In this paper, we consider the statistical inference for several low-rank tensor models. Specifically, in the Tucker low-rank tensor PCA or regression model, provided with any estimates achieving some attainable error rate, we develop the data-driven confidence regions for the singular subspace of the parameter tensor based on the asymptotic distribution of an updated estimate by two-iteration alternating minimization. The asymptotic distributions are established under some essential conditions on the signal-to-noise ratio (in PCA model) or sample size (in regression model). If the parameter tensor is further orthogonally decomposable, we develop the methods and theory for inference on each individual singular vector. For the rank-one tensor PCA model, we establish the asymptotic distribution for general linear forms of principal components and confidence interval for each entry of the parameter tensor. Finally, numerical simulations are presented to corroborate our theoretical discoveries. In all these models, we observe that different from many matrix/vector settings in existing work, debiasing is not required to establish the asymptotic distribution of estimates or to make statistical inference on low-rank tensors. In fact, due to the widely observed statistical-computational-gap for low-rank tensor estimation, one usually requires stronger conditions than the statistical (or information-theoretic) limit to ensure the computationally feasible estimation is achievable. Surprisingly, such conditions ``incidentally" render a feasible low-rank tensor inference without debiasing.

Fast Incremental Expectation Maximization (FIEM) is a version of the EM framework for large datasets. In this paper, we first recast FIEM and other incremental EM type algorithms in the {\em Stochastic Approximation within EM} framework. Then, we provide nonasymptotic bounds for the convergence in expectation as a function of the number of examples $n$ and of the maximal number of iterations $\kmax$. We propose two strategies for achieving an $\epsilon$-approximate stationary point, respectively with $\kmax = O(n^{2/3}/\epsilon)$ and $\kmax = O(\sqrt{n}/\epsilon^{3/2})$, both strategies relying on a random termination rule before $\kmax$ and on a constant step size in the Stochastic Approximation step. Our bounds provide some improvements on the literature. First, they allow $\kmax$ to scale as $\sqrt{n}$ which is better than $n^{2/3}$ which was the best rate obtained so far; it is at the cost of a larger dependence upon the tolerance $\epsilon$, thus making this control relevant for small to medium accuracy with respect to the number of examples $n$. Second, for the $n^{2/3}$-rate, the numerical illustrations show that thanks to an optimized choice of the step size and of the bounds in terms of quantities characterizing the optimization problem at hand, our results desig a less conservative choice of the step size and provide a better control of the convergence in expectation.

In the past decades, boosting has become a major and powerful prediction method in machine learning. The success of the classification algorithm AdaBoost by Freund and Schapire (1999) demonstrated the possibility to combine many weak learners in a sequential way in order to produce better predictions, with widespread applications in gene expression (Dudoit et al., 2002) or music genre identification (Bergstra et al., 2006), to name only a few. Friedman et al. (2000) were able to see a wider statistical framework that lead to the gradient boosting (Friedman, 2001), where a weak learner (e.g., regression trees) is used to optimize a loss function in a sequential procedure akin to gradient descent. Choosing the loss function according to the statistical problem at hand results in a versatile and efficient tool that can handle classification, regression, quantile regression or survival analysis... The popularity of gradient boosting is also due to its efficient implementation in the R package gbm by Ridgeway (2007). Along the methodological developments, strong theoretical results have justified the good performance of boosting. Consistency of boosting algorithm, i.e. their ability to achieve the optimal Bayes error rate for large samples, is considered in Breiman (2004), Zhang and Yu (2005) or Bartlett and Traskin (2007). The present paper is strongly influenced by Bühlmann 2 and Yu (2003) that proposes an analysis of regression boosting algorithms built on linear base learners thanks to explicit formulas for the boosted predictor and its error rate. In this paper, we focus on gradient boosting for regression with square loss and we briefly describe the corresponding algorithm.

Ocean dynamics constitute a source of incertitude in determining the ocean's role in complex climatic phenomena. Current observation systems have difficulty achieving sufficiently statistic precision for three-dimensional oceanic data. It is crucial knowledge to describe the behavior of internal ocean structures. We present a data-driven approach that explores latent class regressions and deep neural networks in modeling ocean dynamics in the extensions of Gulf Stream and Kuroshio currents. The obtained results show a promising direction of data-driven for understanding the ocean's characteristics (salinity, temperature) in both spatial and temporal dimensions in the turbulent regions. Our source codes are publicly available at https://github.com/v18nguye/gulfstream-lrm and at https://github.com/sagudelor/Kuroshio.

