arXiv subjects

Ainesh Bakshi

Publications and source records attributed to Ainesh Bakshi.

At least 37 records · Page 2Linked to original sources

arXiv2024

File System Aging

File systems must allocate space for files without knowing what will be added or removed in the future. Over the life of a file system, this may cause suboptimal file placement decisions that eventually lead to slower performance, or aging. Conventional wisdom suggests that file system aging is a solved problem in the common case; heuristics to avoid aging, such as colocating related files and data blocks, are effective until a storage device fills up, at which point space pressure exacerbates fragmentation-based aging. However, this article describes both realistic and synthetic workloads that can cause these heuristics to fail, inducing large performance declines due to aging, even when the storage device is nearly empty. We argue that these slowdowns are caused by poor layout. We demonstrate a correlation between the read performance of a directory scan and the locality within a file system's access patterns, using a dynamic layout score. We complement these results with microbenchmarks that show that space pressure can cause a substantial amount of inter-file and intra-file fragmentation. However, our results suggest that the effect of free-space fragmentation on read performance is best described as accelerating the file system aging process. The effect on write performance is non-existent in some cases, and, in most cases, an order of magnitude smaller than the read degradation from fragmentation caused by normal usage. In short, many file systems are exquisitely prone to read aging after a variety of write patterns. We show, however, that aging is not inevitable. BetrFS, a file system based on write-optimized dictionaries, exhibits almost no aging in our experiments. We present a framework for understanding and predicting aging, and identify the key features of BetrFS that avoid aging.

cs.OS↗

arXiv2023

Tensor Decompositions Meet Control Theory: Learning General Mixtures of Linear Dynamical Systems

Recently Chen and Poor initiated the study of learning mixtures of linear dynamical systems. While linear dynamical systems already have wide-ranging applications in modeling time-series data, using mixture models can lead to a better fit or even a richer understanding of underlying subpopulations represented in the data. In this work we give a new approach to learning mixtures of linear dynamical systems that is based on tensor decompositions. As a result, our algorithm succeeds without strong separation conditions on the components, and can be used to compete with the Bayes optimal clustering of the trajectories. Moreover our algorithm works in the challenging partially-observed setting. Our starting point is the simple but powerful observation that the classic Ho-Kalman algorithm is a close relative of modern tensor decomposition methods for learning latent variable models. This gives us a playbook for how to extend it to work with more complicated generative models.

cs.LG↗

arXiv2023

A Near-Linear Time Algorithm for the Chamfer Distance

For any two point sets $A,B \subset \mathbb{R}^d$ of size up to $n$, the Chamfer distance from $A$ to $B$ is defined as $\text{CH}(A,B)=\sum_{a \in A} \min_{b \in B} d_X(a,b)$, where $d_X$ is the underlying distance measure (e.g., the Euclidean or Manhattan distance). The Chamfer distance is a popular measure of dissimilarity between point clouds, used in many machine learning, computer vision, and graphics applications, and admits a straightforward $O(d n^2)$-time brute force algorithm. Further, the Chamfer distance is often used as a proxy for the more computationally demanding Earth-Mover (Optimal Transport) Distance. However, the \emph{quadratic} dependence on $n$ in the running time makes the naive approach intractable for large datasets. We overcome this bottleneck and present the first $(1+ε)$-approximate algorithm for estimating the Chamfer distance with a near-linear running time. Specifically, our algorithm runs in time $O(nd \log (n)/\varepsilon^2)$ and is implementable. Our experiments demonstrate that it is both accurate and fast on large high-dimensional datasets. We believe that our algorithm will open new avenues for analyzing large high-dimensional point clouds. We also give evidence that if the goal is to \emph{report} a $(1+\varepsilon)$-approximate mapping from $A$ to $B$ (as opposed to just its value), then any sub-quadratic time algorithm is unlikely to exist.

