Machine Learning is the study of methods for programming computers to learn. Computers are applied to a wide range of tasks, and for most of these it is relatively easy for programmers to design and implement the necessary software. However, there are many tasks for which this is difficult or impossible. These can be divided into four general categories. First, there are problems for which there exist no human experts. For example, in modern automated manufacturing facilities, there is a need to predict machine failures before they occur by analyzing sensor readings. Because the machines are new, there are no human experts who can be interviewed by a programmer to provide the knowledge necessary to build a computer system. A machine learning system can study recorded data and subsequent machine failures and learn prediction rules. Second, there are problems where human experts exist, but where they are unable to explain their expertise. This is the case in many perceptual tasks, such as speech recognition, hand-writing recognition, and natural language understanding. Virtually all humans exhibit expert-level abilities on these tasks, but none of them can describe the detailed steps that they follow as they perform them. Fortunately, humans can provide machines with examples of the inputs and correct outputs for these tasks, so machine learning algorithms can learn to map the inputs to the outputs. Third, there are problems where phenomena are changing rapidly. In finance, for example, people would like to predict the future behavior of the stock market, of consumer purchases, or of exchange rates. These behaviors change frequently, so that even if a programmer could construct a good predictive computer program, it would need to be rewritten frequently. A learning program can relieve the programmer of this burden by constantly modifying and tuning a set of learned prediction rules. Fourth, there are applications that need to be customized for each computer user separately. Consider, for example, a program to filter unwanted electronic mail messages. Different users will need different filters. It is unreasonable to expect each user to program his or her own rules, and it is infeasible to provide every user with a software engineer to keep the rules up-to-date. A machine learning system can learn which mail messages the user rejects and maintain the filtering rules automatically. Machine learning addresses many of the same research questions as the fields of statistics, data mining, and psychology, but with differences of emphasis. Statistics focuses on understanding the phenomena that have generated the data, often with the goal of testing different hypotheses about those phenomena. Data mining seeks to find patterns in the data that are understandable by people. Psychological studies of human learning aspire to understand the mechanisms underlying the various learning behaviors exhibited by people (concept learning, skill acquisition, strategy change, etc.).

Machine learning

Differential privacy is a recent framework for computation on sensitive data, which has shown considerable promise in the regime of large datasets. Stochastic gradient methods are a popular approach for learning in the data-rich regime because they are computationally tractable and scalable. In this paper, we derive differentially private versions of stochastic gradient descent, and test them empirically. Our results show that standard SGD experiences high variability due to differential privacy, but a moderate increase in the batch size can improve performance significantly.

/pdf/stochastic-gradient-descent-with-differentially-private-4o3xut8y6o.pdf

Stochastic gradient descent with differentially private updates

The broad application of artificial intelligence techniques in medicine is currently hindered by limited dataset availability for algorithm training and validation, due to the absence of standardized electronic medical records, and strict legal and ethical requirements to protect patient privacy. In medical imaging, harmonized data exchange formats such as Digital Imaging and Communication in Medicine and electronic data storage are the standard, partially addressing the first issue, but the requirements for privacy preservation are equally strict. To prevent patient privacy compromise while promoting scientific research on large datasets that aims to improve patient care, the implementation of technical solutions to simultaneously address the demands for data protection and utilization is mandatory. Here we present an overview of current and next-generation methods for federated, secure and privacy-preserving artificial intelligence with a focus on medical imaging applications, alongside potential attack vectors and future prospects in medical imaging and beyond. Medical imaging data is often subject to privacy and intellectual property restrictions. AI techniques can help out by offering tools like federated learning to bridge the gap between personal data protection and data utilisation for research and clinical routine, but these tools need to be secure.

