total 215329took 0.16s

Gaussian Process Optimization in the Bandit Setting: No Regret and Experimental DesignDec 21 2009Jun 09 2010Many applications require optimizing an unknown, noisy function that is expensive to evaluate. We formalize this task as a multi-armed bandit problem, where the payoff function is either sampled from a Gaussian process (GP) or has low RKHS norm. We resolve ... More

Calibration, Entropy Rates, and Memory in Language ModelsJun 11 2019Building accurate language models that capture meaningful long-term dependencies is a core challenge in natural language processing. Towards this end, we present a calibration-based approach to measure long-term discrepancies between a generative sequence ... More

Learning mixtures of spherical Gaussians: moment methods and spectral decompositionsJun 25 2012Oct 28 2012This work provides a computationally efficient and statistically consistent moment-based estimator for mixtures of spherical Gaussians. Under the condition that component means are in general position, a simple spectral decomposition technique yields ... More

Super-Resolution Off the GridSep 26 2015Super-resolution is the problem of recovering a superposition of point sources using bandlimited measurements, which may be corrupted with noise. This signal processing problem arises in numerous imaging problems, ranging from astronomy to biology to ... More

Random design analysis of ridge regressionJun 13 2011Mar 25 2014This work gives a simultaneous analysis of both the ordinary least squares estimator and the ridge regression estimator in the random design setting under mild assumptions on the covariate/response distributions. In particular, the analysis provides sharp ... More

Provable Efficient Online Matrix Completion via Non-convex Stochastic Gradient DescentMay 26 2016Matrix completion, where we wish to recover a low rank matrix by observing a few entries from it, is a widely studied problem in both theory and practice with wide applications. Most of the provable algorithms so far on this problem have been restricted ... More

Learning Mixtures of Gaussians in High DimensionsMar 02 2015Mar 10 2015Efficiently learning mixture of Gaussians is a fundamental problem in statistics and learning theory. Given samples coming from a random one out of k Gaussian distributions in Rn, the learning problem asks to estimate the means and the covariance matrices ... More

An Optimal Dynamic Mechanism for Multi-Armed Bandit ProcessesJan 26 2010Oct 15 2010We consider the problem of revenue-optimal dynamic mechanism design in settings where agents' types evolve over time as a function of their (both public and private) experience with items that are auctioned repeatedly over an infinite horizon. A central ... More

A Method of Moments for Mixture Models and Hidden Markov ModelsMar 03 2012Sep 05 2012Mixture models are a fundamental tool in applied statistics and machine learning for treating data taken from multiple subpopulations. The current practice for estimating the parameters of such models relies on local search heuristics (e.g., the EM algorithm) ... More

A tail inequality for quadratic forms of subgaussian random vectorsOct 13 2011We prove an exponential probability tail inequality for positive semidefinite quadratic forms in a subgaussian random vector. The bound is analogous to one that holds when the vector has independent Gaussian entries.

Robust Matrix Decomposition with OutliersNov 05 2010Dec 04 2010Suppose a given observation matrix can be decomposed as the sum of a low-rank matrix and a sparse matrix (outliers), and the goal is to recover these individual components from the observed sum. Such additive decompositions have applications in a variety ... More

Identifiability and Unmixing of Latent Parse TreesJun 14 2012This paper explores unsupervised learning of parsing models along two directions. First, which models are identifiable from infinite data? We use a general technique for numerically checking identifiability based on the rank of a Jacobian matrix, and ... More

A Spectral Algorithm for Learning Hidden Markov ModelsNov 26 2008Jul 06 2012Hidden Markov Models (HMMs) are one of the most fundamental and widely used statistical tools for modeling discrete time series. In general, learning HMMs from data is computationally hard (under cryptographic assumptions), and practitioners typically ... More

Dimension-free tail inequalities for sums of random matricesApr 09 2011Apr 16 2011We derive exponential tail inequalities for sums of random matrices with no dependence on the explicit matrix dimensions. These are similar to the matrix versions of the Chernoff bound and Bernstein inequality except with the explicit matrix dimensions ... More

Analysis of a randomized approximation scheme for matrix multiplicationNov 23 2012This note gives a simple analysis of a randomized approximation scheme for matrix multiplication proposed by Sarlos (2006) based on a random rotation followed by uniform column sampling. The result follows from a matrix version of Bernstein's inequality ... More

