Search

Any supervised machine learning analysis is required to provide an estimate of the out-of-sample predictive performance. However, it is imperative to also provide a quantification of the uncertainty of this performance in the form of a confidence or credible interval (CI) and not just a point estimate. In an AutoML setting, estimating the CI is challenging due to the ``winner's curse", i.e., the bias of estimation due to cross-validating several machine learning pipelines and selecting the winning one. In this work, we perform a comparative evaluation of 9 state-of-the-art methods and variants in CI estimation in an AutoML setting on a corpus of real and simulated datasets. The methods are compared in terms of inclusion percentage (does a 95\% CI include the true performance at least 95\% of the time), CI tightness (tighter CIs are preferable as being more informative), and execution time. The evaluation is the first one that covers most, if not all, such methods and extends previous work to imbalanced and small-sample tasks. In addition, we present a variant, called BBC-F, of an existing method (the Bootstrap Bias Correction, or BBC) that maintains the statistical properties of the BBC but is more computationally efficient. The results support that BBC-F and BBC dominate the other methods in all metrics measured., Comment: Accepted at AutoML 2024 conference

We introduce the concept of Automated Causal Discovery (AutoCD), defined as any system that aims to fully automate the application of causal discovery and causal reasoning methods. AutoCD's goal is to deliver all causal information that an expert human analyst would and answer a user's causal queries. We describe the architecture of such a platform, and illustrate its performance on synthetic data sets. As a case study, we apply it on temporal telecommunication data. The system is general and can be applied to a plethora of causal discovery problems., Comment: 14 pages, 9 figures

AutoML platforms have numerous options for the algorithms to try for each step of the analysis, i.e., different possible algorithms for imputation, transformations, feature selection, and modelling. Finding the optimal combination of algorithms and hyper-parameter values is computationally expensive, as the number of combinations to explore leads to an exponential explosion of the space. In this paper, we present the Sequential Hyper-parameter Space Reduction (SHSR) algorithm that reduces the space for an AutoML tool with negligible drop in its predictive performance. SHSR is a meta-level learning algorithm that analyzes past runs of an AutoML tool on several datasets and learns which hyper-parameter values to filter out from consideration on a new dataset to analyze. SHSR is evaluated on 284 classification and 375 regression problems, showing an approximate 30% reduction in execution time with a performance drop of less than 0.1%.

Real-time detection of anomalies in streaming data is receiving increasing attention as it allows us to raise alerts, predict faults, and detect intrusions or threats across industries. Yet, little attention has been given to compare the effectiveness and efficiency of anomaly detectors for streaming data (i.e., of online algorithms). In this paper, we present a qualitative, synthetic overview of major online detectors from different algorithmic families (i.e., distance, density, tree or projection-based) and highlight their main ideas for constructing, updating and testing detection models. Then, we provide a thorough analysis of the results of a quantitative experimental evaluation of online detection algorithms along with their offline counterparts. The behavior of the detectors is correlated with the characteristics of different datasets (i.e., meta-features), thereby providing a meta-level analysis of their performance. Our study addresses several missing insights from the literature such as (a) how reliable are detectors against a random classifier and what dataset characteristics make them perform randomly; (b) to what extent online detectors approximate the performance of offline counterparts; (c) which sketch strategy and update primitives of detectors are best to detect anomalies visible only within a feature subspace of a dataset; (d) what are the tradeoffs between the effectiveness and the efficiency of detectors belonging to different algorithmic families; (e) which specific characteristics of datasets yield an online algorithm to outperform all others.

Numerous algorithms have been proposed for detecting anomalies (outliers, novelties) in an unsupervised manner. Unfortunately, it is not trivial, in general, to understand why a given sample (record) is labelled as an anomaly and thus diagnose its root causes. We propose the following reduced-dimensionality, surrogate model approach to explain detector decisions: approximate the detection model with another one that employs only a small subset of features. Subsequently, samples can be visualized in this low-dimensionality space for human understanding. To this end, we develop PROTEUS, an AutoML pipeline to produce the surrogate model, specifically designed for feature selection on imbalanced datasets. The PROTEUS surrogate model can not only explain the training data, but also the out-of-sample (unseen) data. In other words, PROTEUS produces predictive explanations by approximating the decision surface of an unsupervised detector. PROTEUS is designed to return an accurate estimate of out-of-sample predictive performance to serve as a metric of the quality of the approximation. Computational experiments confirm the efficacy of PROTEUS to produce predictive explanations for different families of detectors and to reliably estimate their predictive performance in unseen data. Unlike several ad-hoc feature importance methods, PROTEUS is robust to high-dimensional data., Comment: 12 pages

