Analysis of Distributed Stochastic Dual Coordinate Ascent

In \citep{Yangnips13}, the author presented distributed stochastic dual coordinate ascent (DisDCA) algorithms for solving large-scale regularized loss minimization. Extraordinary performances have been observed and reported for the well-motivated updates, as referred to the practical updates, compared to the naive updates. However, no serious analysis has been provided to understand the updates and therefore the convergence rates. In the paper, we bridge the gap by providing a theoretical analysis of the convergence rates of the practical DisDCA algorithm. Our analysis helped by empirical studies has shown that it could yield an exponential speed-up in the convergence by increasing the number of dual updates at each iteration. This result justifies the superior performances of the practical DisDCA as compared to the naive variant. As a byproduct, our analysis also reveals the convergence behavior of the one-communication DisDCA.

CUR Algorithm with Incomplete Matrix Observation

CUR matrix decomposition is a randomized algorithm that can efficiently compute the low rank approximation for a given rectangle matrix. One limitation with the existing CUR algorithms is that they require an access to the full matrix A for computing U. In this work, we aim to alleviate this limitation. In particular, we assume that besides having an access to randomly sampled d rows and d columns from A, we only observe a subset of randomly sampled entries from A. Our goal is to develop a low rank approximation algorithm, similar to CUR, based on (i) randomly sampled rows and columns from A, and (ii) randomly sampled entries from A. The proposed algorithm is able to perfectly recover the target matrix A with only O(rn log n) number of observed entries. In addition, instead of having to solve an optimization problem involved trace norm regularization, the proposed algorithm only needs to solve a standard regression problem. Finally, unlike most matrix completion theories that hold only when the target matrix is of low rank, we show a strong guarantee for the proposed algorithm even when the target matrix is not low rank.

Recovering the Optimal Solution by Dual Random Projection

Random projection has been widely used in data classification. It maps high-dimensional data into a low-dimensional subspace in order to reduce the computational cost in solving the related optimization problem. While previous studies are focused on analyzing the classification performance of using random projection, in this work, we consider the recovery problem, i.e., how to accurately recover the optimal solution to the original optimization problem in the high-dimensional space based on the solution learned from the subspace spanned by random projections. We present a simple algorithm, termed Dual Random Projection, that uses the dual solution of the low-dimensional optimization problem to recover the optimal solution to the original problem. Our theoretical analysis shows that with a high probability, the proposed algorithm is able to accurately recover the optimal solution to the original problem, provided that the data matrix is of low rank or can be well approximated by a low rank matrix.

Scalable Kernel Clustering: Approximate Kernel k-means

Kernel-based clustering algorithms have the ability to capture the non-linear structure in real world data. Among various kernel-based clustering algorithms, kernel k-means has gained popularity due to its simple iterative nature and ease of implementation. However, its run-time complexity and memory footprint increase quadratically in terms of the size of the data set, and hence, large data sets cannot be clustered efficiently. In this paper, we propose an approximation scheme based on randomization, called the Approximate Kernel k-means. We approximate the cluster centers using the kernel similarity between a few sampled points and all the points in the data set. We show that the proposed method achieves better clustering performance than the traditional low rank kernel approximation based clustering schemes. We also demonstrate that its running time and memory requirements are significantly lower than those of kernel k-means, with only a small reduction in the clustering quality on several public domain large data sets. We then employ ensemble clustering techniques to further enhance the performance of our algorithm.

Excess Risk Bounds for Exponentially Concave Losses

The overarching goal of this paper is to derive excess risk bounds for learning from exp-concave loss functions in passive and sequential learning settings. Exp-concave loss functions encompass several fundamental problems in machine learning such as squared loss in linear regression, logistic loss in classification, and negative logarithm loss in portfolio management. In batch setting, we obtain sharp bounds on the performance of empirical risk minimization performed in a linear hypothesis space and with respect to the exp-concave loss functions. We also extend the results to the online setting where the learner receives the training examples in a sequential manner. We propose an online learning algorithm that is a properly modified version of online Newton method to obtain sharp risk bounds. Under an additional mild assumption on the loss function, we show that in both settings we are able to achieve an excess risk bound of $O(d\log n/n)$ that holds with a high probability.