A Linear Dynamical System Model for TextFeb 13 2015May 31 2015Low dimensional representations of words allow accurate NLP models to be trained on limited annotated data. While most representations ignore words' local context, a natural way to induce context-dependent representations is to perform inference in a ... More

(weak) Calibration is Computationally HardFeb 20 2012We show that the existence of a computationally efficient calibration algorithm, with a low weak calibration rate, would imply the existence of an efficient algorithm for computing approximate Nash equilibria - thus implying the unlikely conclusion that ... More

Computing Matrix Squareroot via Non Convex Local SearchJul 21 2015We consider the problem of computing the squareroot of a positive semidefinite (PSD) matrix. Several fast algorithms (some based on eigenvalue decomposition and some based on Taylor expansion) are known to solve this problem. In this paper, we propose ... More

Recovering Structured Probability MatricesFeb 21 2016Apr 15 2016We consider the problem of accurately recovering a matrix B of size M by M , which represents a probability distribution over M2 outcomes, given access to an observed matrix of "counts" generated by taking independent samples from the distribution B. ... More

The Step Decay Schedule: A Near Optimal, Geometrically Decaying Learning Rate ProcedureApr 29 2019There is a stark disparity between the step size schedules used in practical large scale machine learning and those that are considered optimal by the theory of stochastic approximation. In theory, most results utilize polynomially decaying learning rate ... More

Maximum Likelihood Estimation for Learning Populations of ParametersFeb 12 2019Consider a setting with $N$ independent individuals, each with an unknown parameter, $p_i \in [0, 1]$ drawn from some unknown distribution $P^\star$. After observing the outcomes of $t$ independent Bernoulli trials, i.e., $X_i \sim \text{Binomial}(t, ... More

Un-regularizing: approximate proximal point and faster stochastic algorithms for empirical risk minimizationJun 24 2015We develop a family of accelerated stochastic algorithms that minimize sums of convex functions. Our algorithms improve upon the fastest running time for empirical risk minimization (ERM), and in particular linear least-squares regression, across a wide ... More

Regularization Techniques for Learning with MatricesOct 04 2009Oct 17 2010There is growing body of learning problems for which it is natural to organize the parameters into matrix, so as to appropriately regularize the parameters under some matrix norm (in order to impose some more sophisticated prior knowledge). This work ... More

On the insufficiency of existing momentum schemes for Stochastic OptimizationMar 15 2018Jul 31 2018Momentum based stochastic gradient methods such as heavy ball (HB) and Nesterov's accelerated gradient descent (NAG) method are widely used in practice for training deep networks and other supervised learning models, as they often provide significant ... More

Planning in POMDPs Using Multiplicity AutomataJul 04 2012Planning and learning in Partially Observable MDPs (POMDPs) are among the most challenging tasks in both the AI and Operation Research communities. Although solutions to these problems are intractable in general, there might be special cases, such as ... More

Provably Efficient Maximum Entropy ExplorationDec 06 2018Jan 26 2019Suppose an agent is in a (possibly unknown) Markov Decision Process in the absence of a reward signal, what might we hope that an agent can efficiently learn to do? This work studies a broad class of objectives that are defined solely as functions of ... More

Towards minimax policies for online linear optimization with bandit feedbackFeb 14 2012We address the online linear optimization problem with bandit feedback. Our contribution is twofold. First, we provide an algorithm (based on exponential weights) with a regret of order $\sqrt{d n \log N}$ for any finite action set with $N$ actions, under ... More

Global Convergence of Non-Convex Gradient Descent for Computing Matrix SquarerootJul 21 2015Mar 09 2017While there has been a significant amount of work studying gradient descent techniques for non-convex optimization problems over the last few years, all existing results establish either local convergence with good rates or global convergence with highly ... More

Optimality and Approximation with Policy Gradient Methods in Markov Decision ProcessesAug 01 2019Policy gradient methods are among the most effective methods in challenging reinforcement learning problems with large state and/or action spaces. However, little is known about even their most basic theoretical convergence properties, including: if and ... More

Revisiting the Polyak step sizeMay 01 2019This paper revisits the Polyak step size schedule for convex optimization problems, proving that a simple variant of it simultaneously attains near optimal convergence rates for the gradient descent algorithm, for all ranges of strong convexity, smoothness, ... More

