arXiv subjects

Mikhail Belkin

Publications and source records attributed to Mikhail Belkin.

90 records · Page 5Linked to original sources

arXiv2017

Electrical Tuning of Polarizaion-state Using Graphene-Integrated Metasurfaces

Plasmonic metasurfaces have been employed for tuning and controlling light enabling various novel applications. Their appeal is enhanced with the incorporation of an active element with the metasurfaces paving the way for dynamic control. In this letter, we realize a dynamic polarization state generator using graphene-integrated anisotropic metasurface (GIAM), where a linear incidence polarization is controllably converted into an elliptical one. The anisotropic metasurface leads to an intrinsic polarization conversion when illuminated with non-orthogonal incident polarization. Additionally, the single-layer graphene allows us to tune the phase and intensity of the reflected light on the application of a gate voltage, enabling dynamic polarization control. The stokes polarization parameters of the reflected light are measured using rotating polarizer method and it is demonstrated that a large change in the ellipticity as well as orientation angle can be induced by this device. We also provide experimental evidence that the titl angle can change independent of the ellipticity going from positive values to nearly zero to negative values while ellipticity is constant.

physics.optics↗

arXiv2016

The Hidden Convexity of Spectral Clustering

In recent years, spectral clustering has become a standard method for data analysis used in a broad range of applications. In this paper we propose a new class of algorithms for multiway spectral clustering based on optimization of a certain "contrast function" over the unit sphere. These algorithms, partly inspired by certain Independent Component Analysis techniques, are simple, easy to implement and efficient. Geometrically, the proposed algorithms can be interpreted as hidden basis recovery by means of function optimization. We give a complete characterization of the contrast functions admissible for provable basis recovery. We show how these conditions can be interpreted as a "hidden convexity" of our optimization problem on the sphere; interestingly, we use efficient convex maximization rather than the more common convex minimization. We also show encouraging experimental results on real and simulated data.

cs.LG↗

arXiv2016

Learning Privately from Multiparty Data

Learning a classifier from private data collected by multiple parties is an important problem that has many potential applications. How can we build an accurate and differentially private global classifier by combining locally-trained classifiers from different parties, without access to any party's private data? We propose to transfer the `knowledge' of the local classifier ensemble by first creating labeled data from auxiliary unlabeled data, and then train a global $ε$-differentially private classifier. We show that majority voting is too sensitive and therefore propose a new risk weighted by class probabilities estimated from the ensemble. Relative to a non-private solution, our private solution has a generalization error bounded by $O(ε^{-2}M^{-2})$ where $M$ is the number of parties. This allows strong privacy without performance loss when $M$ is large, such as in crowdsensing applications. We demonstrate the performance of our method with realistic tasks of activity recognition, network intrusion detection, and malicious URL detection.

cs.LG↗

arXiv2015

A Pseudo-Euclidean Iteration for Optimal Recovery in Noisy ICA

Independent Component Analysis (ICA) is a popular model for blind signal separation. The ICA model assumes that a number of independent source signals are linearly mixed to form the observed signals. We propose a new algorithm, PEGI (for pseudo-Euclidean Gradient Iteration), for provable model recovery for ICA with Gaussian noise. The main technical innovation of the algorithm is to use a fixed point iteration in a pseudo-Euclidean (indefinite "inner product") space. The use of this indefinite "inner product" resolves technical issues common to several existing algorithms for noisy ICA. This leads to an algorithm which is conceptually simple, efficient and accurate in testing. Our second contribution is combining PEGI with the analysis of objectives for optimal recovery in the noisy ICA model. It has been observed that the direct approach of demixing with the inverse of the mixing matrix is suboptimal for signal recovery in terms of the natural Signal to Interference plus Noise Ratio (SINR) criterion. There have been several partial solutions proposed in the ICA literature. It turns out that any solution to the mixing matrix reconstruction problem can be used to construct an SINR-optimal ICA demixing, despite the fact that SINR itself cannot be computed from data. That allows us to obtain a practical and provably SINR-optimal recovery method for ICA with arbitrary Gaussian noise.

