arXiv subjects

David Woodruff

Publications and source records attributed to David Woodruff.

31 records · Page 2Linked to original sources

arXiv2020

Oblivious Sketching of High-Degree Polynomial Kernels

Kernel methods are fundamental tools in machine learning that allow detection of non-linear dependencies between data without explicitly constructing feature vectors in high dimensional spaces. A major disadvantage of kernel methods is their poor scalability: primitives such as kernel PCA or kernel ridge regression generally take prohibitively large quadratic space and (at least) quadratic time, as kernel matrices are usually dense. Some methods for speeding up kernel linear algebra are known, but they all invariably take time exponential in either the dimension of the input point set (e.g., fast multipole methods suffer from the curse of dimensionality) or in the degree of the kernel function. Oblivious sketching has emerged as a powerful approach to speeding up numerical linear algebra over the past decade, but our understanding of oblivious sketching solutions for kernel matrices has remained quite limited, suffering from the aforementioned exponential dependence on input parameters. Our main contribution is a general method for applying sketching solutions developed in numerical linear algebra over the past decade to a tensoring of data points without forming the tensoring explicitly. This leads to the first oblivious sketch for the polynomial kernel with a target dimension that is only polynomially dependent on the degree of the kernel function, as well as the first oblivious sketch for the Gaussian kernel on bounded datasets that does not suffer from an exponential dependence on the dimensionality of input data points.

cs.DS↗

arXiv2020

Input-Sparsity Low Rank Approximation in Schatten Norm

We give the first input-sparsity time algorithms for the rank-$k$ low rank approximation problem in every Schatten norm. Specifically, for a given $n\times n$ matrix $A$, our algorithm computes $Y,Z\in \mathbb{R}^{n\times k}$, which, with high probability, satisfy $\|A-YZ^T\|_p \leq (1+ε)\|A-A_k\|_p$, where $\|M\|_p = \left (\sum_{i=1}^n σ_i(M)^p \right )^{1/p}$ is the Schatten $p$-norm of a matrix $M$ with singular values $σ_1(M), \ldots, σ_n(M)$, and where $A_k$ is the best rank-$k$ approximation to $A$. Our algorithm runs in time $\tilde{O}(\operatorname{nnz}(A) + mn^{α_p}\operatorname{poly}(k/ε))$, where $α_p = 0$ for $p\in [1,2)$ and $α_p = (ω-1)(1-2/p)$ for $p>2$ and $ω\approx 2.374$ is the exponent of matrix multiplication. For the important case of $p = 1$, which corresponds to the more "robust" nuclear norm, we obtain $\tilde{O}(\operatorname{nnz}(A) + m \cdot \operatorname{poly}(k/ε))$ time, which was previously only known for the Frobenius norm ($p = 2$). Moreover, since $α_p < ω- 1$ for every $p$, our algorithm has a better dependence on $n$ than that in the singular value decomposition for every $p$. Crucial to our analysis is the use of dimensionality reduction for Ky-Fan $p$-norms.

cs.DS↗

arXiv2019

On Low-Risk Heavy Hitters and Sparse Recovery Schemes

We study the heavy hitters and related sparse recovery problems in the low-failure probability regime. This regime is not well-understood, and has only been studied for non-adaptive schemes. The main previous work is one on sparse recovery by Gilbert et al.(ICALP'13). We recognize an error in their analysis, improve their results, and contribute new non-adaptive and adaptive sparse recovery algorithms, as well as provide upper and lower bounds for the heavy hitters problem with low failure probability.