Competing with the Empirical Risk Minimizer in a Single PassDec 20 2014Feb 25 2015In many estimation problems, e.g. linear and logistic regression, we wish to minimize an unknown objective given only unbiased samples of the objective function. Furthermore, we aim to achieve this using as few samples as possible. In the absence of computational ... More

Learning Exponential Families in High-Dimensions: Strong Convexity and SparsityOct 31 2009May 16 2015The versatility of exponential families, along with their attendant convexity properties, make them a popular and effective statistical model. A central issue is learning these models in high-dimensions, such as when there is some sparsity pattern of ... More

A Smoother Way to Train Structured Prediction ModelsFeb 08 2019We present a framework to train a structured prediction model by performing smoothing on the inference algorithm it builds upon. Smoothing overcomes the non-smoothness inherent to the maximum margin structured prediction objective, and paves the way for ... More

Multi-Label Prediction via Compressed SensingFeb 08 2009Jun 02 2009We consider multi-label prediction problems with large output spaces under the assumption of output sparsity -- that the target (label) vectors have small support. We develop a general theory for a variant of the popular error correcting output code scheme, ... More

Coupled Recurrent Models for Polyphonic Music CompositionNov 20 2018This work describes a novel recurrent model for music composition, which accounts for the rich statistical structure of polyphonic music. There are many ways to factor the probability distribution over musical scores; we consider the merits of various ... More

Global Convergence of Policy Gradient Methods for the Linear Quadratic RegulatorJan 15 2018Oct 21 2018Direct policy gradient methods for reinforcement learning and continuous control problems are a popular approach for a variety of reasons: 1) they are easy to implement without explicit knowledge of the underlying model 2) they are an "end-to-end" approach, ... More

Global Convergence of Policy Gradient Methods for the Linear Quadratic RegulatorJan 15 2018Mar 23 2019Direct policy gradient methods for reinforcement learning and continuous control problems are a popular approach for a variety of reasons: 1) they are easy to implement without explicit knowledge of the underlying model 2) they are an "end-to-end" approach, ... More

A Tensor Approach to Learning Mixed Membership Community ModelsFeb 12 2013Oct 24 2013Community detection is the task of detecting hidden communities from observed interactions. Guaranteed community detection has so far been mostly limited to models with non-overlapping communities such as the stochastic block model. In this paper, we ... More

Learning Topic Models and Latent Bayesian Networks Under Expansion ConstraintsSep 24 2012May 24 2013Unsupervised estimation of latent variable models is a fundamental problem central to numerous applications of machine learning and statistics. This work presents a principled approach for estimating broad classes of such models, including probabilistic ... More

Recovering Structured Probability MatricesFeb 21 2016Feb 06 2018We consider the problem of accurately recovering a matrix B of size M by M , which represents a probability distribution over M2 outcomes, given access to an observed matrix of "counts" generated by taking independent samples from the distribution B. ... More

Invariances and Data Augmentation for Supervised Music TranscriptionNov 13 2017This paper explores a variety of models for frame-based music transcription, with an emphasis on the methods needed to reach state-of-the-art on human recordings. The translation-invariant network discussed in this paper, which combines a traditional ... More

Capturing vehicular space headway using low-cost LIDAR and processing through ARIMA prediction modelingJul 25 2019The project is aimed at designing a low-cost system to capture spatial vehicle headway data and process the raw data by filtering outliers using a unique filtering technique. Multiple sensors and modules are integrated to form the system. The sensors ... More

Provably Correct Automatic Subdifferentiation for Qualified ProgramsSep 23 2018Jan 14 2019The Cheap Gradient Principle (Griewank 2008) --- the computational cost of computing the gradient of a scalar-valued function is nearly the same (often within a factor of $5$) as that of simply computing the function itself --- is of central importance ... More

An Optimal Algorithm for Linear BanditsOct 19 2011Feb 14 2012We provide the first algorithm for online bandit linear optimization whose regret after T rounds is of order sqrt{Td ln N} on any finite class X of N actions in d dimensions, and of order d*sqrt{T} (up to log factors) when X is infinite. These bounds ... More

Tensor decompositions for learning latent variable modelsOct 29 2012Nov 13 2014This work considers a computationally and statistically efficient parameter estimation method for a wide class of latent variable models---including Gaussian mixture models, hidden Markov models, and latent Dirichlet allocation---which exploits a certain ... More