Neural text generation models conditioning on given input (e.g. machine translation and image captioning) are usually trained by maximum likelihood estimation of target text. However, the trained models suffer from various types of errors at inference time. In this paper, we propose to suppress an arbitrary type of errors by training the text generation model in a reinforcement learning framework, where we use a trainable reward function that is capable of discriminating between references and sentences containing the targeted type of errors. We create such negative examples by artificially injecting the targeted errors to the references. In experiments, we focus on two error types, repeated and dropped tokens in model-generated text. The experimental results show that our method can suppress the generation errors and achieve significant improvements on two machine translation and two image captioning tasks.

In the field of data mining, how to deal with high-dimensional data is an inevitable problem. Unsupervised feature selection has attracted more and more attention because it does not rely on labels. The performance of spectral-based unsupervised methods depends on the quality of constructed similarity matrix, which is used to depict the intrinsic structure of data. However, real-world data contain a large number of noise samples and features, making the similarity matrix constructed by original data cannot be completely reliable. Worse still, the size of similarity matrix expands rapidly as the number of samples increases, making the computational cost increase significantly. Inspired by principal component analysis, we propose a simple and efficient unsupervised feature selection method, by combining reconstruction error with $l_{2,p}$-norm regularization. The projection matrix, which is used for feature selection, is learned by minimizing the reconstruction error under the sparse constraint. Then, we present an efficient optimization algorithm to solve the proposed unsupervised model, and analyse the convergence and computational complexity of the algorithm theoretically. Finally, extensive experiments on real-world data sets demonstrate the effectiveness of our proposed method.

We introduce a novel interpretable and tree-based algorithm for prediction in a regression setting in which each tree in a classical random forest is replaced by a family of planted trees that grow simultaneously. The motivation for our algorithm is to estimate the unknown regression function from a functional ANOVA decomposition perspective, where each tree corresponds to a function within that decomposition. Therefore, planted trees are limited in the number of interaction terms. The maximal order of approximation in the ANOVA decomposition can be specified or left unlimited. If a first order approximation is chosen, the result is an additive model. In the other extreme case, if the order of approximation is not limited, the resulting model puts no restrictions on the form of the regression function. In a simulation study we find encouraging prediction and visualisation properties of our random planted forest method. We also develop theory for an idealised version of random planted forests in the case of an underlying additive model. We show that in the additive case, the idealised version achieves up to a logarithmic factor asymptotically optimal one-dimensional convergence rates of order $n^{-2/5}$.

Rates of convergence are established and, in many cases, provide superior rates to current standard estimators such as those based on kernels, including kernel density estimators and kernel regression functions.

Federated Learning is a novel paradigm that involves learning from data samples distributed across a large network of clients while the data remains local. It is, however, known that federated learning is prone to multiple system challenges including system heterogeneity where clients have different computation and communication capabilities. Such heterogeneity in clients' computation speeds has a negative effect on the scalability of federated learning algorithms and causes significant slow-down in their runtime due to the existence of stragglers. In this paper, we propose a novel straggler-resilient federated learning method that incorporates statistical characteristics of the clients' data to adaptively select the clients in order to speed up the learning procedure. The key idea of our algorithm is to start the training procedure with faster nodes and gradually involve the slower nodes in the model training once the statistical accuracy of the data corresponding to the current participating nodes is reached. The proposed approach reduces the overall runtime required to achieve the statistical accuracy of data of all nodes, as the solution for each stage is close to the solution of the subsequent stage with more samples and can be used as a warm-start. Our theoretical results characterize the speedup gain in comparison to standard federated benchmarks for strongly convex objectives, and our numerical experiments also demonstrate significant speedups in wall-clock time of our straggler-resilient method compared to federated learning benchmarks.

Independent component analysis (ICA) has been a popular dimension reduction tool in statistical machine learning and signal processing. In this paper, we present a convergence analysis for an online tensorial ICA algorithm, by viewing the problem as a nonconvex stochastic approximation problem. For estimating one component, we provide a dynamics-based analysis to prove that our online tensorial ICA algorithm with a specific choice of stepsize achieves a sharp finite-sample error bound. In particular, under a mild assumption on the data-generating distribution and a scaling condition such that $d^4 / T$ is sufficiently small up to a polylogarithmic factor of data dimension $d$ and sample size $T$, a sharp finite-sample error bound of $\tilde O(\sqrt{d / T})$ can be obtained. As a by-product, we also design an online tensorial ICA algorithm that estimates multiple independent components in parallel, achieving desirable finite-sample error bound for each independent component estimator.