arXiv subjects

Shai Ben-David

Publications and source records attributed to Shai Ben-David.

33 records · Page 2Linked to original sources

arXiv2018

Provably noise-robust, regularised $k$-means clustering

We consider the problem of clustering in the presence of noise. That is, when on top of cluster structure, the data also contains a subset of \emph{unstructured} points. Our goal is to detect the clusters despite the presence of many unstructured points. Any algorithm that achieves this goal is noise-robust. We consider a regularisation method which converts any center-based clustering objective into a noise-robust one. We focus on the $k$-means objective and we prove that the regularised version of $k$-means is NP-Hard even for $k=1$. We consider two algorithms based on the convex (sdp and lp) relaxation of the regularised objective and prove robustness guarantees for both. The sdp and lp relaxation of the standard (non-regularised) $k$-means objective has been previously studied by [ABC+15]. Under the stochastic ball model of the data they show that the sdp-based algorithm recovers the underlying structure as long as the balls are separated by $δ> 2\sqrt{2} + ε$. We improve upon this result in two ways. First, we show recovery even for $δ> 2 + ε$. Second, our regularised algorithm recovers the balls even in the presence of noise so long as the number of noisy points is not too large. We complement our theoretical analysis with simulations and analyse the effect of various parameters like regularization constant, noise-level etc. on the performance of our algorithm. In the presence of noise, our algorithm performs better than $k$-means++ on MNIST.

cs.LG↗

arXiv2018

Sample-Efficient Learning of Mixtures

We consider PAC learning of probability distributions (a.k.a. density estimation), where we are given an i.i.d. sample generated from an unknown target distribution, and want to output a distribution that is close to the target in total variation distance. Let $\mathcal F$ be an arbitrary class of probability distributions, and let $\mathcal{F}^k$ denote the class of $k$-mixtures of elements of $\mathcal F$. Assuming the existence of a method for learning $\mathcal F$ with sample complexity $m_{\mathcal{F}}(ε)$, we provide a method for learning $\mathcal F^k$ with sample complexity $O({k\log k \cdot m_{\mathcal F}(ε) }/{ε^{2}})$. Our mixture learning algorithm has the property that, if the $\mathcal F$-learner is proper/agnostic, then the $\mathcal F^k$-learner would be proper/agnostic as well. This general result enables us to improve the best known sample complexity upper bounds for a variety of important mixture classes. First, we show that the class of mixtures of $k$ axis-aligned Gaussians in $\mathbb{R}^d$ is PAC-learnable in the agnostic setting with $\widetilde{O}({kd}/{ε^ 4})$ samples, which is tight in $k$ and $d$ up to logarithmic factors. Second, we show that the class of mixtures of $k$ Gaussians in $\mathbb{R}^d$ is PAC-learnable in the agnostic setting with sample complexity $\widetilde{O}({kd^2}/{ε^ 4})$, which improves the previous known bounds of $\widetilde{O}({k^3d^2}/{ε^ 4})$ and $\widetilde{O}(k^4d^4/ε^ 2)$ in its dependence on $k$ and $d$. Finally, we show that the class of mixtures of $k$ log-concave distributions over $\mathbb{R}^d$ is PAC-learnable using $\widetilde{O}(d^{(d+5)/2}ε^{-(d+9)/2}k)$ samples.

cs.LG↗

arXiv2018

Clustering - What Both Theoreticians and Practitioners are Doing Wrong

Unsupervised learning is widely recognized as one of the most important challenges facing machine learning nowa- days. However, in spite of hundreds of papers on the topic being published every year, current theoretical understanding and practical implementations of such tasks, in particular of clustering, is very rudimentary. This note focuses on clustering. I claim that the most signif- icant challenge for clustering is model selection. In contrast with other common computational tasks, for clustering, dif- ferent algorithms often yield drastically different outcomes. Therefore, the choice of a clustering algorithm, and their pa- rameters (like the number of clusters) may play a crucial role in the usefulness of an output clustering solution. However, currently there exists no methodical guidance for clustering tool-selection for a given clustering task. Practitioners pick the algorithms they use without awareness to the implications of their choices and the vast majority of theory of clustering papers focus on providing savings to the resources needed to solve optimization problems that arise from picking some concrete clustering objective. Saving that pale in com- parison to the costs of mismatch between those objectives and the intended use of clustering results. I argue the severity of this problem and describe some recent proposals aiming to address this crucial lacuna.