cs.LG↗

arXiv2015

Beyond Hartigan Consistency: Merge Distortion Metric for Hierarchical Clustering

Hierarchical clustering is a popular method for analyzing data which associates a tree to a dataset. Hartigan consistency has been used extensively as a framework to analyze such clustering algorithms from a statistical point of view. Still, as we show in the paper, a tree which is Hartigan consistent with a given density can look very different than the correct limit tree. Specifically, Hartigan consistency permits two types of undesirable configurations which we term over-segmentation and improper nesting. Moreover, Hartigan consistency is a limit property and does not directly quantify difference between trees. In this paper we identify two limit properties, separation and minimality, which address both over-segmentation and improper nesting and together imply (but are not implied by) Hartigan consistency. We proceed to introduce a merge distortion metric between hierarchical clusterings and show that convergence in our distance implies both separation and minimality. We also prove that uniform separation and minimality imply convergence in the merge distortion metric. Furthermore, we show that our merge distortion metric is stable under perturbations of the density. Finally, we demonstrate applicability of these concepts by proving convergence results for two clustering algorithms. First, we show convergence (and hence separation and minimality) of the recent robust single linkage algorithm of Chaudhuri and Dasgupta (2010). Second, we provide convergence results on manifolds for topological split tree clustering.

stat.ML↗

arXiv2015

Probabilistic Zero-shot Classification with Semantic Rankings

In this paper we propose a non-metric ranking-based representation of semantic similarity that allows natural aggregation of semantic information from multiple heterogeneous sources. We apply the ranking-based representation to zero-shot learning problems, and present deterministic and probabilistic zero-shot classifiers which can be built from pre-trained classifiers without retraining. We demonstrate their the advantages on two large real-world image datasets. In particular, we show that aggregating different sources of semantic information, including crowd-sourcing, leads to more accurate classification.

cs.LG↗

arXiv2015

Crowd-ML: A Privacy-Preserving Learning Framework for a Crowd of Smart Devices

Smart devices with built-in sensors, computational capabilities, and network connectivity have become increasingly pervasive. The crowds of smart devices offer opportunities to collectively sense and perform computing tasks in an unprecedented scale. This paper presents Crowd-ML, a privacy-preserving machine learning framework for a crowd of smart devices, which can solve a wide range of learning problems for crowdsensing data with differential privacy guarantees. Crowd-ML endows a crowdsensing system with an ability to learn classifiers or predictors online from crowdsensing data privately with minimal computational overheads on devices and servers, suitable for a practical and large-scale employment of the framework. We analyze the performance and the scalability of Crowd-ML, and implement the system with off-the-shelf smartphones as a proof of concept. We demonstrate the advantages of Crowd-ML with real and simulated experiments under various conditions.

cs.LG↗

arXiv2014

The More, the Merrier: the Blessing of Dimensionality for Learning Large Gaussian Mixtures

In this paper we show that very large mixtures of Gaussians are efficiently learnable in high dimension. More precisely, we prove that a mixture with known identical covariance matrices whose number of components is a polynomial of any fixed degree in the dimension n is polynomially learnable as long as a certain non-degeneracy condition on the means is satisfied. It turns out that this condition is generic in the sense of smoothed complexity, as soon as the dimensionality of the space is high enough. Moreover, we prove that no such condition can possibly exist in low dimension and the problem of learning the parameters is generically hard. In contrast, much of the existing work on Gaussian Mixtures relies on low-dimensional projections and thus hits an artificial barrier. Our main result on mixture recovery relies on a new "Poissonization"-based technique, which transforms a mixture of Gaussians to a linear map of a product distribution. The problem of learning this map can be efficiently solved using some recent results on tensor decompositions and Independent Component Analysis (ICA), thus giving an algorithm for recovering the mixture. In addition, we combine our low-dimensional hardness results for Gaussian mixtures with Poissonization to show how to embed difficult instances of low-dimensional Gaussian mixtures into the ICA setting, thus establishing exponential information-theoretic lower bounds for underdetermined ICA in low dimension. To the best of our knowledge, this is the first such result in the literature. In addition to contributing to the problem of Gaussian mixture learning, we believe that this work is among the first steps toward better understanding the rare phenomenon of the "blessing of dimensionality" in the computational aspects of statistical inference.

