Adversarially Robust Learning via Entropic Regularization.
Ontology highlight
ABSTRACT:
SUBMITTER: Jagatap G
PROVIDER: S-EPMC8764444 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:This paper frames causal structure estimation as a machine learning task. The idea is to treat indicators of causal relationships between variables as 'labels' and to exploit available data on the variables of interest to provide features for the labelling task. Background scientific knowledge or any available interventional data provide labels on some causal relationships and the remainder are treated as unlabelled. To illustrate the key ideas, we develop a distance-based approach (based on bivariate histograms) within a manifold regularization framework. We present empirical results on three different biological data sets (including examples where causal effects can be verified by experimental intervention), that together demonstrate the efficacy and general nature of the approach as well as its simplicity from a user's point of view.
| S-EPMC6986916 | biostudies-literature
Project description:Entropic outlier sparsification (EOS) is proposed as a cheap and robust computational strategy for learning in the presence of data anomalies and outliers. EOS dwells on the derived analytic solution of the (weighted) expected loss minimization problem subject to Shannon entropy regularization. An identified closed-form solution is proven to impose additional costs that depend linearly on statistics size and are independent of data dimension. Obtained analytic results also explain why the mixtures of spherically symmetric Gaussians-used heuristically in many popular data analysis algorithms-represent an optimal and least-biased choice for the nonparametric probability distributions when working with squared Euclidean distances. The performance of EOS is compared to a range of commonly used tools on synthetic problems and on partially mislabeled supervised classification problems from biomedicine. Applying EOS for coinference of data anomalies during learning is shown to allow reaching an accuracy of [Formula: see text] when predicting patient mortality after heart failure, statistically significantly outperforming predictive performance of common learning tools for the same data.
| S-EPMC8917346 | biostudies-literature
Project description:Reliable motion estimation and strain analysis using 3D+ time echocardiography (4DE) for localization and characterization of myocardial injury is valuable for early detection and targeted interventions. However, motion estimation is difficult due to the low-SNR that stems from the inherent image properties of 4DE, and intelligent regularization is critical for producing reliable motion estimates. In this work, we incorporated the notion of domain adaptation into a supervised neural network regularization framework. We first propose a semi-supervised Multi-Layered Perceptron (MLP) network with biomechanical constraints for learning a latent representation that is shown to have more physiologically plausible displacements. We extended this framework to include a supervised loss term on synthetic data and showed the effects of biomechanical constraints on the network's ability for domain adaptation. We validated the semi-supervised regularization method on in vivo data with implanted sonomicrometers. Finally, we showed the ability of our semi-supervised learning regularization approach to identify infarct regions using estimated regional strain maps with good agreement to manually traced infarct regions from postmortem excised hearts.
| S-EPMC8442959 | biostudies-literature
Project description:Machine learning (ML) models have demonstrated the power of utilizing clinical instruments to provide tools for domain experts in gaining additional insights toward complex clinical diagnoses. In this context these tools desire two additional properties: interpretability, being able to audit and understand the decision function, and robustness, being able to assign the correct label in spite of missing or noisy inputs. This work formulates diagnostic classification as a decision-making process and utilizes Q-learning to build classifiers that meet the aforementioned desired criteria. As an exemplary task, we simulate the process of differentiating Autism Spectrum Disorder from Attention Deficit-Hyperactivity Disorder in verbal school aged children. This application highlights how reinforcement learning frameworks can be utilized to train more robust classifiers by jointly learning to maximize diagnostic accuracy while minimizing the amount of information required.
| S-EPMC8175431 | biostudies-literature
Project description:Exploratory mediation analysis refers to a class of methods used to identify a set of potential mediators of a process of interest. Despite its exploratory nature, conventional approaches are rooted in confirmatory traditions, and as such have limitations in exploratory contexts. We propose a two-stage approach called exploratory mediation analysis via regularization (XMed) to better address these concerns. We demonstrate that this approach is able to correctly identify mediators more often than conventional approaches and that its estimates are unbiased. Finally, this approach is illustrated through an empirical example examining the relationship between college acceptance and enrollment.