cs.LG↗

arXiv2017

A learning problem that is independent of the set theory ZFC axioms

We consider the following statistical estimation problem: given a family F of real valued functions over some domain X and an i.i.d. sample drawn from an unknown distribution P over X, find h in F such that the expectation of h w.r.t. P is probably approximately equal to the supremum over expectations on members of F. This Expectation Maximization (EMX) problem captures many well studied learning problems; in fact, it is equivalent to Vapnik's general setting of learning. Surprisingly, we show that the EMX learnability, as well as the learning rates of some basic class F, depend on the cardinality of the continuum and is therefore independent of the set theory ZFC axioms (that are widely accepted as a formalization of the notion of a mathematical proof). We focus on the case where the functions in F are Boolean, which generalizes classification problems. We study the interaction between the statistical sample complexity of F and its combinatorial structure. We introduce a new version of sample compression schemes and show that it characterizes EMX learnability for a wide family of classes. However, we show that for the class of finite subsets of the real line, the existence of such compression schemes is independent of set theory. We conclude that the learnability of that class with respect to the family of probability distributions of countable support is independent of the set theory ZFC axioms. We also explore the existence of a "VC-dimension-like" parameter that captures learnability in this setting. Our results imply that that there exist no "finitary" combinatorial parameter that characterizes EMX learnability in a way similar to the VC-dimension based characterization of binary valued classification problems.

cs.LG↗

arXiv2016

Clustering with Same-Cluster Queries

We propose a framework for Semi-Supervised Active Clustering framework (SSAC), where the learner is allowed to interact with a domain expert, asking whether two given instances belong to the same cluster or not. We study the query and computational complexity of clustering in this framework. We consider a setting where the expert conforms to a center-based clustering with a notion of margin. We show that there is a trade off between computational complexity and query complexity; We prove that for the case of $k$-means clustering (i.e., when the expert conforms to a solution of $k$-means), having access to relatively few such queries allows efficient solutions to otherwise NP hard problems. In particular, we provide a probabilistic polynomial-time (BPP) algorithm for clustering in this setting that asks $O\big(k^2\log k + k\log n)$ same-cluster queries and runs with time complexity $O\big(kn\log n)$ (where $k$ is the number of clusters and $n$ is the number of instances). The algorithm succeeds with high probability for data satisfying margin conditions under which, without queries, we show that the problem is NP hard. We also prove a lower bound on the number of queries needed to have a computationally efficient clustering algorithm in this setting.

cs.LG↗

arXiv2016

Weighted Clustering

One of the most prominent challenges in clustering is "the user's dilemma," which is the problem of selecting an appropriate clustering algorithm for a specific task. A formal approach for addressing this problem relies on the identification of succinct, user-friendly properties that formally capture when certain clustering methods are preferred over others. Until now these properties focused on advantages of classical Linkage-Based algorithms, failing to identify when other clustering paradigms, such as popular center-based methods, are preferable. We present surprisingly simple new properties that delineate the differences between common clustering paradigms, which clearly and formally demonstrates advantages of center-based approaches for some applications. These properties address how sensitive algorithms are to changes in element frequencies, which we capture in a generalized setting where every element is associated with a real-valued weight.

cs.LG↗

arXiv2016

Multi-task and Lifelong Learning of Kernels

We consider a problem of learning kernels for use in SVM classification in the multi-task and lifelong scenarios and provide generalization bounds on the error of a large margin classifier. Our results show that, under mild conditions on the family of kernels used for learning, solving several related tasks simultaneously is beneficial over single task learning. In particular, as the number of observed tasks grows, assuming that in the considered family of kernels there exists one that yields low approximation error on all tasks, the overhead associated with learning such a kernel vanishes and the complexity converges to that of learning when this good kernel is given to the learner.

stat.ML↗

arXiv2015

Clustering is Easy When ....What?

It is well known that most of the common clustering objectives are NP-hard to optimize. In practice, however, clustering is being routinely carried out. One approach for providing theoretical understanding of this seeming discrepancy is to come up with notions of clusterability that distinguish realistically interesting input data from worst-case data sets. The hope is that there will be clustering algorithms that are provably efficient on such "clusterable" instances. This paper addresses the thesis that the computational hardness of clustering tasks goes away for inputs that one really cares about. In other words, that "Clustering is difficult only when it does not matter" (the \emph{CDNM thesis} for short). I wish to present a a critical bird's eye overview of the results published on this issue so far and to call attention to the gap between available and desirable results on this issue. A longer, more detailed version of this note is available as arXiv:1507.05307. I discuss which requirements should be met in order to provide formal support to the the CDNM thesis and then examine existing results in view of these requirements and list some significant unsolved research challenges in that direction.

stat.ML↗

arXiv2015

2 Notes on Classes with Vapnik-Chervonenkis Dimension 1

The Vapnik-Chervonenkis dimension is a combinatorial parameter that reflects the "complexity" of a set of sets (a.k.a. concept classes). It has been introduced by Vapnik and Chervonenkis in their seminal 1971 paper and has since found many applications, most notably in machine learning theory and in computational geometry. Arguably the most influential consequence of the VC analysis is the fundamental theorem of statistical machine learning, stating that a concept class is learnable (in some precise sense) if and only if its VC-dimension is finite. Furthermore, for such classes a most simple learning rule - empirical risk minimization (ERM) - is guaranteed to succeed. The simplest non-trivial structures, in terms of the VC-dimension, are the classes (i.e., sets of subsets) for which that dimension is 1. In this note we show a couple of curious results concerning such classes. The first result shows that such classes share a very simple structure, and, as a corollary, the labeling information contained in any sample labeled by such a class can be compressed into a single instance. The second result shows that due to some subtle measurability issues, in spite of the above mentioned fundamental theorem, there are classes of dimension 1 for which an ERM learning rule fails miserably.