cs.DS↗

arXiv2023

Krylov Methods are (nearly) Optimal for Low-Rank Approximation

We consider the problem of rank-$1$ low-rank approximation (LRA) in the matrix-vector product model under various Schatten norms: $$ \min_{\|u\|_2=1} \|A (I - u u^\top)\|_{\mathcal{S}_p} , $$ where $\|M\|_{\mathcal{S}_p}$ denotes the $\ell_p$ norm of the singular values of $M$. Given $\varepsilon>0$, our goal is to output a unit vector $v$ such that $$ \|A(I - vv^\top)\|_{\mathcal{S}_p} \leq (1+\varepsilon) \min_{\|u\|_2=1}\|A(I - u u^\top)\|_{\mathcal{S}_p}. $$ Our main result shows that Krylov methods (nearly) achieve the information-theoretically optimal number of matrix-vector products for Spectral ($p=\infty$), Frobenius ($p=2$) and Nuclear ($p=1$) LRA. In particular, for Spectral LRA, we show that any algorithm requires $Ω\left(\log(n)/\varepsilon^{1/2}\right)$ matrix-vector products, exactly matching the upper bound obtained by Krylov methods [MM15, BCW22]. Our lower bound addresses Open Question 1 in [Woo14], providing evidence for the lack of progress on algorithms for Spectral LRA and resolves Open Question 1.2 in [BCW22]. Next, we show that for any fixed constant $p$, i.e. $1\leq p =O(1)$, there is an upper bound of $O\left(\log(1/\varepsilon)/\varepsilon^{1/3}\right)$ matrix-vector products, implying that the complexity does not grow as a function of input size. This improves the $O\left(\log(n/\varepsilon)/\varepsilon^{1/3}\right)$ bound recently obtained in [BCW22], and matches their $Ω\left(1/\varepsilon^{1/3}\right)$ lower bound, to a $\log(1/\varepsilon)$ factor.

cs.DS↗

arXiv2023

A New Approach to Learning Linear Dynamical Systems

Linear dynamical systems are the foundational statistical model upon which control theory is built. Both the celebrated Kalman filter and the linear quadratic regulator require knowledge of the system dynamics to provide analytic guarantees. Naturally, learning the dynamics of a linear dynamical system from linear measurements has been intensively studied since Rudolph Kalman's pioneering work in the 1960's. Towards these ends, we provide the first polynomial time algorithm for learning a linear dynamical system from a polynomial length trajectory up to polynomial error in the system parameters under essentially minimal assumptions: observability, controllability, and marginal stability. Our algorithm is built on a method of moments estimator to directly estimate Markov parameters from which the dynamics can be extracted. Furthermore, we provide statistical lower bounds when our observability and controllability assumptions are violated.

math.OC↗

arXiv2022

Sub-quadratic Algorithms for Kernel Matrices via Kernel Density Estimation

Kernel matrices, as well as weighted graphs represented by them, are ubiquitous objects in machine learning, statistics and other related fields. The main drawback of using kernel methods (learning and inference using kernel matrices) is efficiency -- given $n$ input points, most kernel-based algorithms need to materialize the full $n \times n$ kernel matrix before performing any subsequent computation, thus incurring $Ω(n^2)$ runtime. Breaking this quadratic barrier for various problems has therefore, been a subject of extensive research efforts. We break the quadratic barrier and obtain $\textit{subquadratic}$ time algorithms for several fundamental linear-algebraic and graph processing primitives, including approximating the top eigenvalue and eigenvector, spectral sparsification, solving linear systems, local clustering, low-rank approximation, arboricity estimation and counting weighted triangles. We build on the recent Kernel Density Estimation framework, which (after preprocessing in time subquadratic in $n$) can return estimates of row/column sums of the kernel matrix. In particular, we develop efficient reductions from $\textit{weighted vertex}$ and $\textit{weighted edge sampling}$ on kernel graphs, $\textit{simulating random walks}$ on kernel graphs, and $\textit{importance sampling}$ on matrices to Kernel Density Estimation and show that we can generate samples from these distributions in $\textit{sublinear}$ (in the support of the distribution) time. Our reductions are the central ingredient in each of our applications and we believe they may be of independent interest. We empirically demonstrate the efficacy of our algorithms on low-rank approximation (LRA) and spectral sparsification, where we observe a $\textbf{9x}$ decrease in the number of kernel evaluations over baselines for LRA and a $\textbf{41x}$ reduction in the graph size for spectral sparsification.