Inferring the driving equations of a dynamical system from population or time-course data is important in several scientific fields such as biochemistry, epidemiology, financial mathematics and many others. Despite the existence of algorithms that learn the dynamics from trajectorial measurements there are few attempts to infer the dynamical system straight from population data. In this work, we deduce and then computationally estimate the Fokker-Planck equation which describes the evolution of the population's probability density, based on stochastic differential equations. Then, following the USDL approach, we project the Fokker-Planck equation to a proper set of test functions, transforming it into a linear system of equations. Finally, we apply sparse inference methods to solve the latter system and thus induce the driving forces of the dynamical system. Our approach is illustrated in both synthetic and real data including non-linear, multimodal stochastic differential equations, biochemical reaction networks as well as mass cytometry biological measurements.

Feature selection for predictive analytics is the problem of identifying a minimal-size subset of features that is maximally predictive of an outcome of interest. To apply to molecular data, feature selection algorithms need to be scalable to tens of thousands of available features. In this paper, we propose gOMP, a highly-scalable generalisation of the Orthogonal Matching Pursuit feature selection algorithm to several directions: (a) different types of outcomes, such as continuous, binary, nominal, and time-to-event, (b) different types of predictive models (e.g., linear least squares, logistic regression), (c) different types of predictive features (continuous, categorical), and (d) different, statistical-based stopping criteria. We compare the proposed algorithm against LASSO, a prototypical, widely used algorithm for high-dimensional data. On dozens of simulated datasets, as well as, real gene expression datasets, gOMP is on par, or outperforms LASSO for case-control binary classification, quantified outcomes (regression), and (censored) survival times (time-to-event) analysis. gOMP has also several theoretical advantages that are discussed. While gOMP is based on quite simple and basic statistical ideas, easy to implement and to generalize, we also show in an extensive evaluation that it is also quite effective in bioinformatics analysis settings.

Feature selection is an important problem studied in data analytics seeking to identify a minimal-size feature subset that is optimally predictive for an outcome of interest. It is also a powerful tool in Knowledge Discovery as a means for gaining domain insight, e.g., identifying which medical quantities carry unique information for the disease status. It is arguably less recognized however, that the problem may have multiple, equivalent solutions. In that case, it is misleading to domain experts to report only one of them and ignore all other equivalent solutions. In this paper, we extend a well-established single, feature selection algorithm (i.e., reporting a single solution), namely the Lasso algorithm, to the multiple solution problem based on formalized notion of equivalence for both classification and regression tasks. Empirical results are obtained using a fully automated pipeline called Just Add Data Bio or JAD Bio training and selecting multiple, linear as well as nonlinear learners, optimizing hyper-parameter values, and correcting for the bias of multiple inductions (model selection). The results show that multiple solutions do exist in real datasets, as well as the ability of the algorithm to identify a subset of them. A comparison with the Statistical Equivalent Solutions (SES) algorithm shows that Lasso equivalent solutions have better prediction performance at the cost of selecting more features., Comment: 10 pages, 2 figures, 3 tables

Temporal variations in biological systems and more generally in natural sciences are typically modelled as a set of Ordinary, Partial, or Stochastic Differential or Difference Equations. Algorithms for learning the structure and the parameters of a dynamical system are distinguished based on whether time is discrete or continuous, observations are time-series or time-course, and whether the system is deterministic or stochastic, however, there is no approach able to handle the various types of dynamical systems simultaneously. In this paper, we present a unified approach to infer both the structure and the parameters of nonlinear dynamical systems of any type under the restriction of being linear with respect to the unknown parameters. Our approach, which is named Unified Sparse Dynamics Learning (USDL), constitutes of two steps. First, an atemporal system of equations is derived through the application of the weak formulation. Then, assuming a sparse representation for the dynamical system, we show that the inference problem can be expressed as a sparse signal recovery problem, allowing the application of an extensive body of algorithms and theoretical results. Results on simulated data demonstrate the efficacy and superiority of the USDL algorithm as a function of the experimental setup (sample size, number of time measurements, number of interventions, noise level). Additionally, USDL's accuracy significantly correlates with theoretical metrics such as the exact recovery coefficient. On real single-cell data, the proposed approach is able to induce high-confidence subgraphs of the signaling pathway. USDL algorithm has been integrated in SCENERY (\url{http://scenery.csd.uoc.gr/}); an online tool for single-cell mass cytometry analytics., Comment: 13 pages, 3 figures