cs.DS↗

arXiv2019

Regularized Weighted Low Rank Approximation

The classical low rank approximation problem is to find a rank $k$ matrix $UV$ (where $U$ has $k$ columns and $V$ has $k$ rows) that minimizes the Frobenius norm of $A - UV$. Although this problem can be solved efficiently, we study an NP-hard variant of this problem that involves weights and regularization. A previous paper of [Razenshteyn et al. '16] derived a polynomial time algorithm for weighted low rank approximation with constant rank. We derive provably sharper guarantees for the regularized version by obtaining parameterized complexity bounds in terms of the statistical dimension rather than the rank, allowing for a rank-independent runtime that can be significantly faster. Our improvement comes from applying sharper matrix concentration bounds, using a novel conditioning technique, and proving structural theorems for regularized low rank problems.

cs.DS↗

arXiv2019

Faster Algorithms for High-Dimensional Robust Covariance Estimation

We study the problem of estimating the covariance matrix of a high-dimensional distribution when a small constant fraction of the samples can be arbitrarily corrupted. Recent work gave the first polynomial time algorithms for this problem with near-optimal error guarantees for several natural structured distributions. Our main contribution is to develop faster algorithms for this problem whose running time nearly matches that of computing the empirical covariance. Given $N = \tildeΩ(d^2/ε^2)$ samples from a $d$-dimensional Gaussian distribution, an $ε$-fraction of which may be arbitrarily corrupted, our algorithm runs in time $\tilde{O}(d^{3.26})/\mathrm{poly}(ε)$ and approximates the unknown covariance matrix to optimal error up to a logarithmic factor. Previous robust algorithms with comparable error guarantees all have runtimes $\tildeΩ(d^{2 ω})$ when $ε= Ω(1)$, where $ω$ is the exponent of matrix multiplication. We also provide evidence that improving the running time of our algorithm may require new algorithmic techniques.

cs.LG↗

arXiv2019

Sample-Optimal Low-Rank Approximation of Distance Matrices

A distance matrix $A \in \mathbb R^{n \times m}$ represents all pairwise distances, $A_{ij}=\mathrm{d}(x_i,y_j)$, between two point sets $x_1,...,x_n$ and $y_1,...,y_m$ in an arbitrary metric space $(\mathcal Z, \mathrm{d})$. Such matrices arise in various computational contexts such as learning image manifolds, handwriting recognition, and multi-dimensional unfolding. In this work we study algorithms for low-rank approximation of distance matrices. Recent work by Bakshi and Woodruff (NeurIPS 2018) showed it is possible to compute a rank-$k$ approximation of a distance matrix in time $O((n+m)^{1+γ}) \cdot \mathrm{poly}(k,1/ε)$, where $ε>0$ is an error parameter and $γ>0$ is an arbitrarily small constant. Notably, their bound is sublinear in the matrix size, which is unachievable for general matrices. We present an algorithm that is both simpler and more efficient. It reads only $O((n+m) k/ε)$ entries of the input matrix, and has a running time of $O(n+m) \cdot \mathrm{poly}(k,1/ε)$. We complement the sample complexity of our algorithm with a matching lower bound on the number of entries that must be read by any algorithm. We provide experimental results to validate the approximation quality and running time of our algorithm.

cs.DS↗

arXiv2019

Robust Communication-Optimal Distributed Clustering Algorithms

In this work, we study the $k$-median and $k$-means clustering problems when the data is distributed across many servers and can contain outliers. While there has been a lot of work on these problems for worst-case instances, we focus on gaining a finer understanding through the lens of beyond worst-case analysis. Our main motivation is the following: for many applications such as clustering proteins by function or clustering communities in a social network, there is some unknown target clustering, and the hope is that running a $k$-median or $k$-means algorithm will produce clusterings which are close to matching the target clustering. Worst-case results can guarantee constant factor approximations to the optimal $k$-median or $k$-means objective value, but not closeness to the target clustering. Our first result is a distributed algorithm which returns a near-optimal clustering assuming a natural notion of stability, namely, approximation stability [Balcan et. al 2013], even when a constant fraction of the data are outliers. The communication complexity is $\tilde O(sk+z)$ where $s$ is the number of machines, $k$ is the number of clusters, and $z$ is the number of outliers. Next, we show this amount of communication cannot be improved even in the setting when the input satisfies various non-worst-case assumptions. We give a matching $Ω(sk+z)$ lower bound on the communication required both for approximating the optimal $k$-means or $k$-median cost up to any constant, and for returning a clustering that is close to the target clustering in Hamming distance. These lower bounds hold even when the data satisfies approximation stability or other common notions of stability, and the cluster sizes are balanced. Therefore, $Ω(sk+z)$ is a communication bottleneck, even for real-world instances.

