Distributed learning has become a critical enabler of the massively connected world envisioned by many. This article discusses four key elements of scalable distributed processing and real-time intelligence --- problems, data, communication and computation. Our aim is to provide a fresh and unique perspective about how these elements should work together in an effective and coherent manner. In particular, we {provide a selective review} about the recent techniques developed for optimizing non-convex models (i.e., problem classes), processing batch and streaming data (i.e., data types), over the networks in a distributed manner (i.e., communication and computation paradigm). We describe the intuitions and connections behind a core set of popular distributed algorithms, emphasizing how to trade off between computation and communication costs. Practical issues and future research directions will also be discussed.
In the applications of signal processing and data analytics, there is a wide class of non-convex problems whose objective function is freed from the common global Lipschitz continuous gradient assumption (e.g., the nonnegative matrix factorization (NMF) problem). Recently, this type of problem with some certain special structures has been solved by Bregman proximal gradient (BPG). This inspires us to propose a new Block-wise two-references Bregman proximal gradient (B2B) method, which adopts two reference functions so that a closed-form solution in the Bregman projection is obtained. Based on the relative smoothness, we prove the global convergence of the proposed algorithms for various block selection rules. In particular, we establish the global convergence rate of $O(\frac{\sqrt{s}}{\sqrt{k}})$ for the greedy and randomized block updating rule for B2B, which is $O(\sqrt{s})$ times faster than the cyclic variant, i.e., $O(\frac{s}{\sqrt{k}} )$, where $s$ is the number of blocks, and $k$ is the number of iterations. Multiple numerical results are provided to illustrate the superiority of the proposed B2B compared to the state-of-the-art works in solving NMF problems.
Federated learning opens a number of research opportunities due to its high communication efficiency in distributed training problems within a star network. In this paper, we focus on improving the communication efficiency for fully decentralized federated learning over a graph, where the algorithm performs local updates for several iterations and then enables communications among the nodes. In such a way, the communication rounds of exchanging the common interest of parameters can be saved significantly without loss of optimality of the solutions. Multiple numerical simulations based on large, real-world electronic health record databases showcase the superiority of the decentralized federated learning compared with classic methods.
The online meta-learning framework is designed for the continual lifelong learning setting. It bridges two fields: meta-learning which tries to extract prior knowledge from existing tasks for fast learning of future tasks, and online-learning which focuses on the sequential setting in which problems are revealed one by one. In this paper, we generalize the original framework from convex to non-convex setting, and introduce the local regret as the alternative performance measure. We then apply this framework to stochastic settings, and show theoretically that it enjoys a logarithmic local regret, and is robust to any hyperparameter initialization. The empirical test on a real-world task demonstrates its superiority compared with traditional methods.
Many modern large-scale machine learning problems benefit from decentralized and stochastic optimization. Recent works have shown that utilizing both decentralized computing and local stochastic gradient estimates can outperform state-of-the-art centralized algorithms, in applications involving highly non-convex problems, such as training deep neural networks. In this work, we propose a decentralized stochastic algorithm to deal with certain smooth non-convex problems where there are $m$ nodes in the system, and each node has a large number of samples (denoted as $n$). Differently from the majority of the existing decentralized learning algorithms for either stochastic or finite-sum problems, our focus is given to both reducing the total communication rounds among the nodes, while accessing the minimum number of local data samples. In particular, we propose an algorithm named D-GET (decentralized gradient estimation and tracking), which jointly performs decentralized gradient estimation (which estimates the local gradient using a subset of local samples) and gradient tracking (which tracks the global full gradient using local estimates). We show that, to achieve certain $\epsilon$ stationary solution of the deterministic finite sum problem, the proposed algorithm achieves an $\mathcal{O}(mn^{1/2}\epsilon^{-1})$ sample complexity and an $\mathcal{O}(\epsilon^{-1})$ communication complexity. These bounds significantly improve upon the best existing bounds of $\mathcal{O}(mn\epsilon^{-1})$ and $\mathcal{O}(\epsilon^{-1})$, respectively. Similarly, for online problems, the proposed method achieves an $\mathcal{O}(m \epsilon^{-3/2})$ sample complexity and an $\mathcal{O}(\epsilon^{-1})$ communication complexity, while the best existing bounds are $\mathcal{O}(m\epsilon^{-2})$ and $\mathcal{O}(\epsilon^{-2})$, respectively.