cs.LG↗

arXiv2022

Low-Rank Approximation with $1/ε^{1/3}$ Matrix-Vector Products

We study iterative methods based on Krylov subspaces for low-rank approximation under any Schatten-$p$ norm. Here, given access to a matrix $A$ through matrix-vector products, an accuracy parameter $ε$, and a target rank $k$, the goal is to find a rank-$k$ matrix $Z$ with orthonormal columns such that $\| A(I -ZZ^\top)\|_{S_p} \leq (1+ε)\min_{U^\top U = I_k} \|A(I - U U^\top)\|_{S_p}$, where $\|M\|_{S_p}$ denotes the $\ell_p$ norm of the the singular values of $M$. For the special cases of $p=2$ (Frobenius norm) and $p = \infty$ (Spectral norm), Musco and Musco (NeurIPS 2015) obtained an algorithm based on Krylov methods that uses $\tilde{O}(k/\sqrtε)$ matrix-vector products, improving on the naïve $\tilde{O}(k/ε)$ dependence obtainable by the power method, where $\tilde{O}$ suppresses poly$(\log(dk/ε))$ factors. Our main result is an algorithm that uses only $\tilde{O}(kp^{1/6}/ε^{1/3})$ matrix-vector products, and works for all $p \geq 1$. For $p = 2$ our bound improves the previous $\tilde{O}(k/ε^{1/2})$ bound to $\tilde{O}(k/ε^{1/3})$. Since the Schatten-$p$ and Schatten-$\infty$ norms are the same up to a $(1+ ε)$-factor when $p \geq (\log d)/ε$, our bound recovers the result of Musco and Musco for $p = \infty$. Further, we prove a matrix-vector query lower bound of $Ω(1/ε^{1/3})$ for any fixed constant $p \geq 1$, showing that surprisingly $\tildeΘ(1/ε^{1/3})$ is the optimal complexity for constant~$k$. To obtain our results, we introduce several new techniques, including optimizing over multiple Krylov subspaces simultaneously, and pinching inequalities for partitioned operators. Our lower bound for $p \in [1,2]$ uses the Araki-Lieb-Thirring trace inequality, whereas for $p>2$, we appeal to a norm-compression inequality for aligned partitioned operators.

cs.DS↗

arXiv2021

Robust and Sample Optimal Algorithms for PSD Low-Rank Approximation

Recently, Musco and Woodruff (FOCS, 2017) showed that given an $n \times n$ positive semidefinite (PSD) matrix $A$, it is possible to compute a $(1+ε)$-approximate relative-error low-rank approximation to $A$ by querying $O(nk/ε^{2.5})$ entries of $A$ in time $O(nk/ε^{2.5} +n k^{ω-1}/ε^{2(ω-1)})$. They also showed that any relative-error low-rank approximation algorithm must query $Ω(nk/ε)$ entries of $A$, this gap has since remained open. Our main result is to resolve this question by obtaining an optimal algorithm that queries $O(nk/ε)$ entries of $A$ and outputs a relative-error low-rank approximation in $O(n(k/ε)^{ω-1})$ time. Note, our running time improves that of Musco and Woodruff, and matches the information-theoretic lower bound if the matrix-multiplication exponent $ω$ is $2$. We then extend our techniques to negative-type distance matrices. Bakshi and Woodruff (NeurIPS, 2018) showed a bi-criteria, relative-error low-rank approximation which queries $O(nk/ε^{2.5})$ entries and outputs a rank-$(k+4)$ matrix. We show that the bi-criteria guarantee is not necessary and obtain an $O(nk/ε)$ query algorithm, which is optimal. Our algorithm applies to all distance matrices that arise from metrics satisfying negative-type inequalities, including $\ell_1, \ell_2,$ spherical metrics and hypermetrics. Next, we introduce a new robust low-rank approximation model which captures PSD matrices that have been corrupted with noise. While a sample complexity lower bound precludes sublinear algorithms for arbitrary PSD matrices, we provide the first sublinear time and query algorithms when the corruption on the diagonal entries is bounded. As a special case, we show sample-optimal sublinear time algorithms for low-rank approximation of correlation matrices corrupted by noise.

cs.DS↗

arXiv2021

Robustly Learning Mixtures of $k$ Arbitrary Gaussians

We give a polynomial-time algorithm for the problem of robustly estimating a mixture of $k$ arbitrary Gaussians in $\mathbb{R}^d$, for any fixed $k$, in the presence of a constant fraction of arbitrary corruptions. This resolves the main open problem in several previous works on algorithmic robust statistics, which addressed the special cases of robustly estimating (a) a single Gaussian, (b) a mixture of TV-distance separated Gaussians, and (c) a uniform mixture of two Gaussians. Our main tools are an efficient \emph{partial clustering} algorithm that relies on the sum-of-squares method, and a novel \emph{tensor decomposition} algorithm that allows errors in both Frobenius norm and low-rank terms.