/pdf/secure-privacy-preserving-and-federated-machine-learning-in-4jedzuai3s.pdf

Secure, privacy-preserving and federated machine learning in medical imaging

The question of aggregating pairwise comparisons to obtain a global ranking over a collection of objects has been of interest for a very long time: be it ranking of online gamers (e.g., MSR’s TrueSkill system) and chess players, aggregating social opinions, or deciding which product to sell based on transactions. In most settings, in addition to obtaining a ranking, finding ‘scores’ for each object (e.g., player’s rating) is of interest for understanding the intensity of the preferences. In this paper, we propose Rank Centrality, an iterative rank aggregation algorithm for discovering scores for objects (or items) from pairwise comparisons. The algorithm has a natural random walk interpretation over the graph of objects with an edge present between a pair of objects if they are compared; the score, which we call Rank Centrality, of an object turns out to be its stationary probability under this random walk. To study the efficacy of the algorithm, we consider the popular Bradley-Terry-Luce (BTL) model (equ...

/pdf/rank-centrality-ranking-from-pairwise-comparisons-1hqlsa2za2.pdf

Rank Centrality: Ranking from Pairwise Comparisons

We consider the problem of Bayesian learning on sensitive datasets and present two simple but somewhat surprising results that connect Bayesian learning to "differential privacy", a cryptographic approach to protect individual-level privacy while permitting database-level utility. Specifically, we show that under standard assumptions, getting one sample from a posterior distribution is differentially private "for free"; and this sample as a statistical estimator is often consistent, near optimal, and computationally tractable. Similarly but separately, we show that a recent line of work that use stochastic gradient for Hybrid Monte Carlo (HMC) sampling also preserve differentially privacy with minor or no modifications of the algorithmic procedure at all, these observations lead to an "anytime" algorithm for Bayesian learning under privacy constraint. We demonstrate that it performs much better than the state-of-the-art differential private methods on synthetic and real datasets.

http://proceedings.mlr.press/v37/wangg15.pdf

Privacy for Free: Posterior Sampling and Stochastic Gradient Monte Carlo

There has been much interest recently in the problem of rank aggregation from pairwise data. A natural question that arises is: under what sorts of statistical assumptions do various rank aggregation algorithms converge to an 'optimal' ranking? In this paper, we consider this question in a natural setting where pairwise comparisons are drawn randomly and independently from some underlying probability distribution. We first show that, under a 'time-reversibility' or Bradley-Terry-Luce (BTL) condition on the distribution, the rank centrality (PageRank) and least squares (HodgeRank) algorithms both converge to an optimal ranking. Next, we show that a matrix version of the Borda count algorithm, and more surprisingly, an algorithm which performs maximum likelihood estimation under a BTL assumption, both converge to an optimal ranking under a 'low-noise' condition that is strictly more general than BTL. Finally, we propose a new SVM-based algorithm for rank aggregation from pairwise data, and show that this converges to an optimal ranking under an even more general condition that we term 'generalized low-noise'. In all cases, we provide explicit sample complexity bounds for exact recovery of an optimal ranking. Our experiments confirm our theoretical findings and help to shed light on the statistical behavior of various rank aggregation algorithms.

/pdf/a-statistical-convergence-perspective-of-algorithms-for-rank-3olu9qrpjv.pdf

A Statistical Convergence Perspective of Algorithms for Rank Aggregation from Pairwise Data

We consider the problem of developing privacypreserving machine learning algorithms in a distributed multiparty setting. Here different parties own different parts of a data set, and the goal is to learn a classifier from the entire data set without any party revealing any information about the individual data points it owns. Pathak et al [7] recently proposed a solution to this problem in which each party learns a local classifier from its own data, and a third party then aggregates these classifiers in a privacy-preserving manner using a cryptographic scheme. The generalization performance of their algorithm is sensitive to the number of parties and the relative fractions of data owned by the different parties. In this paper, we describe a new differentially private algorithm for the multiparty setting that uses a stochastic gradient descent based procedure to directly optimize the overall multiparty objective rather than combining classifiers learned from optimizing local objectives. The algorithm achieves a slightly weaker form of differential privacy than that of [7], but provides improved generalization guarantees that do not depend on the number of parties or the relative sizes of the individual data sets. Experimental results corroborate our theoretical findings.

