This paper analyzes $\ell_1$ regularized linear regression under the challenging scenario of having only adversarially corrupted data for training. We use the primal-dual witness paradigm to provide provable performance guarantees for the support of the estimated regression parameter vector to match the actual parameter. Our theoretical analysis shows the counter-intuitive result that an adversary can influence sample complexity by corrupting the irrelevant features, i.e., those corresponding to zero coefficients of the regression parameter vector, which, consequently, do not affect the dependent variable. As any adversarially robust algorithm has its limitations, our theoretical analysis identifies the regimes under which the learning algorithm and adversary can dominate over each other. It helps us to analyze these fundamental limits and address critical scientific questions of which parameters (like mutual incoherence, the maximum and minimum eigenvalue of the covariance matrix, and the budget of adversarial perturbation) play a role in the high or low probability of success of the LASSO algorithm. Also, the derived sample complexity is logarithmic with respect to the size of the regression parameter vector, and our theoretical claims are validated by empirical analysis on synthetic and real-world datasets.

The goal of co-clustering is to jointly perform a clustering of rows and a clustering of columns of a data table. Proposed by [Good, 1965] then by [Hartigan, 1975], co-clustering is an extension of the standard clustering that extracts the underlying structure in the data in the form of clusters of row and clusters of columns. The advantage of this technique, over the standard clustering, lies in the joint (simultaneous) analysis of the rows and columns which enables extracting the maximum of information about the interdependence between the two entities. The utility of co-clustering lies in its capacity to create easily interpretable clusters and its capability to reduce a large data table into a significantly smaller matrix having the same structure as the orig-Aichetou Bouchareb, Marc Boullé and Fabrice Clérot: Orange Labs, 2 Avenue Pierre Marzin 22300 Lannion - France, e-mail: firstname.

Probabilistic Law Discovery (PLD) is a logic based Machine Learning method, which implements a variant of probabilistic rule learning. In several aspects, PLD is close to Decision Tree/Random Forest methods, but it differs significantly in how relevant rules are defined. The learning procedure of PLD solves the optimization problem related to the search for rules (called probabilistic laws), which have a minimal length and relatively high probability. At inference, ensembles of these rules are used for prediction. Probabilistic laws are human-readable and PLD based models are transparent and inherently interpretable. Applications of PLD include classification/clusterization/regression tasks, as well as time series analysis/anomaly detection and adaptive (robotic) control. In this paper, we outline the main principles of PLD, highlight its benefits and limitations and provide some application guidelines.

The issue of left before treatment complete (LBTC) patients is common in emergency departments (EDs). This issue represents a medico-legal risk and may cause a revenue loss. Thus, understanding the factors that cause patients to leave before treatment is complete is vital to mitigate and potentially eliminate these adverse effects. This paper proposes a framework for studying the factors that affect LBTC outcomes in EDs. The framework integrates machine learning, metaheuristic optimization, and model interpretation techniques. Metaheuristic optimization is used for hyperparameter optimization--one of the main challenges of machine learning model development. Three metaheuristic optimization algorithms are employed for optimizing the parameters of extreme gradient boosting (XGB), which are simulated annealing (SA), adaptive simulated annealing (ASA), and adaptive tabu simulated annealing (ATSA). The optimized XGB models are used to predict the LBTC outcomes for the patients under treatment in ED. The designed algorithms are trained and tested using four data groups resulting from the feature selection phase. The model with the best predictive performance is interpreted using SHaply Additive exPlanations (SHAP) method. The findings show that ATSA-XGB outperformed other mode configurations with an accuracy, area under the curve (AUC), sensitivity, specificity, and F1-score of 86.61%, 87.50%, 85.71%, 87.51%, and 86.60%, respectively. The degree and the direction of effects of each feature were determined and explained using the SHAP method.

For small training set sizes $P$, the generalization error of wide neural networks is well-approximated by the error of an infinite width neural network (NN), either in the kernel or mean-field/feature-learning regime. However, after a critical sample size $P^*$, we empirically find the finite-width network generalization becomes worse than that of the infinite width network. In this work, we empirically study the transition from infinite-width behavior to this variance limited regime as a function of sample size $P$ and network width $N$. We find that finite-size effects can become relevant for very small dataset sizes on the order of $P^* \sim \sqrt{N}$ for polynomial regression with ReLU networks. We discuss the source of these effects using an argument based on the variance of the NN's final neural tangent kernel (NTK). This transition can be pushed to larger $P$ by enhancing feature learning or by ensemble averaging the networks. We find that the learning curve for regression with the final NTK is an accurate approximation of the NN learning curve. Using this, we provide a toy model which also exhibits $P^* \sim \sqrt{N}$ scaling and has $P$-dependent benefits from feature learning.