cs.DS↗

arXiv2018

Conditional Sparse $\ell_p$-norm Regression With Optimal Probability

We consider the following conditional linear regression problem: the task is to identify both (i) a $k$-DNF condition $c$ and (ii) a linear rule $f$ such that the probability of $c$ is (approximately) at least some given bound $μ$, and $f$ minimizes the $\ell_p$ loss of predicting the target $z$ in the distribution of examples conditioned on $c$. Thus, the task is to identify a portion of the distribution on which a linear rule can provide a good fit. Algorithms for this task are useful in cases where simple, learnable rules only accurately model portions of the distribution. The prior state-of-the-art for such algorithms could only guarantee finding a condition of probability $Ω(μ/n^k)$ when a condition of probability $μ$ exists, and achieved an $O(n^k)$-approximation to the target loss, where $n$ is the number of Boolean attributes. Here, we give efficient algorithms for solving this task with a condition $c$ that nearly matches the probability of the ideal condition, while also improving the approximation to the target loss. We also give an algorithm for finding a $k$-DNF reference class for prediction at a given query point, that obtains a sparse regression fit that has loss within $O(n^k)$ of optimal among all sparse regression parameters and sufficiently large $k$-DNF reference classes containing the query point.

cs.LG↗

arXiv2018

Revisiting Frequency Moment Estimation in Random Order Streams

We revisit one of the classic problems in the data stream literature, namely, that of estimating the frequency moments $F_p$ for $0 < p < 2$ of an underlying $n$-dimensional vector presented as a sequence of additive updates in a stream. It is well-known that using $p$-stable distributions one can approximate any of these moments up to a multiplicative $(1+ε)$-factor using $O(ε^{-2} \log n)$ bits of space, and this space bound is optimal up to a constant factor in the turnstile streaming model. We show that surprisingly, if one instead considers the popular random-order model of insertion-only streams, in which the updates to the underlying vector arrive in a random order, then one can beat this space bound and achieve $\tilde{O}(ε^{-2} + \log n)$ bits of space, where the $\tilde{O}$ hides poly$(\log(1/ε) + \log \log n)$ factors. If $ε^{-2} \approx \log n$, this represents a roughly quadratic improvement in the space achievable in turnstile streams. Our algorithm is in fact deterministic, and we show our space bound is optimal up to poly$(\log(1/ε) + \log \log n)$ factors for deterministic algorithms in the random order model. We also obtain a similar improvement in space for $p = 2$ whenever $F_2 \gtrsim \log n\cdot F_1$.

cs.DS↗

arXiv2016

Communication Efficient Distributed Kernel Principal Component Analysis

Kernel Principal Component Analysis (KPCA) is a key machine learning algorithm for extracting nonlinear features from data. In the presence of a large volume of high dimensional data collected in a distributed fashion, it becomes very costly to communicate all of this data to a single data center and then perform kernel PCA. Can we perform kernel PCA on the entire dataset in a distributed and communication efficient fashion while maintaining provable and strong guarantees in solution quality? In this paper, we give an affirmative answer to the question by developing a communication efficient algorithm to perform kernel PCA in the distributed setting. The algorithm is a clever combination of subspace embedding and adaptive sampling techniques, and we show that the algorithm can take as input an arbitrary configuration of distributed datasets, and compute a set of global kernel principal components with relative error guarantees independent of the dimension of the feature space or the total number of data points. In particular, computing $k$ principal components with relative error $ε$ over $s$ workers has communication cost $\tilde{O}(s ρk/ε+s k^2/ε^3)$ words, where $ρ$ is the average number of nonzero entries in each data point. Furthermore, we experimented the algorithm with large-scale real world datasets and showed that the algorithm produces a high quality kernel PCA solution while using significantly less communication than alternative approaches.