Binary Excess Risk for Smooth Convex Surrogates

In statistical learning theory, convex surrogates of the 0-1 loss are highly preferred because of the computational and theoretical virtues that convexity brings in. This is of more importance if we consider smooth surrogates as witnessed by the fact that the smoothness is further beneficial both computationally- by attaining an {\it optimal} convergence rate for optimization, and in a statistical sense- by providing an improved {\it optimistic} rate for generalization bound. In this paper we investigate the smoothness property from the viewpoint of statistical consistency and show how it affects the binary excess risk. We show that in contrast to optimization and generalization errors that favor the choice of smooth surrogate loss, the smoothness of loss function may degrade the binary excess risk. Motivated by this negative result, we provide a unified analysis that integrates optimization error, generalization bound, and the error in translating convex excess risk into a binary excess risk when examining the impact of smoothness on the binary excess risk. We show that under favorable conditions appropriate choice of smooth convex loss will result in a binary excess risk that is better than $O(1/\sqrt{n})$.

Beating the Minimax Rate of Active Learning with Prior Knowledge

Active learning refers to the learning protocol where the learner is allowed to choose a subset of instances for labeling. Previous studies have shown that, compared with passive learning, active learning is able to reduce the label complexity exponentially if the data are linearly separable or satisfy the Tsybakov noise condition with parameter $\kappa=1$. In this paper, we propose a novel active learning algorithm using a convex surrogate loss, with the goal to broaden the cases for which active learning achieves an exponential improvement. We make use of a convex loss not only because it reduces the computational cost, but more importantly because it leads to a tight bound for the empirical process (i.e., the difference between the empirical estimation and the expectation) when the current solution is close to the optimal one. Under the assumption that the norm of the optimal classifier that minimizes the convex risk is available, our analysis shows that the introduction of the convex surrogate loss yields an exponential reduction in the label complexity even when the parameter $\kappa$ of the Tsybakov noise is larger than $1$. To the best of our knowledge, this is the first work that improves the minimax rate of active learning by utilizing certain priori knowledge.

Stochastic Optimization of Smooth Loss

In this paper, we first prove a high probability bound rather than an expectation bound for stochastic optimization with smooth loss. Furthermore, the existing analysis requires the knowledge of optimal classifier for tuning the step size in order to achieve the desired bound. However, this information is usually not accessible in advanced. We also propose a strategy to address the limitation.

MixedGrad: An O(1/T) Convergence Rate Algorithm for Stochastic Smooth Optimization

It is well known that the optimal convergence rate for stochastic optimization of smooth functions is $O(1/\sqrt{T})$, which is same as stochastic optimization of Lipschitz continuous convex functions. This is in contrast to optimizing smooth functions using full gradients, which yields a convergence rate of $O(1/T^2)$. In this work, we consider a new setup for optimizing smooth functions, termed as {\bf Mixed Optimization}, which allows to access both a stochastic oracle and a full gradient oracle. Our goal is to significantly improve the convergence rate of stochastic optimization of smooth functions by having an additional small number of accesses to the full gradient oracle. We show that, with an $O(\ln T)$ calls to the full gradient oracle and an $O(T)$ calls to the stochastic oracle, the proposed mixed optimization algorithm is able to achieve an optimization error of $O(1/T)$.

An Efficient Primal-Dual Prox Method for Non-Smooth Optimization

We study the non-smooth optimization problems in machine learning, where both the loss function and the regularizer are non-smooth functions. Previous studies on efficient empirical loss minimization assume either a smooth loss function or a strongly convex regularizer, making them unsuitable for non-smooth optimization. We develop a simple yet efficient method for a family of non-smooth optimization problems where the dual form of the loss function is bilinear in primal and dual variables. We cast a non-smooth optimization problem into a minimax optimization problem, and develop a primal dual prox method that solves the minimax optimization problem at a rate of $O(1/T)$ {assuming that the proximal step can be efficiently solved}, significantly faster than a standard subgradient descent method that has an $O(1/\sqrt{T})$ convergence rate. Our empirical study verifies the efficiency of the proposed method for various non-smooth optimization problems that arise ubiquitously in machine learning by comparing it to the state-of-the-art first order methods.