cs.LG↗

arXiv2015

Representation Learning for Clustering: A Statistical Framework

We address the problem of communicating domain knowledge from a user to the designer of a clustering algorithm. We propose a protocol in which the user provides a clustering of a relatively small random sample of a data set. The algorithm designer then uses that sample to come up with a data representation under which $k$-means clustering results in a clustering (of the full data set) that is aligned with the user's clustering. We provide a formal statistical model for analyzing the sample complexity of learning a clustering representation with this paradigm. We then introduce a notion of capacity of a class of possible representations, in the spirit of the VC-dimension, showing that classes of representations that have finite such dimension can be successfully learned with sample size error bounds, and end our discussion with an analysis of that dimension for classes of representations induced by linear embeddings.

stat.ML↗

arXiv2015

Computational Feasibility of Clustering under Clusterability Assumptions

It is well known that most of the common clustering objectives are NP-hard to optimize. In practice, however, clustering is being routinely carried out. One approach for providing theoretical understanding of this seeming discrepancy is to come up with notions of clusterability that distinguish realistically interesting input data from worst-case data sets. The hope is that there will be clustering algorithms that are provably efficient on such 'clusterable' instances. In other words, hope that "Clustering is difficult only when it does not matter" (CDNM thesis, for short). We believe that to some extent this may indeed be the case. This paper provides a survey of recent papers along this line of research and a critical evaluation their results. Our bottom line conclusion is that that CDNM thesis is still far from being formally substantiated. We start by discussing which requirements should be met in order to provide formal support the validity of the CDNM thesis. In particular, we list some implied requirements for notions of clusterability. We then examine existing results in view of those requirements and outline some research challenges and open questions.

cs.CC↗

arXiv2014

Multiclass learnability and the ERM principle

We study the sample complexity of multiclass prediction in several learning settings. For the PAC setting our analysis reveals a surprising phenomenon: In sharp contrast to binary classification, we show that there exist multiclass hypothesis classes for which some Empirical Risk Minimizers (ERM learners) have lower sample complexity than others. Furthermore, there are classes that are learnable by some ERM learners, while other ERM learners will fail to learn them. We propose a principle for designing good ERM learners, and use this principle to prove tight bounds on the sample complexity of learning {\em symmetric} multiclass hypothesis classes---classes that are invariant under permutations of label names. We further provide a characterization of mistake and regret bounds for multiclass learning in the online setting and the bandit setting, using new generalizations of Littlestone's dimension.

cs.LG↗

arXiv2012

Minimizing The Misclassification Error Rate Using a Surrogate Convex Loss

We carefully study how well minimizing convex surrogate loss functions, corresponds to minimizing the misclassification error rate for the problem of binary classification with linear predictors. In particular, we show that amongst all convex surrogate losses, the hinge loss gives essentially the best possible bound, of all convex loss functions, for the misclassification error rate of the resulting linear predictor in terms of the best possible margin error rate. We also provide lower bounds for specific convex surrogates that show how different commonly used losses qualitatively differ from each other.

cs.LG↗

arXiv2012

A Uniqueness Theorem for Clustering

Despite the widespread use of Clustering, there is distressingly little general theory of clustering available. Questions like "What distinguishes a clustering of data from other data partitioning?", "Are there any principles governing all clustering paradigms?", "How should a user choose an appropriate clustering algorithm for a particular task?", etc. are almost completely unanswered by the existing body of clustering literature. We consider an axiomatic approach to the theory of Clustering. We adopt the framework of Kleinberg, [Kle03]. By relaxing one of Kleinberg's clustering axioms, we sidestep his impossibility result and arrive at a consistent set of axioms. We suggest to extend these axioms, aiming to provide an axiomatic taxonomy of clustering paradigms. Such a taxonomy should provide users some guidance concerning the choice of the appropriate clustering paradigm for a given task. The main result of this paper is a set of abstract properties that characterize the Single-Linkage clustering function. This characterization result provides new insight into the properties of desired data groupings that make Single-Linkage the appropriate choice. We conclude by considering a taxonomy of clustering functions based on abstract properties that each satisfies.

cs.LG↗

arXiv2009

Learning Low-Density Separators

We define a novel, basic, unsupervised learning problem - learning the lowest density homogeneous hyperplane separator of an unknown probability distribution. This task is relevant to several problems in machine learning, such as semi-supervised learning and clustering stability. We investigate the question of existence of a universally consistent algorithm for this problem. We propose two natural learning paradigms and prove that, on input unlabeled random samples generated by any member of a rich family of distributions, they are guaranteed to converge to the optimal separator for that distribution. We complement this result by showing that no learning algorithm for our task can achieve uniform learning rates (that are independent of the data generating distribution).

cs.LG↗