cs.LG↗

arXiv2013

Blind Signal Separation in the Presence of Gaussian Noise

A prototypical blind signal separation problem is the so-called cocktail party problem, with n people talking simultaneously and n different microphones within a room. The goal is to recover each speech signal from the microphone inputs. Mathematically this can be modeled by assuming that we are given samples from an n-dimensional random variable X=AS, where S is a vector whose coordinates are independent random variables corresponding to each speaker. The objective is to recover the matrix A^{-1} given random samples from X. A range of techniques collectively known as Independent Component Analysis (ICA) have been proposed to address this problem in the signal processing and machine learning literature. Many of these techniques are based on using the kurtosis or other cumulants to recover the components. In this paper we propose a new algorithm for solving the blind signal separation problem in the presence of additive Gaussian noise, when we are given samples from X=AS+η, where ηis drawn from an unknown, not necessarily spherical n-dimensional Gaussian distribution. Our approach is based on a method for decorrelating a sample with additive Gaussian noise under the assumption that the underlying distribution is a linear transformation of a distribution with independent components. Our decorrelation routine is based on the properties of cumulant tensors and can be combined with any standard cumulant-based method for ICA to get an algorithm that is provably robust in the presence of Gaussian noise. We derive polynomial bounds for the sample complexity and error propagation of our method.

cs.LG↗

arXiv2013

Inverse Density as an Inverse Problem: The Fredholm Equation Approach

In this paper we address the problem of estimating the ratio $\frac{q}{p}$ where $p$ is a density function and $q$ is another density, or, more generally an arbitrary function. Knowing or approximating this ratio is needed in various problems of inference and integration, in particular, when one needs to average a function with respect to one probability distribution, given a sample from another. It is often referred as {\it importance sampling} in statistical inference and is also closely related to the problem of {\it covariate shift} in transfer learning as well as to various MCMC methods. It may also be useful for separating the underlying geometry of a space, say a manifold, from the density function defined on it. Our approach is based on reformulating the problem of estimating $\frac{q}{p}$ as an inverse problem in terms of an integral operator corresponding to a kernel, and thus reducing it to an integral equation, known as the Fredholm problem of the first kind. This formulation, combined with the techniques of regularization and kernel methods, leads to a principled kernel-based framework for constructing algorithms and for analyzing them theoretically. The resulting family of algorithms (FIRE, for Fredholm Inverse Regularized Estimator) is flexible, simple and easy to implement. We provide detailed theoretical analysis including concentration bounds and convergence rates for the Gaussian kernel in the case of densities defined on $\R^d$, compact domains in $\R^d$ and smooth $d$-dimensional sub-manifolds of the Euclidean space. We also show experimental results including applications to classification and semi-supervised learning within the covariate shift framework and demonstrate some encouraging experimental comparisons. We also show how the parameters of our algorithms can be chosen in a completely unsupervised manner.

cs.LG↗

arXiv2012

Graph Laplacians on Singular Manifolds: Toward understanding complex spaces: graph Laplacians on manifolds with singularities and boundaries

Recently, much of the existing work in manifold learning has been done under the assumption that the data is sampled from a manifold without boundaries and singularities or that the functions of interest are evaluated away from such points. At the same time, it can be argued that singularities and boundaries are an important aspect of the geometry of realistic data. In this paper we consider the behavior of graph Laplacians at points at or near boundaries and two main types of other singularities: intersections, where different manifolds come together and sharp "edges", where a manifold sharply changes direction. We show that the behavior of graph Laplacian near these singularities is quite different from that in the interior of the manifolds. In fact, a phenomenon somewhat reminiscent of the Gibbs effect in the analysis of Fourier series, can be observed in the behavior of graph Laplacian near such points. Unlike in the interior of the domain, where graph Laplacian converges to the Laplace-Beltrami operator, near singularities graph Laplacian tends to a first-order differential operator, which exhibits different scaling behavior as a function of the kernel width. One important implication is that while points near the singularities occupy only a small part of the total volume, the difference in scaling results in a disproportionately large contribution to the total behavior. Another significant finding is that while the scaling behavior of the operator is the same near different types of singularities, they are very distinct at a more refined level of analysis. We believe that a comprehensive understanding of these structures in addition to the standard case of a smooth manifold can take us a long way toward better methods for analysis of complex non-linear data and can lead to significant progress in algorithm design.

