Statistical learning theory has largely focused on learning and generalization given independent and identically distributed (i.i.d.) samples. Motivated by applications involving time-series data, there has been a growing literature on learning and generalization in settings where data is sampled from an ergodic process. This work has also developed complexity measures, which appropriately extend the notion of Rademacher complexity to bound the generalization error and learning rates of hypothesis classes in this setting. Rather than time-series data, our work is motivated by settings where data is sampled on a network or a spatial domain, and thus do not fit well within the framework of prior work. We provide learning and generalization bounds for data that are complexly dependent, yet their distribution satisfies the standard Dobrushin's condition. Indeed, we show that the standard complexity measures of Gaussian and Rademacher complexities and VC dimension are sufficient measures of complexity for the purposes of bounding the generalization error and learning rates of hypothesis classes in our setting. Moreover, our generalization bounds only degrade by constant factors compared to their i.i.d. analogs, and our learnability bounds degrade by log factors in the size of the training set.

The development of cluster computing frameworks has allowed practitioners to scale out various statistical estimation and machine learning algorithms with minimal programming effort. This is especially true for machine learning problems whose objective function is nicely separable across individual data points, such as classification and regression. In contrast, statistical learning tasks involving pairs (or more generally tuples) of data points - such as metric learning, clustering or ranking do not lend themselves as easily to data-parallelism and in-memory computing. In this paper, we investigate how to balance between statistical performance and computational efficiency in such distributed tuplewise statistical problems. We first propose a simple strategy based on occasionally repartitioning data across workers between parallel computation stages, where the number of repartitioning steps rules the trade-off between accuracy and runtime. We then present some theoretical results highlighting the benefits brought by the proposed method in terms of variance reduction, and extend our results to design distributed stochastic gradient descent algorithms for tuplewise empirical risk minimization. Our results are supported by numerical experiments in pairwise statistical estimation and learning on synthetic and real-world datasets.

The central task in modeling complex dynamical systems is parameter estimation. This task involves numerous evaluations of a computationally expensive objective function. Surrogate-based optimization introduces a computationally efficient predictive model that approximates the value of the objective function. The standard approach involves learning a surrogate from training examples that correspond to past evaluations of the objective function. Current surrogate-based optimization methods use static, predefined substitution strategies that decide when to use the surrogate and when the true objective. We introduce a meta-model framework where the substitution strategy is dynamically adapted to the solution space of the given optimization problem. The meta model encapsulates the objective function, the surrogate model and the model of the substitution strategy, as well as components for learning them. The framework can be seamlessly coupled with an arbitrary optimization algorithm without any modification: it replaces the objective function and autonomously decides how to evaluate a given candidate solution. We test the utility of the framework on three tasks of estimating parameters of real-world models of dynamical systems. The results show that the meta model significantly improves the efficiency of optimization, reducing the total number of evaluations of the objective function up to an average of 77%.

There has been rapidly growing interest in the use of algorithms for employment assessment, especially as a means to address or mitigate bias in hiring. Yet, to date, little is known about how these methods are being used in practice. How are algorithmic assessments built, validated, and examined for bias? In this work, we document and assess the claims and practices of companies offering algorithms for employment assessment, using a methodology that can be applied to evaluate similar applications and issues of bias in other domains. In particular, we identify vendors of algorithmic pre-employment assessments (i.e., algorithms to screen candidates), document what they have disclosed about their development and validation procedures, and evaluate their techniques for detecting and mitigating bias. We find that companies' formulation of "bias" varies, as do their approaches to dealing with it. We also discuss the various choices vendors make regarding data collection and prediction targets, in light of the risks and trade-offs that these choices pose. We consider the implications of these choices and we raise a number of technical and legal considerations.

Deep reinforcement learning has made significant progress in the field of continuous control, such as physical control and autonomous driving. However, it is challenging for a reinforcement model to learn a policy for each task sequentially due to catastrophic forgetting. Specifically, the model would forget knowledge it learned in the past when trained on a new task. We consider this challenge from two perspectives: i) acquiring task-specific skills is difficult since task information and rewards are not highly related; ii) learning knowledge from previous experience is difficult in continuous control domains. In this paper, we introduce an end-to-end framework namely Continual Diversity Adversarial Network (CDAN). We first develop an unsupervised diversity exploration method to learn task-specific skills using an unsupervised objective. Then, we propose an adversarial self-correction mechanism to learn knowledge by exploiting past experience. The two learning procedures are presumably reciprocal. To evaluate the proposed method, we propose a new continuous reinforcement learning environment named Continual Ant Maze (CAM) and a new metric termed Normalized Shorten Distance (NSD). The experimental results confirm the effectiveness of diversity exploration and self-correction. It is worthwhile noting that our final result outperforms baseline by 18.35% in terms of NSD, and 0.61 according to the average reward.