Canonical Correlation Analysis for Analyzing Sequences of Medical Billing CodesDec 01 2016Jan 06 2017We propose using canonical correlation analysis (CCA) to generate features from sequences of medical billing codes. Applying this novel use of CCA to a database of medical billing codes for patients with diverticulitis, we first demonstrate that the CCA ... More

Parallelizing Stochastic Approximation Through Mini-Batching and Tail-AveragingOct 12 2016Oct 27 2016This work characterizes the benefits of averaging techniques widely used in conjunction with stochastic gradient descent (SGD). In particular, this work sharply analyzes: (1) mini-batching, a method of averaging many samples of the gradient to both reduce ... More

Canonical Correlation Analysis for Analyzing Sequences of Medical Billing CodesDec 01 2016We propose using canonical correlation analysis (CCA) to generate features from sequences of medical billing codes. Applying this novel use of CCA to a database of medical billing codes for patients with diverticulitis, we first demonstrate that the CCA ... More

A Spectral Algorithm for Latent Dirichlet AllocationApr 30 2012Jan 17 2013The problem of topic modeling can be seen as a generalization of the clustering problem, in that it posits that observations are generated due to multiple latent factors (e.g., the words in each document are generated as a mixture of several active topics, ... More

Stochastic convex optimization with bandit feedbackJul 08 2011Oct 08 2011This paper addresses the problem of minimizing a convex, Lipschitz function $f$ over a convex, compact set $\xset$ under a stochastic bandit feedback model. In this model, the algorithm is allowed to observe noisy realizations of the function value $f(x)$ ... More

A Short Note on Concentration Inequalities for Random Vectors with SubGaussian NormFeb 11 2019In this note, we derive concentration inequalities for random vectors with subGaussian norm (a generalization of both subGaussian random vectors and norm bounded random vectors), which are tight up to logarithmic factors.

Online Control with Adversarial DisturbancesFeb 23 2019We study the control of a linear dynamical system with adversarial disturbances (as opposed to statistical noise). The objective we consider is one of regret: we desire an online control procedure that can do nearly as well as that of a procedure that ... More

Parallelizing Stochastic Gradient Descent for Least Squares Regression: mini-batching, averaging, and model misspecificationOct 12 2016Jul 31 2018This work characterizes the benefits of averaging schemes widely used in conjunction with stochastic gradient descent (SGD). In particular, this work provides a sharp analysis of: (1) mini-batching, a method of averaging many samples of a stochastic gradient ... More

A Markov Chain Theory Approach to Characterizing the Minimax Optimality of Stochastic Gradient Descent (for Least Squares)Oct 25 2017Jul 21 2018This work provides a simplified proof of the statistical minimax optimality of (iterate averaged) stochastic gradient descent (SGD), for the special case of least squares. This result is obtained by analyzing SGD as a stochastic process and by sharply ... More

Spectral Methods for Learning Multivariate Latent Tree StructureJul 07 2011Nov 08 2011This work considers the problem of learning the structure of multivariate linear tree models, which include a variety of directed tree graphical models with continuous, discrete, and mixed latent variables such as linear-Gaussian models, hidden Markov ... More

Faster Eigenvector Computation via Shift-and-Invert PreconditioningMay 26 2016We give faster algorithms and improved sample complexities for estimating the top eigenvector of a matrix $\Sigma$ -- i.e. computing a unit vector $x$ such that $x^T \Sigma x \ge (1-\epsilon)\lambda_1(\Sigma)$: Offline Eigenvector Estimation: Given an ... More

How to Escape Saddle Points EfficientlyMar 02 2017This paper shows that a perturbed form of gradient descent converges to a second-order stationary point in a number iterations which depends only poly-logarithmically on dimension (i.e., it is almost "dimension-free"). The convergence rate of this procedure ... More

Efficient Algorithms for Large-scale Generalized Eigenvector Computation and Canonical Correlation AnalysisApr 13 2016May 27 2016This paper considers the problem of canonical-correlation analysis (CCA) (Hotelling, 1936) and, more broadly, the generalized eigenvector problem for a pair of symmetric matrices. These are two fundamental problems in data analysis and scientific computing ... More

Robust Shift-and-Invert Preconditioning: Faster and More Sample Efficient Algorithms for Eigenvector ComputationOct 29 2015May 30 2016We provide faster algorithms and improved sample complexities for approximating the top eigenvector of a matrix. Offline Setting: Given an $n \times d$ matrix $A$, we show how to compute an $\epsilon$ approximate top eigenvector in time $\tilde O ( [nnz(A) ... More