cs.AI↗

arXiv2011

Behavior of Graph Laplacians on Manifolds with Boundary

In manifold learning, algorithms based on graph Laplacians constructed from data have received considerable attention both in practical applications and theoretical analysis. In particular, the convergence of graph Laplacians obtained from sampled data to certain continuous operators has become an active research topic recently. Most of the existing work has been done under the assumption that the data is sampled from a manifold without boundary or that the functions of interests are evaluated at a point away from the boundary. However, the question of boundary behavior is of considerable practical and theoretical interest. In this paper we provide an analysis of the behavior of graph Laplacians at a point near or on the boundary, discuss their convergence rates and their implications and provide some numerical results. It turns out that while points near the boundary occupy only a small part of the total volume of a manifold, the behavior of graph Laplacian there has different scaling properties from its behavior elsewhere on the manifold, with global effects on the whole manifold, an observation with potentially important implications for the general problem of learning on manifolds.

cs.LG↗

arXiv2010

Learning Gaussian Mixtures with Arbitrary Separation

In this paper we present a method for learning the parameters of a mixture of $k$ identical spherical Gaussians in $n$-dimensional space with an arbitrarily small separation between the components. Our algorithm is polynomial in all parameters other than $k$. The algorithm is based on an appropriate grid search over the space of parameters. The theoretical analysis of the algorithm hinges on a reduction of the problem to 1 dimension and showing that two 1-dimensional mixtures whose densities are close in the $L^2$ norm must have similar means and mixing coefficients. To produce such a lower bound for the $L^2$ norm in terms of the distances between the corresponding means, we analyze the behavior of the Fourier transform of a mixture of Gaussians in 1 dimension around the origin, which turns out to be closely related to the properties of the Vandermonde matrix obtained from the component means. Analysis of this matrix together with basic function approximation results allows us to provide a lower bound for the norm of the mixture in the Fourier domain. In recent years much research has been aimed at understanding the computational aspects of learning parameters of Gaussians mixture distributions in high dimension. To the best of our knowledge all existing work on learning parameters of Gaussian mixtures assumes minimum separation between components of the mixture which is an increasing function of either the dimension of the space $n$ or the number of components $k$. In our paper we prove the first result showing that parameters of a $n$-dimensional Gaussian mixture model with arbitrarily small component separation can be learned in time polynomial in $n$.

cs.LG↗

arXiv2010

Polynomial Learning of Distribution Families

The question of polynomial learnability of probability distributions, particularly Gaussian mixture distributions, has recently received significant attention in theoretical computer science and machine learning. However, despite major progress, the general question of polynomial learnability of Gaussian mixture distributions still remained open. The current work resolves the question of polynomial learnability for Gaussian mixtures in high dimension with an arbitrary fixed number of components. The result on learning Gaussian mixtures relies on an analysis of distributions belonging to what we call "polynomial families" in low dimension. These families are characterized by their moments being polynomial in parameters and include almost all common probability distributions as well as their mixtures and products. Using tools from real algebraic geometry, we show that parameters of any distribution belonging to such a family can be learned in polynomial time and using a polynomial number of sample points. The result on learning polynomial families is quite general and is of independent interest. To estimate parameters of a Gaussian mixture distribution in high dimensions, we provide a deterministic algorithm for dimensionality reduction. This allows us to reduce learning a high-dimensional mixture to a polynomial number of parameter estimations in low dimension. Combining this reduction with the results on polynomial families yields our result on learning arbitrary Gaussian mixtures in high dimensions.

