kernelized and sparse Support Vector Machines (SVM), sparse logistic regression, and random forests. To strike a balance between accuracy and interpretability of the prediction, which is important in a medical setting, we propose two novel methods: K-LRT, a likelihood ratio test-based method, and a Joint Clustering and Classification (JCC) method which identifies hidden patient clusters and adapts classifiers to each cluster. We develop theoretical out-of-sample guarantees for the latter method. We validate our algorithms on large datasets from the Boston Medical Center, the largest safety-net hospital system in New England.

cs.LG↗
arXiv2017

Statistical Anomaly Detection via Composite Hypothesis Testing for Markov Models

Under Markovian assumptions, we leverage a Central Limit Theorem (CLT) for the empirical measure in the test statistic of the composite hypothesis Hoeffding test so as to establish weak convergence results for the test statistic, and, thereby, derive a new estimator for the threshold needed by the test. We first show the advantages of our estimator over an existing estimator by conducting extensive numerical experiments. We find that our estimator controls better for false alarms while maintaining satisfactory detection probabilities. We then apply the Hoeffding test with our threshold estimator to detecting anomalies in two distinct applications domains: one in communication networks and the other in transportation networks. The former application seeks to enhance cyber security and the latter aims at building smarter transportation systems in cities.

eess.SY↗
arXiv2017

Data-Driven Estimation of Travel Latency Cost Functions via Inverse Optimization in Multi-Class Transportation Networks

We develop a method to estimate from data travel latency cost functions in multi-class transportation networks, which accommodate different types of vehicles with very different characteristics (e.g., cars and trucks). Leveraging our earlier work on inverse variational inequalities, we develop a data-driven approach to estimate the travel latency cost functions. Extensive numerical experiments using benchmark networks, ranging from moderate-sized to large-sized, demonstrate the effectiveness and efficiency of our approach.

eess.SY↗
arXiv2017

Learning Policies for Markov Decision Processes from Data

We consider the problem of learning a policy for a Markov decision process consistent with data captured on the state-actions pairs followed by the policy. We assume that the policy belongs to a class of parameterized policies which are defined using features associated with the state-action pairs. The features are known a priori, however, only an unknown subset of them could be relevant. The policy parameters that correspond to an observed target policy are recovered using $\ell_1$-regularized logistic regression that best fits the observed state-action samples. We establish bounds on the difference between the average reward of the estimated and the original policy (regret) in terms of the generalization error and the ergodic coefficient of the underlying Markov chain. To that end, we combine sample complexity theory and sensitivity analysis of the stationary distribution of Markov chains. Our analysis suggests that to achieve regret within order $O(\sqrtε)$, it suffices to use training sample size on the order of $Ω(\log n \cdot poly(1/ε))$, where $n$ is the number of the features. We demonstrate the effectiveness of our method on a synthetic robot navigation example.

math.OC↗
arXiv2016

Data-driven Estimation of Origin-Destination Demand and User Cost Functions for the Optimization of Transportation Networks

In earlier work (Zhang et al., 2016) we used actual traffic data from the Eastern Massachusetts transportation network in the form of spatial average speeds and road segment flow capacities in order to estimate Origin-Destination (OD) flow demand matrices for the network. Based on a Traffic Assignment Problem (TAP) formulation (termed "forward problem"), in this paper we use a scheme similar to our earlier work to estimate initial OD demand matrices and then propose a new inverse problem formulation in order to estimate user cost functions. This new formulation allows us to efficiently overcome numerical difficulties that limited our prior work to relatively small subnetworks and, assuming the travel latency cost functions are available, to adjust the values of the OD demands accordingly so that the flow observations are as close as possible to the solutions of the forward problem. We also derive sensitivity analysis results for the total user latency cost with respect to important parameters such as road capacities and minimum travel times. Finally, using the same actual traffic data from the Eastern Massachusetts transportation network, we quantify the Price of Anarchy (POA) for a much larger network than that in Zhang et al. (2016).

eess.SY↗
arXiv2016

An Improved Composite Hypothesis Test for Markov Models with Applications in Network Anomaly Detection

Recent work has proposed the use of a composite hypothesis Hoeffding test for statistical anomaly detection. Setting an appropriate threshold for the test given a desired false alarm probability involves approximating the false alarm probability. To that end, a large deviations asymptotic is typically used which, however, often results in an inaccurate setting of the threshold, especially for relatively small sample sizes. This, in turn, results in an anomaly detection test that does not control well for false alarms. In this paper, we develop a tighter approximation using the Central Limit Theorem (CLT) under Markovian assumptions. We apply our result to a network anomaly detection application and demonstrate its advantages over earlier work.

cs.IT↗
arXiv2016

Robust measurement-based buffer overflow probability estimators for QoS provisioning and traffic anomaly prediction applicationm

Suitable estimators for a class of Large Deviation approximations of rare event probabilities based on sample realizations of random processes have been proposed in our earlier work. These estimators are expressed as non-linear multi-dimensional optimization problems of a special structure. In this paper, we develop an algorithm to solve these optimization problems very efficiently based on their characteristic structure. After discussing the nature of the objective function and constraint set and their peculiarities, we provide a formal proof that the developed algorithm is guaranteed to always converge. The existence of efficient and provably convergent algorithms for solving these problems is a prerequisite for using the proposed estimators in real time problems such as call admission control, adaptive modulation and coding with QoS constraints, and traffic anomaly detection in high data rate communication networks.