cs.DS↗

arXiv2021

Learning a Latent Simplex in Input-Sparsity Time

We consider the problem of learning a latent $k$-vertex simplex $K\subset\mathbb{R}^d$, given access to $A\in\mathbb{R}^{d\times n}$, which can be viewed as a data matrix with $n$ points that are obtained by randomly perturbing latent points in the simplex $K$ (potentially beyond $K$). A large class of latent variable models, such as adversarial clustering, mixed membership stochastic block models, and topic models can be cast as learning a latent simplex. Bhattacharyya and Kannan (SODA, 2020) give an algorithm for learning such a latent simplex in time roughly $O(k\cdot\textrm{nnz}(A))$, where $\textrm{nnz}(A)$ is the number of non-zeros in $A$. We show that the dependence on $k$ in the running time is unnecessary given a natural assumption about the mass of the top $k$ singular values of $A$, which holds in many of these applications. Further, we show this assumption is necessary, as otherwise an algorithm for learning a latent simplex would imply an algorithmic breakthrough for spectral low rank approximation. At a high level, Bhattacharyya and Kannan provide an adaptive algorithm that makes $k$ matrix-vector product queries to $A$ and each query is a function of all queries preceding it. Since each matrix-vector product requires $\textrm{nnz}(A)$ time, their overall running time appears unavoidable. Instead, we obtain a low-rank approximation to $A$ in input-sparsity time and show that the column space thus obtained has small $\sinΘ$ (angular) distance to the right top-$k$ singular space of $A$. Our algorithm then selects $k$ points in the low-rank subspace with the largest inner product with $k$ carefully chosen random vectors. By working in the low-rank subspace, we avoid reading the entire matrix in each iteration and thus circumvent the $Θ(k\cdot\textrm{nnz}(A))$ running time.

cs.LG↗

arXiv2021

List-Decodable Subspace Recovery: Dimension Independent Error in Polynomial Time

In list-decodable subspace recovery, the input is a collection of $n$ points $αn$ (for some $α\ll 1/2$) of which are drawn i.i.d. from a distribution $\mathcal{D}$ with a isotropic rank $r$ covariance $Π_*$ (the \emph{inliers}) and the rest are arbitrary, potential adversarial outliers. The goal is to recover a $O(1/α)$ size list of candidate covariances that contains a $\hatΠ$ close to $Π_*$. Two recent independent works (Raghavendra-Yau, Bakshi-Kothari 2020) gave the first efficient algorithm for this problem. These results, however, obtain an error that grows with the dimension (linearly in [RY] and logarithmically in BK) at the cost of quasi-polynomial running time) and rely on \emph{certifiable anti-concentration} - a relatively strict condition satisfied essentially only by the Gaussian distribution. In this work, we improve on these results on all three fronts: \emph{dimension-independent} error via a faster fixed-polynomial running time under less restrictive distributional assumptions. Specifically, we give a $poly(1/α) d^{O(1)}$ time algorithm that outputs a list containing a $\hatΠ$ satisfying $\|\hatΠ -Π_*\|_F \leq O(1/α)$. Our result only needs $\mathcal{D}$ to have \emph{certifiably hypercontractive} degree 2 polynomials. As a result, in addition to Gaussians, our algorithm applies to the uniform distribution on the hypercube and $q$-ary cubes and arbitrary product distributions with subgaussian marginals. Prior work (Raghavendra and Yau, 2020) had identified such distributions as potential hard examples as such distributions do not exhibit strong enough anti-concentration. When $\mathcal{D}$ satisfies certifiable anti-concentration, we obtain a stronger error guarantee of $\|\hatΠ-Π_*\|_F \leq η$ for any arbitrary $η> 0$ in $d^{O(poly(1/α) + \log (1/η))}$ time.

cs.DS↗

arXiv2020

Outlier-Robust Clustering of Non-Spherical Mixtures

We give the first outlier-robust efficient algorithm for clustering a mixture of $k$ statistically separated d-dimensional Gaussians (k-GMMs). Concretely, our algorithm takes input an $ε$-corrupted sample from a $k$-GMM and whp in $d^{\text{poly}(k/η)}$ time, outputs an approximate clustering that misclassifies at most $k^{O(k)}(ε+η)$ fraction of the points whenever every pair of mixture components are separated by $1-\exp(-\text{poly}(k/η)^k)$ in total variation (TV) distance. Such a result was not previously known even for $k=2$. TV separation is the statistically weakest possible notion of separation and captures important special cases such as mixed linear regression and subspace clustering. Our main conceptual contribution is to distill simple analytic properties - (certifiable) hypercontractivity and bounded variance of degree 2 polynomials and anti-concentration of linear projections - that are necessary and sufficient for mixture models to be (efficiently) clusterable. As a consequence, our results extend to clustering mixtures of arbitrary affine transforms of the uniform distribution on the $d$-dimensional unit sphere. Even the information-theoretic clusterability of separated distributions satisfying these two analytic assumptions was not known prior to our work and is likely to be of independent interest. Our algorithms build on the recent sequence of works relying on certifiable anti-concentration first introduced in the works of Karmarkar, Klivans, and Kothari and Raghavendra, and Yau in 2019. Our techniques expand the sum-of-squares toolkit to show robust certifiability of TV-separated Gaussian clusters in data. This involves giving a low-degree sum-of-squares proof of statements that relate parameter (i.e. mean and covariances) distance to total variation distance by relying only on hypercontractivity and anti-concentration.