A Risk Comparison of Ordinary Least Squares vs Ridge RegressionMay 04 2011May 31 2013We compare the risk of ridge regression to a simple variant of ordinary least squares, in which one simply projects the data onto a finite dimensional subspace (as specified by a Principal Component Analysis) and then performs an ordinary (un-regularized) ... More

Parallelizing Stochastic Approximation Through Mini-Batching and Tail-AveragingOct 12 2016This work characterizes the benefits of averaging techniques widely used in conjunction with stochastic gradient descent (SGD). In particular, this work sharply analyzes: (1) mini-batching, a method of averaging many samples of the gradient to both reduce ... More

Accelerating Stochastic Gradient Descent For Least Squares RegressionApr 26 2017Jul 31 2018There is widespread sentiment that it is not possible to effectively utilize fast gradient methods (e.g. Nesterov's acceleration, conjugate gradient, heavy ball) for the purposes of stochastic optimization due to their instability and error accumulation, ... More

Least Squares Revisited: Scalable Approaches for Multi-class PredictionOct 07 2013Oct 21 2013This work provides simple algorithms for multi-class (and multi-label) prediction in settings where both the number of examples n and the data dimension d are relatively large. These robust and parameter free algorithms are essentially iterative least-squares ... More

Stochastic Gradient Descent Escapes Saddle Points EfficientlyFeb 13 2019This paper considers the perturbed stochastic gradient descent algorithm and shows that it finds $\epsilon$-second order stationary points ($\left\|\nabla f(x)\right\|\leq \epsilon$ and $\nabla^2 f(x) \succeq -\sqrt{\epsilon} \mathbf{I}$) in $\tilde{O}(d/\epsilon^4)$ ... More

Streaming PCA: Matching Matrix Bernstein and Near-Optimal Finite Sample Guarantees for Oja's AlgorithmFeb 22 2016Mar 28 2016This work provides improved guarantees for streaming principle component analysis (PCA). Given $A_1, \ldots, A_n\in \mathbb{R}^{d\times d}$ sampled independently from distributions satisfying $\mathbb{E}[A_i] = \Sigma$ for $\Sigma \succeq \mathbf{0}$, ... More

Learning Features of Music from ScratchNov 29 2016We introduce a new large-scale music dataset, MusicNet, to serve as a source of supervision and evaluation of machine learning methods for music research. MusicNet consists of hundreds of freely-licensed classical music recordings by 10 composers, written ... More

On the Optimality of Sparse Model-Based Planning for Markov Decision ProcessesJun 10 2019Jul 04 2019This work considers the sample complexity of obtaining an $\epsilon$-optimal policy in a discounted Markov Decision Process (MDP), given only access to a generative model. In this model, the learner accesses the underlying transition model via a sampling ... More

On the Optimality of Sparse Model-Based Planning for Markov Decision ProcessesJun 10 2019This work considers the sample complexity of obtaining an $\epsilon$-optimal policy in a discounted Markov Decision Process (MDP), given only access to a generative model. In this model, the learner accesses the underlying transition model via a sampling ... More

Domain Adaptation: Overfitting and Small Sample StatisticsMay 04 2011We study the prevalent problem when a test distribution differs from the training distribution. We consider a setting where our training set consists of a small number of sample domains, but where we have many samples in each domain. Our goal is to generalize ... More

Variance Reduction for Policy Gradient with Action-Dependent Factorized BaselinesMar 20 2018Policy gradient methods have enjoyed great success in deep reinforcement learning but suffer from high variance of gradient estimates. The high variance problem is particularly exasperated in problems with long horizons or high-dimensional action spaces. ... More

Photoluminescence and spectral switching of single CdSe/ZnS colloidal nanocrystals in poly(methyl methacrylate)Mar 30 2007Apr 08 2007Emission from single CdSe nanocrystals in PMMA was investigated. A fraction of the nanocrystals exhibiting switching between two energy states, which have similar total intensities, but distinctly different spectra were observed. We found that the spectral ... More

Efficient Learning of Generalized Linear and Single Index Models with Isotonic RegressionApr 11 2011Generalized Linear Models (GLMs) and Single Index Models (SIMs) provide powerful generalizations of linear regression, where the target variable is assumed to be a (possibly unknown) 1-dimensional function of a linear predictor. In general, these problems ... More

