While clients' sampling is a central operation of current state-of-the-art federated learning (FL) approaches, the impact of this procedure on the convergence and speed of FL remains to date under-investigated. In this work we introduce a novel decomposition theorem for the convergence of FL, allowing to clearly quantify the impact of client sampling on the global model update. Contrarily to previous convergence analyses, our theorem provides the exact decomposition of a given convergence step, thus enabling accurate considerations about the role of client sampling and heterogeneity. First, we provide a theoretical ground for previously reported results on the relationship between FL convergence and the variance of the aggregation weights. Second, we prove for the first time that the quality of FL convergence is also impacted by the resulting covariance between aggregation weights. Third, we establish that the sum of the aggregation weights is another source of slow-down and should be equal to 1 to improve FL convergence speed. Our theory is general, and is here applied to Multinomial Distribution (MD) and Uniform sampling, the two default client sampling in FL, and demonstrated through a series of experiments in non-iid and unbalanced scenarios. Our results suggest that MD sampling should be used as default sampling scheme, due to the resilience to the changes in data ratio during the learning process, while Uniform sampling is superior only in the special case when clients have the same amount of data.

The performance of spectral clustering heavily relies on the quality of affinity matrix. A variety of affinity-matrix-construction methods have been proposed but they have hyper-parameters to determine beforehand, which requires strong experience and lead to difficulty in real applications especially when the inter-cluster similarity is high or/and the dataset is large. On the other hand, we often have to determine to use a linear model or a nonlinear model, which still depends on experience. To solve these two problems, in this paper, we present an eigen-gap guided search method for subspace clustering. The main idea is to find the most reliable affinity matrix among a set of candidates constructed by linear and kernel regressions, where the reliability is quantified by the \textit{relative-eigen-gap} of graph Laplacian defined in this paper. We show, theoretically and numerically, that the Laplacian matrix with a larger relative-eigen-gap often yields a higher clustering accuracy and stability. Our method is able to automatically search the best model and hyper-parameters in a pre-defined space. The search space is very easy to determine and can be arbitrarily large, though a relatively compact search space can reduce the highly unnecessary computation. Our method has high flexibility and convenience in real applications, and also has low computational cost because the affinity matrix is not computed by iterative optimization. We extend the method to large-scale datasets such as MNIST, on which the time cost is less than 90s and the clustering accuracy is state-of-the-art. Extensive experiments of natural image clustering show that our method is more stable, accurate, and efficient than baseline methods.

Probabilistic sentential decision diagrams are a class of structured-decomposable probabilistic circuits especially designed to embed logical constraints. To adapt the classical LearnSPN scheme to learn the structure of these models, we propose a new scheme based on a partial closed-world assumption: data implicitly provide the logical base of the circuit. Sum nodes are thus learned by recursively clustering batches in the initial data base, while the partitioning of the variables obeys a given input vtree. Preliminary experiments show that the proposed approach might properly fit training data, and generalize well to test data, provided that these remain consistent with the underlying logical base, that is a relaxation of the training data base.

Price movement forecasting aims at predicting the future trends of financial assets based on the current market conditions and other relevant information. Recently, machine learning(ML) methods have become increasingly popular and achieved promising results for price movement forecasting in both academia and industry. Most existing ML solutions formulate the forecasting problem as a classification(to predict the direction) or a regression(to predict the return) problem in the entire set of training data. However, due to the extremely low signal-to-noise ratio and stochastic nature of financial data, good trading opportunities are extremely scarce. As a result, without careful selection of potentially profitable samples, such ML methods are prone to capture the patterns of noises instead of real signals. To address the above issues, we propose a novel framework-LARA(Locality-Aware Attention and Adaptive Refined Labeling), which contains the following three components: 1)Locality-aware attention automatically extracts the potentially profitable samples by attending to their label information in order to construct a more accurate classifier on these selected samples. 2)Adaptive refined labeling further iteratively refines the labels, alleviating the noise of samples. 3)Equipped with metric learning techniques, Locality-aware attention enjoys task-specific distance metrics and distributes attention on potentially profitable samples in a more effective way. To validate our method, we conduct comprehensive experiments on three real-world financial markets: ETFs, the China's A-share stock market, and the cryptocurrency market. LARA achieves superior performance compared with the time-series analysis methods and a set of machine learning based competitors on the Qlib platform. Extensive ablation studies and experiments demonstrate that LARA indeed captures more reliable trading opportunities.

We introduce computationally simple, data-driven procedures for estimation and inference on a structural function $h_0$ and its derivatives in nonparametric models using instrumental variables. Our first procedure is a bootstrap-based, data-driven choice of sieve dimension for sieve nonparametric instrumental variables (NPIV) estimators. When implemented with this data-driven choice, sieve NPIV estimators of $h_0$ and its derivatives are adaptive: they converge at the best possible (i.e., minimax) sup-norm rate, without having to know the smoothness of $h_0$, degree of endogeneity of the regressors, or instrument strength. Our second procedure is a data-driven approach for constructing honest and adaptive uniform confidence bands (UCBs) for $h_0$ and its derivatives. Our data-driven UCBs guarantee coverage for $h_0$ and its derivatives uniformly over a generic class of data-generating processes (honesty) and contract at, or within a logarithmic factor of, the minimax sup-norm rate (adaptivity). As such, our data-driven UCBs deliver asymptotic efficiency gains relative to UCBs constructed via the usual approach of undersmoothing. In addition, both our procedures apply to nonparametric regression as a special case. We use our procedures to estimate and perform inference on a nonparametric gravity equation for the intensive margin of firm exports and find evidence against common parameterizations of the distribution of unobserved firm productivity.

