Concentration inequalities have been widely used in machine learning theory. Model selection techniques, for instance, relies heavily on concentration inequality [Massart, 2007]. They have also been used for high dimensional procedures [Bickel et al., 2009, Alquier et al., 2020] or for studying different machine learning framework, such as time series prediction[Kuznetsov and Mohri, 2015], online machine learning[Sanchez-Perez, 2015] or classification problems [Freund et al., 2004]. Many concentration inequalities has been proposed for different framework and different hypothesis. An interested reader may read [Boucheron et al., 2013] for an overview on stationary concentration inequalities.

Federated learning (FL) is a fast-developing technique that allows multiple workers to train a global model based on a distributed dataset. Conventional FL employs gradient descent algorithm, which may not be efficient enough. It is well known that Nesterov Accelerated Gradient (NAG) is more advantageous in centralized training environment, but it is not clear how to quantify the benefits of NAG in FL so far. In this work, we focus on a version of FL based on NAG (FedNAG) and provide a detailed convergence analysis. The result is compared with conventional FL based on gradient descent. One interesting conclusion is that as long as the learning step size is sufficiently small, FedNAG outperforms FedAvg. Extensive experiments based on real-world datasets are conducted, verifying our conclusions and confirming the better convergence performance of FedNAG.

This work introduces Conditional Image Retrieval (CIR) systems: IR methods that can efficiently specialize to specific subsets of images on the fly. These systems broaden the class of queries IR systems support, and eliminate the need for expensive re-fitting to specific subsets of data. Specifically, we adapt tree-based K-Nearest Neighbor (KNN) data-structures to the conditional setting by introducing additional inverted-index data-structures. This speeds conditional queries and does not slow queries without conditioning. We present two new datasets for evaluating the performance of CIR systems and evaluate a variety of design choices. As a motivating application, we present an algorithm that can explore shared semantic content between works of art of vastly different media and cultural origin. Finally, we demonstrate that CIR data-structures can identify Generative Adversarial Network (GAN) "blind spots": areas where GANs fail to properly model the true data distribution.

BERT has recently attracted a lot of attention in natural language understanding (NLU) and achieved state-of-the-art results in various NLU tasks. However, its success requires large deep neural networks and huge amount of data, which result in long training time and impede development progress. Using stochastic gradient methods with large mini-batch has been advocated as an efficient tool to reduce the training time. Along this line of research, LAMB is a prominent example that reduces the training time of BERT from 3 days to 76 minutes on a TPUv3 Pod. In this paper, we propose an accelerated gradient method called LANS to improve the efficiency of using large mini-batches for training. As the learning rate is theoretically upper bounded by the inverse of the Lipschitz constant of the function, one cannot always reduce the number of optimization iterations by selecting a larger learning rate. In order to use larger mini-batch size without accuracy loss, we develop a new learning rate scheduler that overcomes the difficulty of using large learning rate. Using the proposed LANS method and the learning rate scheme, we scaled up the mini-batch sizes to 96K and 33K in phases 1 and 2 of BERT pretraining, respectively. It takes 54 minutes on 192 AWS EC2 P3dn.24xlarge instances to achieve a target F1 score of 90.5 or higher on SQuAD v1.1, achieving the fastest BERT training time in the cloud.

New York City has been recognized as the world's epicenter of the novel Coronavirus pandemic. To identify the key inherent factors that are highly correlated to the Increase Rate of COVID-19 new cases in NYC, we propose an unsupervised machine learning framework. Based on the assumption that ZIP code areas with similar demographic, socioeconomic, and mobility patterns are likely to experience similar outbreaks, we select the most relevant features to perform a clustering that can best reflect the spread, and map them down to 9 interpretable categories. We believe that our findings can guide policy makers to promptly anticipate and prevent the spread of the virus by taking the right measures.