cs.LG↗

arXiv2014

Improved Distributed Principal Component Analysis

We study the distributed computing setting in which there are multiple servers, each holding a set of points, who wish to compute functions on the union of their point sets. A key task in this setting is Principal Component Analysis (PCA), in which the servers would like to compute a low dimensional subspace capturing as much of the variance of the union of their point sets as possible. Given a procedure for approximate PCA, one can use it to approximately solve $\ell_2$-error fitting problems such as $k$-means clustering and subspace clustering. The essential properties of an approximate distributed PCA algorithm are its communication cost and computational efficiency for a given desired accuracy in downstream applications. We give new algorithms and analyses for distributed PCA which lead to improved communication and computational costs for $k$-means clustering and related problems. Our empirical study on real world data shows a speedup of orders of magnitude, preserving communication with only a negligible degradation in solution quality. Some of these techniques we develop, such as a general transformation from a constant success probability subspace embedding to a high success probability subspace embedding with a dimension and sparsity independent of the success probability, may be of independent interest.

cs.LG↗

arXiv2014

Principal Component Analysis and Higher Correlations for Distributed Data

We consider algorithmic problems in the setting in which the input data has been partitioned arbitrarily on many servers. The goal is to compute a function of all the data, and the bottleneck is the communication used by the algorithm. We present algorithms for two illustrative problems on massive data sets: (1) computing a low-rank approximation of a matrix $A=A^1 + A^2 + \ldots + A^s$, with matrix $A^t$ stored on server $t$ and (2) computing a function of a vector $a_1 + a_2 + \ldots + a_s$, where server $t$ has the vector $a_t$; this includes the well-studied special case of computing frequency moments and separable functions, as well as higher-order correlations such as the number of subgraphs of a specified type occurring in a graph. For both problems we give algorithms with nearly optimal communication, and in particular the only dependence on $n$, the size of the data, is in the number of bits needed to represent indices and words ($O(\log n)$).

cs.DS↗

arXiv2010

Steiner Transitive-Closure Spanners of d-Dimensional Posets

Given a directed graph G and an integer k >= 1, a k-transitive-closure-spanner (k-TCspanner) of G is a directed graph H that has (1) the same transitive-closure as G and (2) diameter at most k. In some applications, the shortcut paths added to the graph in order to obtain small diameter can use Steiner vertices, that is, vertices not in the original graph G. The resulting spanner is called a Steiner transitive-closure spanner (Steiner TC-spanner). Motivated by applications to property reconstruction and access control hierarchies, we concentrate on Steiner TC-spanners of directed acyclic graphs or, equivalently, partially ordered sets. In these applications, the goal is to find a sparsest Steiner k-TC-spanner of a poset G for a given k and G. The focus of this paper is the relationship between the dimension of a poset and the size of its sparsest Steiner TCspanner. The dimension of a poset G is the smallest d such that G can be embedded into a d-dimensional directed hypergrid via an order-preserving embedding. We present a nearly tight lower bound on the size of Steiner 2-TC-spanners of d-dimensional directed hypergrids. It implies better lower bounds on the complexity of local reconstructors of monotone functions and functions with low Lipschitz constant. The proof of the lower bound constructs a dual solution to a linear programming relaxation of the Steiner 2-TC-spanner problem. We also show that one can efficiently construct a Steiner 2-TC-spanner, of size matching the lower bound, for any low-dimensional poset. Finally, we present a lower bound on the size of Steiner k-TC-spanners of d-dimensional posets that shows that the best-known construction, due to De Santis et al., cannot be improved significantly.

cs.DS↗