Towards Generalization and Simplicity in Continuous ControlMar 08 2017Mar 20 2018This work shows that policies with simple linear and RBF parameterizations can be trained to solve a variety of continuous control tasks, including the OpenAI gym benchmarks. The performance of these trained policies are competitive with state of the ... More

Learning Overcomplete HMMsNov 07 2017Jun 28 2018We study the problem of learning overcomplete HMMs---those that have many hidden states but a small output alphabet. Despite having significant practical importance, such HMMs are poorly understood with no known positive or negative results for efficient ... More

Online Meta-LearningFeb 22 2019Jul 03 2019A central capability of intelligent systems is the ability to continuously build upon previous experiences to speed up and enhance learning of new tasks. Two distinct research paradigms have studied this question. Meta-learning views this problem as learning ... More

Prediction with a Short MemoryDec 08 2016We consider the problem of predicting the next observation given a sequence of past observations. We show that for any distribution over observations, if the mutual information between past observations and future observations is upper bounded by $I$, ... More

Online Meta-LearningFeb 22 2019A central capability of intelligent systems is the ability to continuously build upon previous experiences to speed up and enhance learning of new tasks. Two distinct research paradigms have studied this question. Meta-learning views this problem as learning ... More

Learning from Logged Implicit Exploration DataFeb 27 2010Jun 14 2010We provide a sound and consistent foundation for the use of \emph{nonrandom} exploration data in "contextual bandit" or "partially labeled" settings where only the value of a chosen action is learned. The primary challenge in a variety of settings is ... More

Convergence Rates of Active Learning for Maximum Likelihood EstimationJun 08 2015An active learner is given a class of models, a large set of unlabeled examples, and the ability to interactively query labels of a subset of these examples; the goal of the learner is to learn a model in the class that fits the data well. Previous theoretical ... More

When are Overcomplete Topic Models Identifiable? Uniqueness of Tensor Tucker Decompositions with Structured SparsityAug 13 2013Overcomplete latent representations have been very popular for unsupervised feature learning in recent years. In this paper, we specify which overcomplete models can be identified given observable moments of a certain order. We consider probabilistic ... More

Online Meta-LearningFeb 22 2019May 16 2019A central capability of intelligent systems is the ability to continuously build upon previous experiences to speed up and enhance learning of new tasks. Two distinct research paradigms have studied this question. Meta-learning views this problem as learning ... More

Prediction with a Short MemoryDec 08 2016Jun 28 2018We consider the problem of predicting the next observation given a sequence of past observations, and consider the extent to which accurate prediction requires complex algorithms that explicitly leverage long-range dependencies. Perhaps surprisingly, ... More

Plan Online, Learn Offline: Efficient Learning and Exploration via Model-Based ControlNov 05 2018Jan 28 2019We propose a plan online and learn offline (POLO) framework for the setting where an agent, with an internal model, needs to continually act and learn in the world. Our work builds on the synergistic relationship between local model-based control, global ... More

Minimal Realization Problems for Hidden Markov ModelsNov 13 2014Dec 14 2015Consider a stationary discrete random process with alphabet size d, which is assumed to be the output process of an unknown stationary Hidden Markov Model (HMM). Given the joint probabilities of finite length strings of the process, we are interested ... More

Stochastic subgradient method converges on tame functionsApr 20 2018May 26 2018This work considers the question: what convergence guarantees does the stochastic subgradient method have in the absence of smoothness and convexity? We prove that the stochastic subgradient method, on any semialgebraic locally Lipschitz function, produces ... More

Phononic band structure engineering for high-Q gigahertz surface acoustic wave resonators on lithium niobateJan 25 2019May 29 2019Phonons at gigahertz frequencies interact with electrons, photons, and atomic systems in solids, and therefore have extensive applications in signal processing, sensing, and quantum technologies. Surface acoustic wave (SAW) resonators that confine surface ... More

On the functorial properties of the p-analog of the Fourier-Stieltjes algebras and their homomorphismsFeb 26 2019Let G be a locally compact group, and 1 < p < \infty, and let Ap(G) and Bp(G) denote the Figa-Talamanca-Herz algebra and the p-analog of the Fourier-Stieltjes algebra, repectively. In this paper for a locally compact group H, a subset Y \in \Omega 0(H), ... More

