Automatic fake news detection with machine learning can prevent the dissemination of false statements before they gain many views. Several datasets labeling statements as legitimate or false have been created since the 2016 United States presidential election for the prospect of training machine learning models. We evaluate the robustness of both traditional and deep state-of-the-art models to gauge how well they may perform in the real world. We find that traditional models tend to generalize better to data outside the distribution it was trained on compared to more recently-developed large language models, though the best model to use may depend on the specific task at hand.

Sometimes it is important to know the accuracy of a classifier on unlabeled data. The labels may be delayed, as in consumer purchasing predictions, or obtaining the labels is cost prohibitive. The labels may not exist, as for some medical conditions, for which the true gold standard diagnostic test(a 100% sensitive and 100% specific classifier) would require subjects be euthanized and autopsied to obtain labels. Epidemiologists and biostatisticians have developed statistical methods for assessing the sensitivity (Se) and specificity (Sp) of diagnostic tests when gold standard comparison tests are unavailable. In data science terms, the diagnostic test assessment data are unlabeled. In this article, I describe how to modify those diagnostic test statistical methods to estimate confusion matrices and accuracy statistics for binary classifiers.

This article was published as a part of the Data Science Blogathon. AdaBoost stands for Adaptive Boosting. It is a statistical classification algorithm. It is an algorithm that forms a committee of weak classifiers. It boosts the performance of machine learning algorithms.

In the previous post, we learned about tree based learning methods - basics of tree based models and the use of bagging to reduce variance. We also looked at one of the most famous learning algorithms based on the idea of bagging- random forests. In this post, we will look into the details of yet another type of tree-based learning algorithms: boosted trees. Boosting, similar to Bagging, is a general class of learning algorithm where a set of weak learners are combined to get strong learners. For classification problems, a weak learner is defined to be a classifier which is only slightly correlated with the true classification (it can label examples better than random guessing). In contrast, a strong learner is a classifier that is arbitrarily well-correlated with the true classification. Recall that bagging involves creating multiple copies of the original training data set via bootstrapping, fitting a separate decision tree to each copy, and then combining all of the trees in order to create a single predictive model.

AdaBoost is one of the most popular machine-learning algorithms. It is simple to implement and often found very effective by practitioners, while still being mathematically elegant and theoretically sound. AdaBoost's behavior in practice, and in particular the test-error behavior, has puzzled many eminent researchers for over a decade: It seems to defy our general intuition in machine learning regarding the fundamental trade-off between model complexity and generalization performance. In this paper, we establish the convergence of "Optimal AdaBoost," a term coined by Rudin, Daubechies, and Schapire in 2004. We prove the convergence, with the number of rounds, of the classifier itself, its generalization error, and its resulting margins for fixed data sets, under certain reasonable conditions. More generally, we prove that the time/per-round average of almost any function of the example weights converges. Our approach is to frame AdaBoost as a dynamical system, to provide sufficient conditions for the existence of an invariant measure, and to employ tools from ergodic theory. Unlike previous work, we do not assume AdaBoost cycles; actually, we present empirical evidence against it on real-world datasets. Our main theoretical results hold under a weaker condition. We show sufficient empirical evidence that Optimal AdaBoost always met the condition on every real-world dataset we tried. Our results formally ground future convergence-rate analyses, and may even provide opportunities for slight algorithmic modifications to optimize the generalization ability of AdaBoost classifiers, thus reducing a practitioner's burden of deciding how long to run the algorithm.

Despite the fact that they do not consider the temporal nature of data, classic dimensionality reduction techniques, such as PCA, are widely applied to time series data. In this paper, we introduce a factor decomposition specific for time series that builds upon the Bayesian multivariate autoregressive model and hence evades the assumption that data points are mutually independent. The key is to find a low-rank estimation of the autoregressive matrices. As in the probabilistic version of other factor models, this induces a latent low-dimensional representation of the original data. We discuss some possible generalisations and alternatives, with the most relevant being a technique for simultaneous smoothing and dimensionality reduction. To illustrate the potential applications, we apply the model on a synthetic data set and different types of neuroimaging data (EEG and ECoG).

In this work, we first show that feature selection methods other than boosting can also be used for training an efficient object detector. In particular, we introduce Greedy Sparse Linear Discriminant Analysis (GSLDA) \cite{Moghaddam2007Fast} for its conceptual simplicity and computational efficiency; and slightly better detection performance is achieved compared with \cite{Viola2004Robust}. Moreover, we propose a new technique, termed Boosted Greedy Sparse Linear Discriminant Analysis (BGSLDA), to efficiently train a detection cascade. BGSLDA exploits the sample re-weighting property of boosting and the class-separability criterion of GSLDA.