Artificial intelligence (AI) provides many opportunities to improve private and public life. Discovering patterns and structures in large troves of data in an automated manner is a core component of data science, and currently drives applications in diverse areas such as computational biology, law and finance. However, such a highly positive impact is coupled with significant challenges: how do we understand the decisions suggested by these systems in order that we can trust them? In this report, we focus specifically on data-driven methods -- machine learning (ML) and pattern recognition models in particular -- so as to survey and distill the results and observations from the literature. The purpose of this report can be especially appreciated by noting that ML models are increasingly deployed in a wide range of businesses. However, with the increasing prevalence and complexity of methods, business stakeholders in the very least have a growing number of concerns about the drawbacks of models, data-specific biases, and so on. Analogously, data science practitioners are often not aware about approaches emerging from the academic literature, or may struggle to appreciate the differences between different methods, so end up using industry standards such as SHAP. Here, we have undertaken a survey to help industry practitioners (but also data scientists more broadly) understand the field of explainable machine learning better and apply the right tools. Our latter sections build a narrative around a putative data scientist, and discuss how she might go about explaining her models by asking the right questions.

This part of the series looks at the future of AI with much of the focus in the period after 2025. The leading AI researcher, Geoff Hinton, stated that it is very hard to predict what advances AI will bring beyond five years, noting that exponential progress makes the uncertainty too great. This article will therefore consider both the opportunities as well as the challenges that we will face along the way across different sectors of the economy. It is not intended to be exhaustive. AI deals with the area of developing computing systems which are capable of performing tasks that humans are very good at, for example recognising objects, recognising and making sense of speech, and decision making in a constrained environment. Some of the classical approaches to AI include (non-exhaustive list) Search algorithms such as Breath-First, Depth-First, Iterative Deepening Search, A* algorithm, and the field of Logic including Predicate Calculus and Propositional Calculus. Local Search approaches were also developed for example Simulated Annealing, Hill Climbing (see also Greedy), Beam Search and Genetic Algorithms (see below). Machine Learning is defined as the field of AI that applies statistical methods to enable computer systems to learn from the data towards an end goal. The term was introduced by Arthur Samuel in 1959. A non-exhaustive list of examples of techniques include Linear Regression, Logistic Regression, K-Means, k-Nearest Neighbour (kNN), Naive Bayes, Support Vector Machine (SVM), Decision Trees, Random Forests, XG Boost, Light Gradient Boosting Machine (LightGBM), CatBoost. Deep Learning refers to the field of Neural Networks with several hidden layers. Such a neural network is often referred to as a deep neural network. Neural Networks are biologically inspired networks that extract abstract features from the data in a hierarchical fashion.

Let's now look at the common types of linear-regression analysis used in machine learning. There are four basic techniques that we're going to have a look at here. Other regression models can also be found, but they're not so commonly used. Simple linear regression uses one independent variable to explain or predict the outcome. For example, you have a table with the sample data concerning the temperature of cables and their durability.

Clustering is one of the most fundamental tools in the artificial intelligence area, particularly in the pattern recognition and learning theory. In this paper, we propose a simple, but novel approach for variance-based k-clustering tasks, included in which is the widely known k-means clustering. The proposed approach picks a sampling subset from the given dataset and makes decisions based on the data information in the subset only. With certain assumptions, the resulting clustering is provably good to estimate the optimum of the variance-based objective with high probability. Extensive experiments on synthetic datasets and real-world datasets show that to obtain competitive results compared with k-means method (Llyod 1982) and k-means method (Arthur and Vassilvitskii 2007), we only need 7 up to 15 k-means method and k-means method in at least 80 terms of the quality of clustering.

Let's say you want to take one of the very important decision in your life, it will be a choosing your career or choosing your life partner. Do you think that you can depend on a just one person advice. Advice from the one person can be highly biased also. The best way you can go ahead by asking and taking guidance from multiple people which reduce the bias. Same thing apply on machine learning world also while predicting some class or predicting any continuous value for regression problem, why you should rely on a one model only.