A predictive analytics approach to reducing avoidable hospital readmissionFeb 24 2014Mar 12 2014Hospital readmission has become a critical metric of quality and cost of healthcare. Medicare anticipates that nearly $17 billion is paid out on the 20% of patients who are readmitted within 30 days of discharge. Although several interventions such as ... More

Predicting patient risk of readmission with frailty models in the Department of Veteran AffairsMar 05 2014Reducing potentially preventable readmissions has been identified as an important issue for decreasing Medicare costs and improving quality of care provided by hospitals. Based on previous research by medical professionals, preventable readmissions are ... More

Leverage Score Sampling for Faster Accelerated Regression and ERMNov 22 2017Given a matrix $\mathbf{A}\in\mathbb{R}^{n\times d}$ and a vector $b \in\mathbb{R}^{d}$, we show how to compute an $\epsilon$-approximate solution to the regression problem $ \min_{x\in\mathbb{R}^{d}}\frac{1}{2} \|\mathbf{A} x - b\|_{2}^{2} $ in time ... More

Learning High-Dimensional Mixtures of Graphical ModelsMar 04 2012Jun 30 2012We consider unsupervised estimation of mixtures of discrete graphical models, where the class variable corresponding to the mixture components is hidden and each mixture component over the observed variables can have a potentially different Markov graph ... More

Mass and Heat Diffusion in Ternary Polymer Solutions: A Classical Irreversible Thermodynamics ApproachJan 25 2016Apr 22 2016Governing equations for evolution of concentration and temperature in three-component systems were derived in the framework of classical irreversible thermodynamics using Onsager variational principle and were presented for solvent/solvent/polymer and ... More

Linear Exp6 Isotherm for Compressed Molten Cesium Over the Whole Liquid range Including Metal-nonmetls Transition and TcDec 16 2000The linear exp6 isotherm is presented as an approach to the thermodynamic properies of liquid alkali metals over the whole liquid range including metal-nonmetal transition. The exp6 pair interaction potential is applied to approach the underlying interplay ... More

On certain classes of harmonic functions defined by the fractional derivativesJul 16 2009In this paper we have introduced two new classes $\mathcal{H}\mathcal{M}(\beta, \lambda, k, \nu)$ and $\overline{\mathcal{H}\mathcal{M}} (\beta, \lambda, k, \nu)$ of complex valued harmonic multivalent functions of the form $f = h + \overline g$, satisfying ... More

Electronic Excitations and Stability of the Ground State of C60 MoleculesJul 09 1998A model study of the singlet excitons in the C60 molecule with emphasis on the Coulomb interaction between excited electron and hole leads to a physical understanding of the interaction effects on the absorption spectra and to a new identification of ... More

Low-loss fiber-to-chip interface for lithium niobate photonic integrated circuitsFeb 24 2019Integrated lithium niobate (LN) photonic circuits have recently emerged as a promising candidate for advanced photonic functions such as high-speed modulation, nonlinear frequency conversion and frequency comb generation. For practical applications, optical ... More

Ultra-low loss integrated visible photonics using thin-film lithium niobateFeb 21 2019Mar 08 2019Integrated photonics is a powerful platform that can improve the performance and stability of optical systems, while providing low-cost, small-footprint and scalable alternatives to implementations based on free-space optics. While great progress has ... More

An integrated diamond Raman laser pumped in the near-visibleDec 12 2017Using a high-Q diamond microresonator (Q > 300,000) interfaced with high-power-handling directly-written doped-glass waveguides, we demonstrate a Raman laser in an integrated platform pumped in the near-visible. Both TM-to-TE and TE-to-TE lasing is observed, ... More

Congeniality Bounds on Quark Masses from NucleosynthesisDec 12 2012Jul 01 2013The work of Jaffe, Jenkins and Kimchi [Phys. Rev. D79, 065014 (2009)] is revisited to see if indeed the region of congeniality found in their analysis survives further restrictions from nucleosynthesis. It is observed that much of their congenial region ... More

A Study on the Prevalence of Human Values in Software Engineering Publications, 2015-2018Jul 18 2019Failure to account for human values in software (e.g., equality and fairness) can result in user dissatisfaction and negative socio-economic impact. Engineering these values in software, however, requires technical and methodological support throughout ... More