| S-EPMC5720177 | biostudies-literature
Project description:Since the emergence of high-throughput genome sequencing platforms and more recently the next-generation platforms, the genome databases are growing at an astronomical rate. Tremendous efforts have been invested in recent years in understanding intriguing complexities beneath the vast ocean of genomic data. This is apparent in the spurt of computational methods for interpreting these data in the past few years. Genomic data interpretation is notoriously difficult, partly owing to the inherent heterogeneities appearing at different scales. Methods developed to interpret these data often suffer from their inability to adequately measure the underlying heterogeneities and thus lead to confounding results. Here, we present an information entropy-based approach that unravels the distinctive patterns underlying genomic data efficiently and thus is applicable in addressing a variety of biological problems. We show the robustness and consistency of the proposed methodology in addressing three different biological problems of significance--identification of alien DNAs in bacterial genomes, detection of structural variants in cancer cell lines and alignment-free genome comparison.
| S-EPMC3592408 | biostudies-literature
Project description:Learning gene expression programs directly from a set of observations is challenging due to the complexity of gene regulation, high noise of experimental measurements, and insufficient number of experimental measurements. Imposing additional constraints with strong and biologically motivated regularizations is critical in developing reliable and effective algorithms for inferring gene expression programs. Here we propose a new form of regulation that constrains the number of independent connectivity patterns between regulators and targets, motivated by the modular design of gene regulatory programs and the belief that the total number of independent regulatory modules should be small. We formulate a multi-target linear regression framework to incorporate this type of regulation, in which the number of independent connectivity patterns is expressed as the rank of the connectivity matrix between regulators and targets. We then generalize the linear framework to nonlinear cases, and prove that the generalized low-rank regularization model is still convex. Efficient algorithms are derived to solve both the linear and nonlinear low-rank regularized problems. Finally, we test the algorithms on three gene expression datasets, and show that the low-rank regularization improves the accuracy of gene expression prediction in these three datasets.
| S-EPMC3866120 | biostudies-literature
Project description:We apply the nonconcave penalized likelihood approach to obtain variable selections as well as shrinkage estimators. This approach relies heavily on the choice of regularization parameter, which controls the model complexity. In this paper, we propose employing the generalized information criterion (GIC), encompassing the commonly used Akaike information criterion (AIC) and Bayesian information criterion (BIC), for selecting the regularization parameter. Our proposal makes a connection between the classical variable selection criteria and the regularization parameter selections for the nonconcave penalized likelihood approaches. We show that the BIC-type selector enables identification of the true model consistently, and the resulting estimator possesses the oracle property in the terminology of Fan and Li (2001). In contrast, however, the AIC-type selector tends to overfit with positive probability. We further show that the AIC-type selector is asymptotically loss efficient, while the BIC-type selector is not. Our simulation results confirm these theoretical findings, and an empirical example is presented. Some technical proofs are given in the online supplementary material.
| S-EPMC2911045 | biostudies-literature
Project description:Large spatial datasets with many spatial covariates have become ubiquitous in many fields in recent years. A question of interest is to identify which covariates are likely to influence a spatial response, and whether and how the effects of these covariates vary across space, including potential abrupt changes from region to region. To solve this question, a new efficient regularized spatially clustered coefficient (RSCC) regression approach is proposed, which could achieve variable selection and identify latent spatially heterogeneous covariate effects with clustered patterns simultaneously. By carefully designing the regularization term of RSCC as a chain graph guided fusion penalty plus a group lasso penalty, the RSCC model is computationally efficient for large spatial datasets while still achieving the theoretical guarantees for estimation. RSCC also adopts the idea of adaptive learning to allow for adaptive weights and adaptive graphs in its regularization terms and further improves the estimation performance. RSCC is applied to study the acceptance of COVID-19 vaccines using county-level data in the United States and discover the determinants of vaccination acceptance with varying effects across counties, revealing important within-state and across-state spatially clustered patterns of covariates effects.
| S-EPMC9335734 | biostudies-literature
Project description:Rare-earth substituted inorganic phosphors are critical for solid state lighting. New phosphors are traditionally identified through chemical intuition or trial and error synthesis, inhibiting the discovery of potential high-performance materials. Here, we merge a support vector machine regression model to predict a phosphor host crystal structure's Debye temperature, which is a proxy for photoluminescent quantum yield, with high-throughput density functional theory calculations to evaluate the band gap. This platform allows the identification of phosphors that may have otherwise been overlooked. Among the compounds with the highest Debye temperature and largest band gap, NaBaB9O15 shows outstanding potential. Following its synthesis and structural characterization, the structural rigidity is confirmed to stem from a unique corner sharing [B3O7]5- polyanionic backbone. Substituting this material with Eu2+ yields UV excitation bands and a narrow violet emission at 416?nm with a full-width at half-maximum of 34.5?nm. More importantly, NaBaB9O15:Eu2+ possesses a quantum yield of 95% and excellent thermal stability.
| S-EPMC6197245 | biostudies-literature