Many applications of representation learning, such as privacy preservation, algorithmic fairness, and domain adaptation, desire explicit control over semantic information being discarded. This goal is formulated as satisfying two objectives: maximizing utility for predicting a target attribute while simultaneously being invariant (independent) to a known semantic attribute. Solutions to invariant representation learning (IRepL) problems lead to a trade-off between utility and invariance when they are competing. While existing works study bounds on this trade-off, two questions remain outstanding: 1) What is the exact trade-off between utility and invariance? and 2) What are the encoders (mapping the data to a representation) that achieve the trade-off, and how can we estimate it from training data? This paper addresses these questions for IRepLs in reproducing kernel Hilbert spaces (RKHS)s. Under the assumption that the distribution of a low-dimensional projection of high-dimensional data is approximately normal, we derive a closed-form solution for the global optima of the underlying optimization problem for encoders in RKHSs. This yields closed formulae for a near-optimal trade-off, corresponding optimal representation dimensionality, and the corresponding encoder(s). We also numerically quantify the trade-off on representative problems and compare them to those achieved by baseline IRepL algorithms.

Self-supervised learning (SSL) aims to produce useful feature representations without access to any human-labeled data annotations. Due to the success of recent SSL methods based on contrastive learning, such as SimCLR, this problem has gained popularity. Most current contrastive learning approaches append a parametrized projection head to the end of some backbone network to optimize the InfoNCE objective and then discard the learned projection head after training. This raises a fundamental question: Why is a learnable projection head required if we are to discard it after training? In this work, we first perform a systematic study on the behavior of SSL training focusing on the role of the projection head layers. By formulating the projection head as a parametric component for the InfoNCE objective rather than a part of the network, we present an alternative optimization scheme for training contrastive learning based SSL frameworks. Our experimental study on multiple image classification datasets demonstrates the effectiveness of the proposed approach over alternatives in the SSL literature.

In this article, we will be exploring how machine learning (ML) techniques can be used to identify and analyze biomarkers from next generation sequencing (NGS) data. Biomarkers are specific biological molecules or characteristics that can be used to identify the presence or severity of a particular disease or condition. They play a crucial role in medical diagnosis, treatment, and prognosis, and their discovery and validation is an important area of research in the field of biomedical science. Next Generation Sequencing is a powerful tool that allows researchers to analyze large amounts of genetic data quickly and accurately. By combining the capabilities of machine learning with next generation sequencing data, we can unlock the potential to identify and validate new biomarkers that can improve our understanding of diseases and lead to more effective treatments.

Interactive Pipeline and Composite Estimators for Your End-to-End ML Model Machine Learning Modeling posted by ODSC Community November 3, 2022 ODSC Community A data science model development pipeline involves various components including data injection, data preprocessing, feature engineering, feature scaling, and modeling. A data science model development pipeline involves various components including data injection, data preprocessing, feature engineering, feature scaling, and modeling. A data scientist needs to write the learning and inference code for all the components. The code structure sometimes becomes messier and difficult to interpret for other team members, for machine learning projects with heterogeneous data. A pipeline is a very handy function that can sequentially ensemble all your model development components.

As of 2022, greenhouse gases (GHG) emissions reporting and auditing are not yet compulsory for all companies and methodologies of measurement and estimation are not unified. We propose a machine learning-based model to estimate scope 1 and scope 2 GHG emissions of companies not reporting them yet. Our model, specifically designed to be transparent and completely adapted to this use case, is able to estimate emissions for a large universe of companies. It shows good out-of-sample global performances as well as good out-of-sample granular performances when evaluating it by sectors, by countries or by revenues buckets. We also compare our results to those of other providers and find our estimates to be more accurate. Thanks to the proposed explainability tools using Shapley values, our model is fully interpretable, the user being able to understand which factors split explain the GHG emissions for each particular company.