Artificial intelligence is often hailed as a great catalyst of medical innovation, a way to find cures to diseases that have confounded doctors and make health care more efficient, personalized, and accessible. But what if it turns out to be poison? Jonathan Zittrain, a Harvard Law School professor, posed that question during a conference in Boston Tuesday that examined the use of AI to accelerate the delivery of precision medicine to the masses. "I think of machine learning kind of as asbestos," he said. "It turns out that it's all over the place, even though at no point did you explicitly install it, and it has possibly some latent bad effects that you might regret later, after it's already too hard to get it all out."

With strong roots in statistics, Machine Learning is becoming one of the most interesting and fast-paced computer science fields to work in. There's an endless supply of industries and applications machine learning can be applied to to make them more efficient and intelligent. Chat bots, spam filtering, ad serving, search engines, and fraud detection, are among just a few examples of how machine learning models underpin everyday life. Machine learning is what lets us find patterns and create mathematical models for things that would sometimes be impossible for humans to do. Unlike data science courses, which contain topics like exploratory data analysis, statistics, communication, and visualization techniques, machine learning courses focus on teaching only the machine learning algorithms, how they work mathematically, and how to utilize them in a programming language. Now, it's time to get started.

It's not hard to find a good story in the tech industry. The problem is that due to the industry's staggering gender gap, most of these stories center on the struggles and accomplishments of men. In this article, we aim to provide a platform for female technologists to share the stories of how they got into engineering, the biggest challenges they've faced, and their advice to the next generation of women in tech. You'll meet a former geologist turned product manager, an academic who fell in love with data science, a senior tech leader who discovered her dream job after the first two companies she worked for folded, and more. CCC's technology solutions are designed to increase connectedness among companies in the automotive industry, including insurance carriers, manufacturers, parts suppliers and collision repair shops. Ranjini Vaidyanathan was in academia and earned a PhD before realizing she had a passion for data science. While changing focuses wasn't always easy, Vaidyanathan said the transition was made easier by some simple, yet powerful, advice from her mentors. "When the going gets tough, what'll help you pull through is your passion for the technical work." How did you get into engineering? I studied applied science and mathematics before finally switching to data science after my PhD. It took me some time to decide what, exactly, I wanted to pursue. I had been doing pen-and-paper theory work as a student, but after a certain point, I realized I found applied problems more interesting. What's the biggest challenge you've faced in your career, and how have you worked to overcome it? Switching fields from academia to data science was challenging. I had to brush up industry-relevant skills like programming, and also adjust to the paradigm shift in thinking, both in terms of technical and soft skills.

Nearly every industry is using artificial intelligence in one way or another to improve business outcomes. AI holds great promise as new and exciting applications are discovered, but there is a catch. There aren't enough trained AI engineers capable of carrying out the work. Karen Roby talks with Sameer Maskey, a professor of AI at Columbia University and founder of Fusemachines, about the shortage and what can be done. The following is an edited transcript of the interview.

People increasingly turn to the Internet when they have a medical condition. The data they create during this process is a valuable source for medical research and for future health services. However, utilizing these data could come at a cost to user privacy. Thus, it is important to balance the perceived value that users assign to these data with the value of the services derived from them. Here we describe experiments where methods from Mechanism Design were used to elicit a truthful valuation from users for their Internet data and for services to screen people for medical conditions. In these experiments, 880 people from around the world were asked to participate in an auction to provide their data for uses differing in their contribution to the participant, to society, and in the disease they addressed. Some users were offered monetary compensation for their participation, while others were asked to pay to participate. Our findings show that 99\% of people were willing to contribute their data in exchange for monetary compensation and an analysis of their data, while 53\% were willing to pay to have their data analyzed. The average perceived value users assigned to their data was estimated at US\$49. Their value to screen them for a specific cancer was US\$22 while the value of this service offered to the general public was US\$22. Participants requested higher compensation when notified that their data would be used to analyze a more severe condition. They were willing to pay more to have their data analyzed when the condition was more severe, when they had higher education or if they had recently experienced a serious medical condition.