Stochastic gradient descent (SGD) has been deployed to solve highly non-linear and non-convex machine learning problems such as the training of deep neural networks. However, previous works on SGD often rely on highly restrictive and unrealistic assumptions about the nature of noise in SGD. In this work, we mathematically construct examples that defy previous understandings of SGD. For example, our constructions show that: (1) SGD may converge to a local maximum; (2) SGD may escape a saddle point arbitrarily slowly; (3) SGD may prefer sharp minima over the flat ones; and (4) AMSGrad may converge to a local maximum. Our result suggests that the noise structure of SGD might be more important than the loss landscape in neural network training and that future research should focus on deriving the actual noise structure in deep learning.

Generalization performance of stochastic optimization stands a central place in learning theory. In this paper, we investigate the excess risk performance and towards improved learning rates for two popular approaches of stochastic optimization: empirical risk minimization (ERM) and stochastic gradient descent (SGD). Although there exists plentiful generalization analysis of ERM and SGD for supervised learning, current theoretical understandings of ERM and SGD either have stronger assumptions in convex learning, e.g., strong convexity, or show slow rates and less studied in nonconvex learning. Motivated by these problems, we aim to provide improved rates under milder assumptions in convex learning and derive faster rates in nonconvex learning. It is notable that our analysis span two popular theoretical viewpoints: \emph{stability} and \emph{uniform convergence}. Specifically, in stability regime, we present high probability learning rates of order $\mathcal{O} (1/n)$ w.r.t. the sample size $n$ for ERM and SGD with milder assumptions in convex learning and similar high probability rates of order $\mathcal{O} (1/n)$ in nonconvex learning, rather than in expectation. Furthermore, this type of learning rate is improved to faster order $\mathcal{O} (1/n^2)$ in uniform convergence regime. To our best knowledge, for ERM and SGD, the learning rates presented in this paper are all state-of-the-art.

Detecting rumors on social media is a very critical task with significant implications to the economy, public health, etc. Previous works generally capture effective features from texts and the propagation structure. However, the uncertainty caused by unreliable relations in the propagation structure is common and inevitable due to wily rumor producers and the limited collection of spread data. Most approaches neglect it and may seriously limit the learning of features. Towards this issue, this paper makes the first attempt to explore propagation uncertainty for rumor detection. Specifically, we propose a novel Edge-enhanced Bayesian Graph Convolutional Network (EBGCN) to capture robust structural features. The model adaptively rethinks the reliability of latent relations by adopting a Bayesian approach. Besides, we design a new edge-wise consistency training framework to optimize the model by enforcing consistency on relations. Experiments on three public benchmark datasets demonstrate that the proposed model achieves better performance than baseline methods on both rumor detection and early rumor detection tasks.

Statistical signal processing applications usually require the estimation of some parameters of interest given a set of observed data. These estimates are typically obtained either by solving a multi-variate optimization problem, as in the maximum likelihood (ML) or maximum a posteriori (MAP) estimators, or by performing a multi-dimensional integration, as in the minimum mean squared error (MMSE) estimators. Unfortunately, analytical expressions for these estimators cannot be found in most real-world applications, and the Monte Carlo (MC) methodology is one feasible approach. MC methods proceed by drawing random samples, either from the desired distribution or from a simpler one, and using them to compute consistent estimators. The most important families of MC algorithms are Markov chain MC (MCMC) and importance sampling (IS). On the one hand, MCMC methods draw samples from a proposal density, building then an ergodic Markov chain whose stationary distribution is the desired distribution by accepting or rejecting those candidate samples as the new state of the chain. On the other hand, IS techniques draw samples from a simple proposal density, and then assign them suitable weights that measure their quality in some appropriate way. In this paper, we perform a thorough review of MC methods for the estimation of static parameters in signal processing applications. A historical note on the development of MC schemes is also provided, followed by the basic MC method and a brief description of the rejection sampling (RS) algorithm, as well as three sections describing many of the most relevant MCMC and IS algorithms, and their combined use.

Sign language is the only medium of communication for the hearing impaired and the deaf and dumb community. Communication with the general mass is thus always a challenge for this minority group. Especially in Bangla sign language (BdSL), there are 38 alphabets with some having nearly identical symbols. As a result, in BdSL recognition, the posture of hand is an important factor in addition to visual features extracted from traditional Convolutional Neural Network (CNN). In this paper, a novel architecture "Concatenated BdSL Network" is proposed which consists of a CNN based image network and a pose estimation network. While the image network gets the visual features, the relative positions of hand keypoints are taken by the pose estimation network to obtain the additional features to deal with the complexity of the BdSL symbols. A score of 91.51% was achieved by this novel approach in test set and the effectiveness of the additional pose estimation network is suggested by the experimental results.