Energy-based models (EBMs) are a simple yet powerful framework for generative modeling. They are based on a trainable energy function which defines an associated Gibbs measure, and they can be trained and sampled from via well-established statistical tools, such as MCMC. Neural networks may be used as energy function approximators, providing both a rich class of expressive models as well as a flexible device to incorporate data structure. In this work we focus on shallow neural networks. Building from the incipient theory of overparametrized neural networks, we show that models trained in the so-called "active" regime provide a statistical advantage over their associated "lazy" or kernel regime, leading to improved adaptivity to hidden low-dimensional structure in the data distribution, as already observed in supervised learning. Our study covers both maximum likelihood and Stein Discrepancy estimators, and we validate our theoretical results with numerical experiments on synthetic data.

Face representation learning using datasets with massive number of identities requires appropriate training methods. Softmax-based approach, currently the state-of-the-art in face recognition, in its usual "full softmax" form is not suitable for datasets with millions of persons. Several methods, based on the "sampled softmax" approach, were proposed to remove this limitation. These methods, however, have a set of disadvantages. One of them is a problem of "prototype obsolescence": classifier weights (prototypes) of the rarely sampled classes, receive too scarce gradients and become outdated and detached from the current encoder state, resulting in an incorrect training signals. This problem is especially serious in ultra-large-scale datasets. In this paper, we propose a novel face representation learning model called Prototype Memory, which alleviates this problem and allows training on a dataset of any size. Prototype Memory consists of the limited-size memory module for storing recent class prototypes and employs a set of algorithms to update it in appropriate way. New class prototypes are generated on the fly using exemplar embeddings in the current mini-batch. These prototypes are enqueued to the memory and used in a role of classifier weights for usual softmax classification-based training. To prevent obsolescence and keep the memory in close connection with encoder, prototypes are regularly refreshed, and oldest ones are dequeued and disposed. Prototype Memory is computationally efficient and independent of dataset size. It can be used with various loss functions, hard example mining algorithms and encoder architectures. We prove the effectiveness of the proposed model by extensive experiments on popular face recognition benchmarks.

Adaptive Bit Rate (ABR) decision plays a crucial role for ensuring satisfactory Quality of Experience (QoE) in video streaming applications, in which past network statistics are mainly leveraged for future network bandwidth prediction. However, most algorithms, either rules-based or learning-driven approaches, feed throughput traces or classified traces based on traditional statistics (i.e., mean/standard deviation) to drive ABR decision, leading to compromised performances in specific scenarios. Given the diverse network connections (e.g., WiFi, cellular and wired link) from time to time, this paper thus proposes to learn the ANT (a.k.a., Accurate Network Throughput) model to characterize the full spectrum of network throughput dynamics in the past for deriving the proper network condition associated with a specific cluster of network throughput segments (NTS). Each cluster of NTS is then used to generate a dedicated ABR model, by which we wish to better capture the network dynamics for diverse connections. We have integrated the ANT model with existing reinforcement learning (RL)-based ABR decision engine, where different ABR models are applied to respond to the accurate network sensing for better rate decision. Extensive experiment results show that our approach can significantly improve the user QoE by 65.5% and 31.3% respectively, compared with the state-of-the-art Pensive and Oboe, across a wide range of network scenarios.

In the probability theory, there are two principles associated with entropy: the principle of maximum entropy and the principle of minimum cross-entropy. At very beginning we notice that there are two types of entropy, however there are more in stock. First of all, let us emphasize that neither the principle of maximum entropy nor the principle of minimum cross-entropy are theorems, they are only principles of statistical inference. This is very similar to philosophical doctrine. However, these doctrines certainly have mathematical implications. So we have two different types of entropy: entropy and cross-entropy.

This is a brand new Machine Learning and Data Science course just launched and updated this month with the latest trends and skills for 2021! Become a complete Data Scientist and Machine Learning engineer! Join a live online community of 400,000 engineers and a course taught by industry experts that have actually worked for large companies in places like Silicon Valley and Toronto. Graduates of Andrei's courses are now working at Google, Tesla, Amazon, Apple, IBM, JP Morgan, Facebook, other top tech companies. You will go from zero to mastery!