cs.IT↗
arXiv2015

Robust Anomaly Detection in Dynamic Networks

We propose two robust methods for anomaly detection in dynamic networks in which the properties of normal traffic are time-varying. We formulate the robust anomaly detection problem as a binary composite hypothesis testing problem and propose two methods: a model-free and a model-based one, leveraging techniques from the theory of large deviations. Both methods require a family of Probability Laws (PLs) that represent normal properties of traffic. We devise a two-step procedure to estimate this family of PLs. We compare the performance of our robust methods and their vanilla counterparts, which assume that normal traffic is stationary, on a network with a diurnal normal pattern and a common anomaly related to data exfiltration. Simulation results show that our robust methods perform better than their vanilla counterparts in dynamic networks.

cs.NI↗
arXiv2015

Botnet Detection using Social Graph Analysis

Signature-based botnet detection methods identify botnets by recognizing Command and Control (C\&C) traffic and can be ineffective for botnets that use new and sophisticate mechanisms for such communications. To address these limitations, we propose a novel botnet detection method that analyzes the social relationships among nodes. The method consists of two stages: (i) anomaly detection in an "interaction" graph among nodes using large deviations results on the degree distribution, and (ii) community detection in a social "correlation" graph whose edges connect nodes with highly correlated communications. The latter stage uses a refined modularity measure and formulates the problem as a non-convex optimization problem for which appropriate relaxation strategies are developed. We apply our method to real-world botnet traffic and compare its performance with other community detection methods. The results show that our approach works effectively and the refined modularity measure improves the detection accuracy.

cs.SI↗
arXiv2014

Data-Driven Estimation in Equilibrium Using Inverse Optimization

Equilibrium modeling is common in a variety of fields such as game theory and transportation science. The inputs for these models, however, are often difficult to estimate, while their outputs, i.e., the equilibria they are meant to describe, are often directly observable. By combining ideas from inverse optimization with the theory of variational inequalities, we develop an efficient, data-driven technique for estimating the parameters of these models from observed equilibria. We use this technique to estimate the utility functions of players in a game from their observed actions and to estimate the congestion function on a road network from traffic count data. A distinguishing feature of our approach is that it supports both parametric and \emph{nonparametric} estimation by leveraging ideas from statistical learning (kernel methods and regularization operators). In computational experiments involving Nash and Wardrop equilibria in a nonparametric setting, we find that a) we effectively estimate the unknown demand or congestion function, respectively, and b) our proposed regularization technique substantially improves the out-of-sample performance of our estimators.

math.OC↗
arXiv2013

Network Anomaly Detection: A Survey and Comparative Analysis of Stochastic and Deterministic Methods

We present five methods to the problem of network anomaly detection. These methods cover most of the common techniques in the anomaly detection field, including Statistical Hypothesis Tests (SHT), Support Vector Machines (SVM) and clustering analysis. We evaluate all methods in a simulated network that consists of nominal data, three flow-level anomalies and one packet-level attack. Through analyzing the results, we point out the advantages and disadvantages of each method and conclude that combining the results of the individual methods can yield improved anomaly detection results.

stat.ML↗
arXiv2012

Temporal Logic Motion Control using Actor-Critic Methods

In this paper, we consider the problem of deploying a robot from a specification given as a temporal logic statement about some properties satisfied by the regions of a large, partitioned environment. We assume that the robot has noisy sensors and actuators and model its motion through the regions of the environment as a Markov Decision Process (MDP). The robot control problem becomes finding the control policy maximizing the probability of satisfying the temporal logic task on the MDP. For a large environment, obtaining transition probabilities for each state-action pair, as well as solving the necessary optimization problem for the optimal policy are usually not computationally feasible. To address these issues, we propose an approximate dynamic programming framework based on a least-square temporal difference learning method of the actor-critic type. This framework operates on sample paths of the robot and optimizes a randomized control policy with respect to a small set of parameters. The transition probabilities are obtained only when needed. Hardware-in-the-loop simulations confirm that convergence of the parameters translates to an approximately optimal policy.

cs.RO↗
arXiv2011

Least Squares Temporal Difference Actor-Critic Methods with Applications to Robot Motion Control

We consider the problem of finding a control policy for a Markov Decision Process (MDP) to maximize the probability of reaching some states while avoiding some other states. This problem is motivated by applications in robotics, where such problems naturally arise when probabilistic models of robot motion are required to satisfy temporal logic task specifications. We transform this problem into a Stochastic Shortest Path (SSP) problem and develop a new approximate dynamic programming algorithm to solve it. This algorithm is of the actor-critic type and uses a least-square temporal difference learning method. It operates on sample paths of the system and optimizes the policy within a pre-specified class parameterized by a parsimonious set of parameters. We show its convergence to a policy corresponding to a stationary point in the parameters' space. Simulation results confirm the effectiveness of the proposed solution.

cs.RO↗