cs.DS↗

arXiv2020

Robust Linear Regression: Optimal Rates in Polynomial Time

We obtain robust and computationally efficient estimators for learning several linear models that achieve statistically optimal convergence rate under minimal distributional assumptions. Concretely, we assume our data is drawn from a $k$-hypercontractive distribution and an $ε$-fraction is adversarially corrupted. We then describe an estimator that converges to the optimal least-squares minimizer for the true distribution at a rate proportional to $ε^{2-2/k}$, when the noise is independent of the covariates. We note that no such estimator was known prior to our work, even with access to unbounded computation. The rate we achieve is information-theoretically optimal and thus we resolve the main open question in Klivans, Kothari and Meka [COLT'18]. Our key insight is to identify an analytic condition that serves as a polynomial relaxation of independence of random variables. In particular, we show that when the moments of the noise and covariates are negatively-correlated, we obtain the same rate as independent noise. Further, when the condition is not satisfied, we obtain a rate proportional to $ε^{2-4/k}$, and again match the information-theoretic lower bound. Our central technical contribution is to algorithmically exploit independence of random variables in the "sum-of-squares" framework by formulating it as the aforementioned polynomial inequality.

stat.ML↗

arXiv2020

Testing Positive Semi-Definiteness via Random Submatrices

We study the problem of testing whether a matrix $\mathbf{A} \in \mathbb{R}^{n \times n}$ with bounded entries ($\|\mathbf{A}\|_\infty \leq 1$) is positive semi-definite (PSD), or $ε$-far in Euclidean distance from the PSD cone, meaning that $\min_{\mathbf{B} \succeq 0} \|\mathbf{A} - \mathbf{B}\|_F^2 > εn^2$, where $\mathbf{B} \succeq 0$ denotes that $\mathbf{B}$ is PSD. Our main algorithmic contribution is a non-adaptive tester which distinguishes between these cases using only $\tilde{O}(1/ε^4)$ queries to the entries of $\mathbf{A}$. If instead of the Euclidean norm we considered the distance in spectral norm, we obtain the "$\ell_\infty$-gap problem", where $\mathbf{A}$ is either PSD or satisfies $\min_{\mathbf{B}\succeq 0} \|\mathbf{A}- \mathbf{B}\|_2 > εn$. For this related problem, we give a $\tilde{O}(1/ε^2)$ query tester, which we show is optimal up to $\log(1/ε)$ factors. Our testers randomly sample a collection of principal submatrices and check whether these submatrices are PSD. Consequentially, our algorithms achieve one-sided error: whenever they output that $\mathbf{A}$ is not PSD, they return a certificate that $\mathbf{A}$ has negative eigenvalues. We complement our upper bound for PSD testing with Euclidean norm distance by giving a $\tildeΩ(1/ε^2)$ lower bound for any non-adaptive algorithm. Our lower bound construction is general, and can be used to derive lower bounds for a number of spectral testing problems. As an example of the applicability of our construction, we obtain a new $\tildeΩ(1/ε^4)$ sampling lower bound for testing the Schatten-$1$ norm with a $εn^{1.5}$ gap, extending a result of Balcan, Li, Woodruff, and Zhang [SODA'19]. In addition, it yields new sampling lower bounds for estimating the Ky-Fan Norm, and the cost of the best rank-$k$ approximation.