cs.LG↗

arXiv2009

Data spectroscopy: Eigenspaces of convolution operators and clustering

This paper focuses on obtaining clustering information about a distribution from its i.i.d. samples. We develop theoretical results to understand and use clustering information contained in the eigenvectors of data adjacency matrices based on a radial kernel function with a sufficiently fast tail decay. In particular, we provide population analyses to gain insights into which eigenvectors should be used and when the clustering information for the distribution can be recovered from the sample. We learn that a fixed number of top eigenvectors might at the same time contain redundant clustering information and miss relevant clustering information. We use this insight to design the data spectroscopic clustering (DaSpec) algorithm that utilizes properly selected eigenvectors to determine the number of clusters automatically and to group the data accordingly. Our findings extend the intuitions underlying existing spectral techniques such as spectral clustering and Kernel Principal Components Analysis, and provide new understanding into their usability and modes of failure. Simulation studies and experiments on real-world data are conducted to show the potential of our algorithm. In particular, DaSpec is found to handle unbalanced groups and recover clusters of different shapes better than the competing methods.

stat.ML↗

arXiv2009

Laplacian Support Vector Machines Trained in the Primal

In the last few years, due to the growing ubiquity of unlabeled data, much effort has been spent by the machine learning community to develop better understanding and improve the quality of classifiers exploiting unlabeled data. Following the manifold regularization approach, Laplacian Support Vector Machines (LapSVMs) have shown the state of the art performance in semi--supervised classification. In this paper we present two strategies to solve the primal LapSVM problem, in order to overcome some issues of the original dual formulation. Whereas training a LapSVM in the dual requires two steps, using the primal form allows us to collapse training to a single step. Moreover, the computational complexity of the training algorithm is reduced from O(n^3) to O(n^2) using preconditioned conjugate gradient, where n is the combined number of labeled and unlabeled examples. We speed up training by using an early stopping strategy based on the prediction on unlabeled data or, if available, on labeled validation examples. This allows the algorithm to quickly compute approximate solutions with roughly the same classification accuracy as the optimal ones, considerably reducing the training time. Due to its simplicity, training LapSVM in the primal can be the starting point for additional enhancements of the original LapSVM formulation, such as those for dealing with large datasets. We present an extensive experimental evaluation on real world data showing the benefits of the proposed approach.

stat.ML↗

arXiv2008

Consistency of spectral clustering

Consistency is a key property of all statistical procedures analyzing randomly sampled data. Surprisingly, despite decades of work, little is known about consistency of most clustering algorithms. In this paper we investigate consistency of the popular family of spectral clustering algorithms, which clusters the data with the help of eigenvectors of graph Laplacian matrices. We develop new methods to establish that, for increasing sample size, those eigenvectors converge to the eigenvectors of certain limit operators. As a result, we can prove that one of the two major classes of spectral clustering (normalized clustering) converges under very general conditions, while the other (unnormalized clustering) is only consistent under strong additional assumptions, which are not always satisfied in real data. We conclude that our analysis provides strong evidence for the superiority of normalized spectral clustering.

math.ST↗

arXiv2002

Using eigenvectors of the bigram graph to infer morpheme identity

This paper describes the results of some experiments exploring statistical methods to infer syntactic behavior of words and morphemes from a raw corpus in an unsupervised fashion. It shares certain points in common with Brown et al (1992) and work that has grown out of that: it employs statistical techniques to analyze syntactic behavior based on what words occur adjacent to a given word. However, we use an eigenvector decomposition of a nearest-neighbor graph to produce a two-dimensional rendering of the words of a corpus in which words of the same syntactic category tend to form neighborhoods. We exploit this technique for extending the value of automatic learning of morphology. In particular, we look at the suffixes derived from a corpus by unsupervised learning of morphology, and we ask which of these suffixes have a consistent syntactic function (e.g., in English, -tion is primarily a mark of nouns, but -s marks both noun plurals and 3rd person present on verbs), and we determine that this method works well for this task.

cs.CL↗