/pdf/a-differentially-private-stochastic-gradient-descent-3hmzix04kc.pdf

A Differentially Private Stochastic Gradient Descent Algorithm for Multiparty Classification

Owing to the tremendous increase in the volume and variety of user generated content, train-once-apply-forever models are insufficient for supervised learning tasks. Thus, developing algorithms that adapt across domains by leveraging data from multiple domains is critical. However, existing adaptation algorithms often fail to identify the right sources to use for adaptation. In this work, we present a novel multi-source iterative domain adaptation algorithm (MSIDA) that leverages knowledge from selective sources to improve the performance in a target domain. The algorithm first chooses the best K sources from possibly numerous existing domains taking into account both similarity and complementarity properties of the domains. Then it learns target specific features in an iterative manner building on the common shared representations from the source domains. We give theoretical justifications for our source selection procedure and also give mistake bounds for the MSIDA algorithm. Experimental results justify the theory as MSIDA significantly outperforms existing cross-domain classification approaches on the real world and benchmark datasets.

Multi-source iterative adaptation for cross-domain classification

Recent work on deriving $O(\log T)$ anytime regret bounds for stochastic dueling bandit problems has considered mostly Condorcet winners, which do not always exist, and more recently, winners defined by the Copeland set, which do always exist. In this work, we consider a broad notion of winners defined by tournament solutions in social choice theory, which include the Copeland set as a special case but also include several other notions of winners such as the top cycle, uncovered set, and Banks set, and which, like the Copeland set, always exist. We develop a family of UCB-style dueling bandit algorithms for such general tournament solutions, and show $O(\log T)$ anytime regret bounds for them. Experiments confirm the ability of our algorithms to achieve low regret relative to the target winning set of interest.

/pdf/dueling-bandits-beyond-condorcet-winners-to-general-4ikm2fz8mc.pdf

Dueling Bandits: Beyond Condorcet Winners to General Tournament Solutions

We consider the problem of ranking n items from stochastically sampled pairwise preferences. It was shown recently that when the underlying pairwise preferences are acyclic, several algorithms including the Rank Centrality algorithm, the Matrix Borda algorithm, and the SVM-Rank Aggregation algorithm succeed in recovering a ranking that minimizes a global pairwise disagreement error (Rajkumar and Agarwal, 2014). In this paper, we consider settings where pairwise preferences can contain cycles. In such settings, one may still like to be able to recover 'good' items at the top of the ranking. For example, if a Condorcet winner exists that beats every other item, it is natural to ask that this be ranked at the top. More generally, several tournament solution concepts such as the top cycle, Copeland set, Markov set and others have been proposed in the social choice literature for choosing a set of winners in the presence of cycles. We show that existing algorithms can fail to perform well in terms of ranking Condorcet winners and various natural tournament solution sets at the top. We then give alternative ranking algorithms that provably rank Condorcet winners, top cycles, and other tournament solution sets of interest at the top. In all cases, we give finite sample complexity bounds for our algorithms to recover such winners. As a by-product of our analysis, we also obtain an improved sample complexity bound for the Rank Centrality algorithm to recover an optimal ranking under a Bradley-Terry-Luce (BTL) condition, which answers an open question of Rajkumar and Agarwal (2014).

/pdf/ranking-from-stochastic-pairwise-preferences-recovering-f2320lq5ux.pdf

Arun Rajkumar

Papers

A Statistical Convergence Perspective of Algorithms for Rank Aggregation from Pairwise Data

A Differentially Private Stochastic Gradient Descent Algorithm for Multiparty Classification

Multi-source iterative adaptation for cross-domain classification

Dueling Bandits: Beyond Condorcet Winners to General Tournament Solutions

Ranking from Stochastic Pairwise Preferences: Recovering Condorcet Winners and Tournament Solution Sets at the Top