My course will be your complete guide to the theory and applications of supervised & unsupervised machine learning and predictive modeling using the R-programming language. Unlike other courses, it offers NOT ONLY the guided demonstrations of the R-scripts but also covers theoretical background that will allow you to FULLY UNDERSTAND & APPLY MACHINE LEARNING & PREDICTIVE MODELS (K-means, Random Forest, SVM, logistic regression, etc) in R (many R packages incl. This course also covers all the main aspects of practical and highly applied data science related to Machine Learning (classification & regressions) and unsupervised clustering techniques. Thus, if you take this course, you will save lots of time & money on other expensive materials in the R based Data Science and Machine Learning domain. In this age of big data, companies across the globe use R to analyze big volumes of data for business and research.

Data Scientists are often asked to predict a target variable in a business setting without given certain instructions. This is a challenging task and there are multiple ways to reach the finishing line. This blog is an example of how to perform an end-to-end multivariate analysis utilizing Ridge Regression. To illustrate an example, the well-known housing data is picked where home sale price will be the target variable. First I started with eliminating the missing data which are caused by lack of an amenity.

Artificial intelligence (AI) has witnessed a substantial breakthrough in a variety of Internet of Things (IoT) applications and services, spanning from recommendation systems to robotics control and military surveillance. This is driven by the easier access to sensory data and the enormous scale of pervasive/ubiquitous devices that generate zettabytes (ZB) of real-time data streams. Designing accurate models using such data streams, to predict future insights and revolutionize the decision-taking process, inaugurates pervasive systems as a worthy paradigm for a better quality-of-life. The confluence of pervasive computing and artificial intelligence, Pervasive AI, expanded the role of ubiquitous IoT systems from mainly data collection to executing distributed computations with a promising alternative to centralized learning, presenting various challenges. In this context, a wise cooperation and resource scheduling should be envisaged among IoT devices (e.g., smartphones, smart vehicles) and infrastructure (e.g. edge nodes, and base stations) to avoid communication and computation overheads and ensure maximum performance. In this paper, we conduct a comprehensive survey of the recent techniques developed to overcome these resource challenges in pervasive AI systems. Specifically, we first present an overview of the pervasive computing, its architecture, and its intersection with artificial intelligence. We then review the background, applications and performance metrics of AI, particularly Deep Learning (DL) and online learning, running in a ubiquitous system. Next, we provide a deep literature review of communication-efficient techniques, from both algorithmic and system perspectives, of distributed inference, training and online learning tasks across the combination of IoT devices, edge devices and cloud servers. Finally, we discuss our future vision and research challenges.

Learning of matrix-valued data has recently surged in a range of scientific and business applications. Trace regression is a widely used method to model effects of matrix predictors and has shown great success in matrix learning. However, nearly all existing trace regression solutions rely on two assumptions: (i) a known functional form of the conditional mean, and (ii) a global low-rank structure in the entire range of the regression function, both of which may be violated in practice. In this article, we relax these assumptions by developing a general framework for nonparametric trace regression models via structured sign series representations of high dimensional functions. The new model embraces both linear and nonlinear trace effects, and enjoys rank invariance to order-preserving transformations of the response. In the context of matrix completion, our framework leads to a substantially richer model based on what we coin as the "sign rank" of a matrix. We show that the sign series can be statistically characterized by weighted classification tasks. Based on this connection, we propose a learning reduction approach to learn the regression model via a series of classifiers, and develop a parallelable computation algorithm to implement sign series aggregations. We establish the excess risk bounds, estimation error rates, and sample complexities. Our proposal provides a broad nonparametric paradigm to many important matrix learning problems, including matrix regression, matrix completion, multi-task learning, and compressed sensing. We demonstrate the advantages of our method through simulations and two applications, one on brain connectivity study and the other on high-rank image completion.

This work presents an algorithm to sample from the Wasserstein barycenter of absolutely continuous measures. Our method is based on the gradient flow of the multimarginal formulation of the Wasserstein barycenter, with an additive penalization to account for the marginal constraints. We prove that the minimum of this penalized multimarginal formulation is achieved for a coupling that is close to the Wasserstein barycenter. The performances of the algorithm are showcased in several settings.