Fuzzy Cognitive Maps (FCMs) have emerged as an interpretable signed weighted digraph method consisting of nodes (concepts) and weights which represent the dependencies among the concepts. Although FCMs have attained considerable achievements in various time series prediction applications, designing an FCM model with time-efficient training method is still an open challenge. Thus, this paper introduces a novel univariate time series forecasting technique, which is composed of a group of randomized high order FCM models labeled R-HFCM. The novelty of the proposed R-HFCM model is relevant to merging the concepts of FCM and Echo State Network (ESN) as an efficient and particular family of Reservoir Computing (RC) models, where the least squares algorithm is applied to train the model. From another perspective, the structure of R-HFCM consists of the input layer, reservoir layer, and output layer in which only the output layer is trainable while the weights of each sub-reservoir components are selected randomly and keep constant during the training process. As case studies, this model considers solar energy forecasting with public data for Brazilian solar stations as well as Malaysia dataset, which includes hourly electric load and temperature data of the power supply company of the city of Johor in Malaysia. The experiment also includes the effect of the map size, activation function, the presence of bias and the size of the reservoir on the accuracy of R-HFCM method. The obtained results confirm the outperformance of the proposed R-HFCM model in comparison to the other methods. This study provides evidence that FCM can be a new way to implement a reservoir of dynamics in time series modelling.

Machine learning algorithms perform well on identifying patterns in many different datasets due to their versatility. However, as one increases the size of the dataset, the computation time for training and using these statistical models grows quickly. Quantum computing offers a new paradigm which may have the ability to overcome these computational difficulties. Here, we propose a quantum analogue to K-means clustering, implement it on simulated superconducting qubits, and compare it to a previously developed quantum support vector machine. We find the algorithm's accuracy comparable to the classical K-means algorithm for clustering and classification problems, and find that it has asymptotic complexity $O(N^{3/2}K^{1/2}\log{P})$, where $N$ is the number of data points, $K$ is the number of clusters, and $P$ is the dimension of the data points, giving a significant speedup over the classical analogue.

The similarity between objects is significant in a broad range of areas. While similarity can be measured using off-the-shelf distance functions, they may fail to capture the inherent meaning of similarity, which tends to depend on the underlying data and task. Moreover, conventional distance functions limit the space of similarity measures to be symmetric and do not directly allow comparing objects from different spaces. We propose using quantum networks (GQSim) for learning task-dependent (a)symmetric similarity between data that need not have the same dimensionality. We analyze the properties of such similarity function analytically (for a simple case) and numerically (for a complex case) and showthat these similarity measures can extract salient features of the data. We also demonstrate that the similarity measure derived using this technique is $(\epsilon,\gamma,\tau)$-good, resulting in theoretically guaranteed performance. Finally, we conclude by applying this technique for three relevant applications - Classification, Graph Completion, Generative modeling.

Tristructural isotropic (TRISO)-coated particle fuel is a robust nuclear fuel and determining its reliability is critical for the success of advanced nuclear technologies. However, TRISO failure probabilities are small and the associated computational models are expensive. We used coupled active learning, multifidelity modeling, and subset simulation to estimate the failure probabilities of TRISO fuels using several 1D and 2D models. With multifidelity modeling, we replaced expensive high-fidelity (HF) model evaluations with information fusion from two low-fidelity (LF) models. For the 1D TRISO models, we considered three multifidelity modeling strategies: only Kriging, Kriging LF prediction plus Kriging correction, and deep neural network (DNN) LF prediction plus Kriging correction. While the results across these multifidelity modeling strategies compared satisfactorily, strategies employing information fusion from two LF models consistently called the HF model least often. Next, for the 2D TRISO model, we considered two multifidelity modeling strategies: DNN LF prediction plus Kriging correction (data-driven) and 1D TRISO LF prediction plus Kriging correction (physics-based). The physics-based strategy, as expected, consistently required the fewest calls to the HF model. However, the data-driven strategy had a lower overall simulation time since the DNN predictions are instantaneous, and the 1D TRISO model requires a non-negligible simulation time.

Autoencoders are the simplest neural network for unsupervised learning, and thus an ideal framework for studying feature learning. While a detailed understanding of the dynamics of linear autoencoders has recently been obtained, the study of non-linear autoencoders has been hindered by the technical difficulty of handling training data with non-trivial correlations - a fundamental prerequisite for feature extraction. Here, we study the dynamics of feature learning in non-linear, shallow autoencoders. We derive a set of asymptotically exact equations that describe the generalisation dynamics of autoencoders trained with stochastic gradient descent (SGD) in the limit of high-dimensional inputs. These equations reveal that autoencoders learn the leading principal components of their inputs sequentially. An analysis of the long-time dynamics explains the failure of sigmoidal autoencoders to learn with tied weights, and highlights the importance of training the bias in ReLU autoencoders. Building on previous results for linear networks, we analyse a modification of the vanilla SGD algorithm which allows learning of the exact principal components. Finally, we show that our equations accurately describe the generalisation dynamics of non-linear autoencoders on realistic datasets such as CIFAR10.

Linear prediction is the cornerstone of a significant group of statistical learning algorithms including linear regression, Support Vector Machines (SVM), regularized regressions (such as ridge, elastic net, lasso, and its variants), logistic regression, Poisson regression, probit models, single-layer perceptrons, and tensor regression, just to name a few. Thus, developing a deeper understanding of the pertinent linear prediction models and generalizing the methods to provide unified theoretical bounds is of critical importance to the machine learning community. For the past few decades, researchers have unveiled different aspects of these linear models. Bartlett and Shawe-Taylor (1999) obtained high confidence generalization error bounds for SVMs and other learning algorithms such as boosting and Bayesian posterior classifier. Vapnik-Chervonenkis (VC) theory (Vapnik, 2013) and Rademacher complexity (Bartlett and Mendelson, 2001, 2002) have been instrumental in the machine learning literature to provide generalization bounds (Shalev-Shwartz and Ben-David, 2014). Theoretical properties of the multiple-instance extensions of SVM were analyzed by Doran and Ray (2014). Joint first authors contributed equally to this work.