cs.DS↗

arXiv2020

Weighted Maximum Independent Set of Geometric Objects in Turnstile Streams

We study the Maximum Independent Set problem for geometric objects given in the data stream model. A set of geometric objects is said to be independent if the objects are pairwise disjoint. We consider geometric objects in one and two dimensions, i.e., intervals and disks. Let $α$ be the cardinality of the largest independent set. Our goal is to estimate $α$ in a small amount of space, given that the input is received as a one-pass stream. We also consider a generalization of this problem by assigning weights to each object and estimating $β$, the largest value of a weighted independent set. We initialize the study of this problem in the turnstile streaming model (insertions and deletions) and provide the first algorithms for estimating $α$ and $β$. For unit-length intervals, we obtain a $(2+ε)$-approximation to $α$ and $β$ in poly$(\frac{\log(n)}ε)$ space. We also show a matching lower bound. Combined with the $3/2$-approximation for insertion-only streams by Cabello and Perez-Lanterno [CP15], our result implies a separation between the insertion-only and turnstile model. For unit-radius disks, we obtain a $\left(\frac{8\sqrt{3}}π\right)$-approximation to $α$ and $β$ in poly$(\log(n), ε^{-1})$ space, which is closely related to the hexagonal circle packing constant. We provide algorithms for estimating $α$ for arbitrary-length intervals under a bounded intersection assumption and study the parameterized space complexity of estimating $α$ and $β$, where the parameter is the ratio of maximum to minimum interval length.

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

Learning Two Layer Rectified Neural Networks in Polynomial Time

Consider the following fundamental learning problem: given input examples $x \in \mathbb{R}^d$ and their vector-valued labels, as defined by an underlying generative neural network, recover the weight matrices of this network. We consider two-layer networks, mapping $\mathbb{R}^d$ to $\mathbb{R}^m$, with $k$ non-linear activation units $f(\cdot)$, where $f(x) = \max \{x , 0\}$ is the ReLU. Such a network is specified by two weight matrices, $\mathbf{U}^* \in \mathbb{R}^{m \times k}, \mathbf{V}^* \in \mathbb{R}^{k \times d}$, such that the label of an example $x \in \mathbb{R}^{d}$ is given by $\mathbf{U}^* f(\mathbf{V}^* x)$, where $f(\cdot)$ is applied coordinate-wise. Given $n$ samples as a matrix $\mathbf{X} \in \mathbb{R}^{d \times n}$ and the (possibly noisy) labels $\mathbf{U}^* f(\mathbf{V}^* \mathbf{X}) + \mathbf{E}$ of the network on these samples, where $\mathbf{E}$ is a noise matrix, our goal is to recover the weight matrices $\mathbf{U}^*$ and $\mathbf{V}^*$. In this work, we develop algorithms and hardness results under varying assumptions on the input and noise. Although the problem is NP-hard even for $k=2$, by assuming Gaussian marginals over the input $\mathbf{X}$ we are able to develop polynomial time algorithms for the approximate recovery of $\mathbf{U}^*$ and $\mathbf{V}^*$. Perhaps surprisingly, in the noiseless case our algorithms recover $\mathbf{U}^*,\mathbf{V}^*$ exactly, i.e., with no error. To the best of the our knowledge, this is the first algorithm to accomplish exact recovery. For the noisy case, we give the first polynomial time algorithm that approximately recovers the weights in the presence of mean-zero noise $\mathbf{E}$. Our algorithms generalize to a larger class of rectified activation functions, $f(x) = 0$ when $x\leq 0$, and $f(x) > 0$ otherwise.

cs.DS↗

arXiv2018

Sublinear Time Low-Rank Approximation of Distance Matrices

Let $\mathbf{P}=\{ p_1, p_2, \ldots p_n \}$ and $\mathbf{Q} = \{ q_1, q_2 \ldots q_m \}$ be two point sets in an arbitrary metric space. Let $\mathbf{A}$ represent the $m\times n$ pairwise distance matrix with $\mathbf{A}_{i,j} = d(p_i, q_j)$. Such distance matrices are commonly computed in software packages and have applications to learning image manifolds, handwriting recognition, and multi-dimensional unfolding, among other things. In an attempt to reduce their description size, we study low rank approximation of such matrices. Our main result is to show that for any underlying distance metric $d$, it is possible to achieve an additive error low-rank approximation in sublinear time. We note that it is provably impossible to achieve such a guarantee in sublinear time for arbitrary matrices $\mathbf{A}$, and consequently our proof exploits special properties of distance matrices. We develop a recursive algorithm based on additive projection-cost preserving sampling. We then show that in general, relative error approximation in sublinear time is impossible for distance matrices, even if one allows for bicriteria solutions. Additionally, we show that if $\mathbf{P} = \mathbf{Q}$ and $d$ is the squared Euclidean distance, which is not a metric but rather the square of a metric, then a relative error bicriteria solution can be found in sublinear time.

cs.DS↗