In this paper, we study the problem of constrained robust (min-max) optimization ina black-box setting, where the desired optimizer cannot access the gradients of the objective function but may query its values. We present a principled optimization framework, integrating a zeroth-order (ZO) gradient estimator with an alternating projected stochastic gradient descent-ascent method, where the former only requires a small number of function queries and the later needs just one-step descent/ascent update. We show that the proposed framework, referred to as ZO-Min-Max, has a sub-linear convergence rate under mild conditions and scales gracefully with problem size. From an application side, we explore a promising connection between black-box min-max optimization and black-box evasion and poisoning attacks in adversarial machine learning (ML). Our empirical evaluations on these use cases demonstrate the effectiveness of our approach and its scalability to dimensions that prohibit using recent black-box solvers.
This paper proposes low-complexity algorithms for finding approximate second-order stationary points (SOSPs) of problems with smooth non-convex objective and linear constraints. While finding (approximate) SOSPs is computationally intractable, we first show that generic instances of the problem can be solved efficiently. More specifically, for a generic problem instance, certain strict complementarity (SC) condition holds for all Karush-Kuhn-Tucker (KKT) solutions (with probability one). The SC condition is then used to establish an equivalence relationship between two different notions of SOSPs, one of which is computationally easy to verify. Based on this particular notion of SOSP, we design an algorithm named the Successive Negative-curvature grAdient Projection (SNAP), which successively performs either conventional gradient projection or some negative curvature based projection steps to find SOSPs. SNAP and its first-order extension SNAP$^+$, require $\mathcal{O}(1/\epsilon^{2.5})$ iterations to compute an $(\epsilon, \sqrt{\epsilon})$-SOSP, and their per-iteration computational complexities are polynomial in the number of constraints and problem dimension. To our knowledge, this is the first time that first-order algorithms with polynomial per-iteration complexity and global sublinear rate have been designed to find SOSPs of the important class of non-convex problems with linear constraints.
In this paper, we investigate the design and implementation of machine learning (ML) based demodulation methods in the physical layer of visible light communication (VLC) systems. We build a flexible hardware prototype of an end-to-end VLC system, from which the received signals are collected as the real data. The dataset is available online, which contains eight types of modulated signals. Then, we propose three ML demodulators based on convolutional neural network (CNN), deep belief network (DBN), and adaptive boosting (AdaBoost), respectively. Specifically, the CNN based demodulator converts the modulated signals to images and recognizes the signals by the image classification. The proposed DBN based demodulator contains three restricted Boltzmann machines (RBMs) to extract the modulation features. The AdaBoost method includes a strong classifier that is constructed by the weak classifiers with the k-nearest neighbor (KNN) algorithm. These three demodulators are trained and tested by our online open dataset. Experimental results show that the demodulation accuracy of the three data-driven demodulators drops as the transmission distance increases. A higher modulation order negatively influences the accuracy for a given transmission distance. Among the three ML methods, the AdaBoost modulator achieves the best performance.
In this paper, we investigate deep learning (DL)-enabled signal demodulation methods and establish the first open dataset of real modulated signals for wireless communication systems. Specifically, we propose a flexible communication prototype platform for measuring real modulation dataset. Then, based on the measured dataset, two DL-based demodulators, called deep belief network (DBN)-support vector machine (SVM) demodulator and adaptive boosting (AdaBoost) based demodulator, are proposed. The proposed DBN-SVM based demodulator exploits the advantages of both DBN and SVM, i.e., the advantage of DBN as a feature extractor and SVM as a feature classifier. In DBN-SVM based demodulator, the received signals are normalized before being fed to the DBN network. Furthermore, an AdaBoost based demodulator is developed, which employs the $k$-Nearest Neighbor (KNN) as a weak classifier to form a strong combined classifier. Finally, experimental results indicate that the proposed DBN-SVM based demodulator and AdaBoost based demodulator are superior to the single classification method using DBN, SVM, and maximum likelihood (MLD) based demodulator.