Cross-Validation (CV), and out-of-sample performance-estimation protocols in general, are often employed both for (a) selecting the optimal combination of algorithms and values of hyper-parameters (called a configuration) for producing the final predictive model, and (b) estimating the predictive performance of the final model. However, the cross-validated performance of the best configuration is optimistically biased. We present an efficient bootstrap method that corrects for the bias, called Bootstrap Bias Corrected CV (BBC-CV). BBC-CV's main idea is to bootstrap the whole process of selecting the best-performing configuration on the out-of-sample predictions of each configuration, without additional training of models. In comparison to the alternatives, namely the nested cross-validation and a method by Tibshirani and Tibshirani, BBC-CV is computationally more efficient, has smaller variance and bias, and is applicable to any metric of performance (accuracy, AUC, concordance index, mean squared error). Subsequently, we employ again the idea of bootstrapping the out-of-sample predictions to speed up the CV process. Specifically, using a bootstrap-based hypothesis test we stop training of models on new folds of statistically-significantly inferior configurations. We name the method Bootstrap Corrected with Early Dropping CV (BCED-CV) that is both efficient and provides accurate performance estimates., Comment: Added acknowledgments

We present the Parallel, Forward-Backward with Pruning (PFBP) algorithm for feature selection (FS) in Big Data settings (high dimensionality and/or sample size). To tackle the challenges of Big Data FS PFBP partitions the data matrix both in terms of rows (samples, training examples) as well as columns (features). By employing the concepts of $p$-values of conditional independence tests and meta-analysis techniques PFBP manages to rely only on computations local to a partition while minimizing communication costs. Then, it employs powerful and safe (asymptotically sound) heuristics to make early, approximate decisions, such as Early Dropping of features from consideration in subsequent iterations, Early Stopping of consideration of features within the same iteration, or Early Return of the winner in each iteration. PFBP provides asymptotic guarantees of optimality for data distributions faithfully representable by a causal network (Bayesian network or maximal ancestral graph). Our empirical analysis confirms a super-linear speedup of the algorithm with increasing sample size, linear scalability with respect to the number of features and processing cores, while dominating other competitive algorithms in its class.

Forward-backward selection is one of the most basic and commonly-used feature selection algorithms available. It is also general and conceptually applicable to many different types of data. In this paper, we propose a heuristic that significantly improves its running time, while preserving predictive accuracy. The idea is to temporarily discard the variables that are conditionally independent with the outcome given the selected variable set. Depending on how those variables are reconsidered and reintroduced, this heuristic gives rise to a family of algorithms with increasingly stronger theoretical guarantees. In distributions that can be faithfully represented by Bayesian networks or maximal ancestral graphs, members of this algorithmic family are able to correctly identify the Markov blanket in the sample limit. In experiments we show that the proposed heuristic increases computational efficiency by about two orders of magnitude in high-dimensional problems, while selecting fewer variables and retaining predictive performance. Furthermore, we show that the proposed algorithm and feature selection with LASSO perform similarly when restricted to select the same number of variables, making the proposed algorithm an attractive alternative for problems where no (efficient) algorithm for LASSO exists.

The statistically equivalent signature (SES) algorithm is a method for feature selection inspired by the principles of constrained-based learning of Bayesian Networks. Most of the currently available feature-selection methods return only a single subset of features, supposedly the one with the highest predictive power. We argue that in several domains multiple subsets can achieve close to maximal predictive accuracy, and that arbitrarily providing only one has several drawbacks. The SES method attempts to identify multiple, predictive feature subsets whose performances are statistically equivalent. Under that respect SES subsumes and extends previous feature selection algorithms, like the max-min parent children algorithm. SES is implemented in an homonym function included in the R package MXM, standing for mens ex machina, meaning 'mind from the machine' in Latin. The MXM implementation of SES handles several data-analysis tasks, namely classification, regression and survival analysis. In this paper we present the SES algorithm, its implementation, and provide examples of use of the SES function in R. Furthermore, we analyze three publicly available data sets to illustrate the equivalence of the signatures retrieved by SES and to contrast SES against the state-of-the-art feature selection method LASSO. Our results provide initial evidence that the two methods perform comparably well in terms of predictive accuracy and that multiple, equally predictive signatures are actually present in real world data., Comment: Accepted for publication in Journal of Statistical Software