In this work, we study empirical risk minimization (ERM) within a federated learning framework, where a central server minimizes an ERM objective function using training data that is stored across $m$ clients. In this setting, the Federated Averaging (FedAve) algorithm is the staple for determining $\epsilon$-approximate solutions to the ERM problem. Similar to standard optimization algorithms, the convergence analysis of FedAve only relies on smoothness of the loss function in the optimization parameter. However, loss functions are often very smooth in the training data too. To exploit this additional smoothness, we propose the Federated Low Rank Gradient Descent (FedLRGD) algorithm. Since smoothness in data induces an approximate low rank structure on the loss function, our method first performs a few rounds of communication between the server and clients to learn weights that the server can use to approximate clients' gradients. Then, our method solves the ERM problem at the server using inexact gradient descent. To show that FedLRGD can have superior performance to FedAve, we present a notion of federated oracle complexity as a counterpart to canonical oracle complexity. Under some assumptions on the loss function, e.g., strong convexity in parameter, $\eta$-H\"older smoothness in data, etc., we prove that the federated oracle complexity of FedLRGD scales like $\phi m(p/\epsilon)^{\Theta(d/\eta)}$ and that of FedAve scales like $\phi m(p/\epsilon)^{3/4}$ (neglecting sub-dominant factors), where $\phi\gg 1$ is a "communication-to-computation ratio," $p$ is the parameter dimension, and $d$ is the data dimension. Then, we show that when $d$ is small and the loss function is sufficiently smooth in the data, FedLRGD beats FedAve in federated oracle complexity. Finally, in the course of analyzing FedLRGD, we also establish a result on low rank approximation of latent variable models.

This paper proposes an efficient approach to learning disentangled representations with causal mechanisms based on the difference of conditional probabilities in original and new distributions. We approximate the difference with models' generalization abilities so that it fits in the standard machine learning framework and can be efficiently computed. In contrast to the state-of-the-art approach, which relies on the learner's adaptation speed to new distribution, the proposed approach only requires evaluating the model's generalization ability. We provide a theoretical explanation for the advantage of the proposed method, and our experiments show that the proposed technique is 1.9-11.0 Causal reasoning is a fundamental tool that has shown significant impact in different disciplines (Rubin & Waterman, 2006; Ramsey et al., 2010; Rotmensch et al., 2017; Schölkopf et al., 2021), and it has roots in work by David Hume in the eighteenth century (Hume, 2003) and classical AI (Pearl, 2003). Causality has been mainly studied from a statistical perspective (Pearl, 2009; Peters et al., 2016; Greenland et al., 1999; Pearl, 2018) with Judea Pearl's work on the causal calculus leading its statistical development. More recently, there has been a growing interest in integrating statistical techniques into machine learning to leverage their benefits. Welling raises a particular question about how to disentangle correlation from causation in machine learning settings to take advantage of the sample efficiency and generalization abilities of causal reasoning (Welling, 2015). Although machine learning has achieved important results on a variety of tasks like computer vision and games over the past decade (e.g., Mnih et al. (2015); Silver et al. (2017); Szegedy et al. (2017); Hudson & Manning (2018)), current approaches can struggle to generalize when the test data distribution is much different from the training distribution (common in real applications). Further, these successful methods are typically "data-hungry", requiring an abundance of labeled examples to perform well across data distributions. In statistical settings, encoding the causal structure in models has been shown to have significant efficiency advantages.

With new technologies in biomedicine, we are able to generate and collect data of various modalities, including genomics, epigenomics, transcriptomics, and proteomics (Figure 1A). Integrating heterogeneous features on a single set of observations provides a unique opportunity to gain a comprehensive understanding of an outcome of interest. It offers the potential for making discoveries that are hidden in data analyses of a single modality and achieving more accurate predictions of the outcome (Kristensen et al. 2014, Ritchie et al. 2015, Gligorijević et al. 2016, Karczewski & Snyder 2018, Ma et al. 2020). While "multi-view data analysis" can mean different things, we use it here in the context of supervised learning, where the goal is to fuse different data views to model an outcome of interest. To give a concrete example, assume that a researcher wants to predict cancer outcomes from RNA expression and DNA methylation measurements for a set of patients. The researcher suspects that: (1) both data views could potentially have prognostic value; (2) the two views share some underlying relationship with each other, as DNA methylation regulates gene expression and can repress the expression of tumor suppressor genes or promote the expression of oncogenes. Should the researcher use both data views for downstream prediction, or just use one view or the other?

In binary classification, imbalance refers to situations in which one class is heavily under-represented. This issue is due to either a data collection process or because one class is indeed rare in a population. Imbalanced classification frequently arises in applications such as biology, medicine, engineering, and social sciences. In this paper, for the first time, we theoretically study the impact of imbalance class sizes on the linear discriminant analysis (LDA) in high dimensions. We show that due to data scarcity in one class, referred to as the minority class, and high-dimensionality of the feature space, the LDA ignores the minority class yielding a maximum misclassification rate. We then propose a new construction of hard-thresholding rules based on a data splitting technique that reduces the large difference between the misclassification rates. We show that the proposed method is asymptotically optimal. We further study two well-known sparse versions of the LDA in imbalanced cases. We evaluate the finite-sample performance of different methods using simulations and by analyzing two real data sets. The results show that our method either outperforms its competitors or has comparable performance based on a much smaller subset of selected features, while being computationally more efficient.