A significant theoretical advantage of search-and-score methods for learning Bayesian Networks is that they can accept informative prior beliefs for each possible network, thus complementing the data. In this paper, a method is presented for assigning priors based on beliefs on the presence or absence of certain paths in the true network. Such beliefs correspond to knowledge about the possible causal and associative relations between pairs of variables. This type of knowledge naturally arises from prior experimental and observational data, among others. In addition, a novel search-operator is proposed to take advantage of such prior knowledge. Experiments show that, using path beliefs improves the learning of the skeleton, as well as the edge directions in the network., Comment: Appears in Proceedings of the Twenty-Ninth Conference on Uncertainty in Artificial Intelligence (UAI2013)

This work presents a sound probabilistic method for enforcing adherence of the marginal probabilities of a multi-label model to automatically discovered deterministic relationships among labels. In particular we focus on discovering two kinds of relationships among the labels. The first one concerns pairwise positive entailement: pairs of labels, where the presence of one implies the presence of the other in all instances of a dataset. The second concerns exclusion: sets of labels that do not coexist in the same instances of the dataset. These relationships are represented with a Bayesian network. Marginal probabilities are entered as soft evidence in the network and adjusted through probabilistic inference. Our approach offers robust improvements in mean average precision compared to the standard binary relavance approach across all 12 datasets involved in our experiments. The discovery process helps interesting implicit knowledge to emerge, which could be useful in itself.

Scientific practice typically involves repeatedly studying a system, each time trying to unravel a different perspective. In each study, the scientist may take measurements under different experimental conditions (interventions, manipulations, perturbations) and measure different sets of quantities (variables). The result is a collection of heterogeneous data sets coming from different data distributions. In this work, we present algorithm COmbINE, which accepts a collection of data sets over overlapping variable sets under different experimental conditions; COmbINE then outputs a summary of all causal models indicating the invariant and variant structural characteristics of all models that simultaneously fit all of the input data sets. COmbINE converts estimated dependencies and independencies in the data into path constraints on the data-generating causal model and encodes them as a SAT instance. The algorithm is sound and complete in the sample limit. To account for conflicting constraints arising from statistical errors, we introduce a general method for sorting constraints in order of confidence, computed as a function of their corresponding p-values. In our empirical evaluation, COmbINE outperforms in terms of efficiency the only pre-existing similar algorithm; the latter additionally admits feedback cycles, but does not admit conflicting constraints which hinders the applicability on real data. As a proof-of-concept, COmbINE is employed to co-analyze 4 real, mass-cytometry data sets measuring phosphorylated protein concentrations of overlapping protein sets under 3 different interventions.

A significant theoretical advantage of search-and-score methods for learning Bayesian Networks is that they can accept informative prior beliefs for each possible network, thus complementing the data. In this paper, a method is presented for assigning priors based on beliefs on the presence or absence of certain paths in the true network. Such beliefs correspond to knowledge about the possible causal and associative relations between pairs of variables. This type of knowledge naturally arises from prior experimental and observational data, among others. In addition, a novel search-operator is proposed to take advantage of such prior knowledge. Experiments show that, using path beliefs improves the learning of the skeleton, as well as the edge directions in the network., Comment: Accepted for publication to the 29th Conference on Uncertainty in Artificial Intelligence (UAI-2013). The content of the paper is identical to the published one, but the compiler at arXiv produces a 11 page long paper, whereas the compiler we used produces a 10 page long paper (page limit for the conference)

We consider the incorporation of causal knowledge about the presence or absence of (possibly indirect) causal relations into a causal model. Such causal relations correspond to directed paths in a causal model. This type of knowledge naturally arises from experimental data, among others. Specifically, we consider the formalisms of Causal Bayesian Networks and Maximal Ancestral Graphs and their Markov equivalence classes: Partially Directed Acyclic Graphs and Partially Oriented Ancestral Graphs. We introduce sound and complete procedures which are able to incorporate causal prior knowledge in such models. In simulated experiments, we show that often considering even a few causal facts leads to a significant number of new inferences. In a case study, we also show how to use real experimental data to infer causal knowledge and incorporate it into a real biological causal network. The code is available at mensxmachina.org., Comment: Appears in Proceedings of the 29th International Conference on Machine Learning (ICML 2012)