arXiv research

Localized sketching improves matrix multiplication and ridge regression complexity.

New method reduces linear regret in high-dimensional bandit problems.

Matrix sketching is a recently developed data compression technique. An input matrix A is efficiently approximated with a smaller matrix B, so that B preserves most of the properties of A up to some guaranteed approximation ratio. In so doing numerical operations on big data sets become faster. Sketching algorithms gen…

Detecting emergence of a low-rank signal from high-dimensional data is an important problem arising from many applications such as camera surveillance and swarm monitoring using sensors. We consider a procedure based on the largest eigenvalue of the sample covariance matrix over a sliding window to detect the change. T…

Newton-LESS sparsifies Gaussian sketching for faster optimization.

The paper sharpens the analysis of sketch-and-project methods using randomized singular value decomposition.

We show that a simple randomized sketch of the matrix multiplicative weight (MMW) update enjoys (in expectation) the same regret bounds as MMW, up to a small constant factor. Unlike MMW, where every step requires full matrix exponentiation, our steps require only a single product of the form $e^A b$, which the Lanczos …

New methods for sketching non-PSD matrices improve regression and optimization tasks.

Paper proposes an online covariance estimator for sketched Newton methods.

We improve prediction risk estimation for large datasets using sketching and ridge regression.

New algorithm optimizes positions of CountSketch non-zero entries for better data compression.

We consider the problem of finding anomalies in high-dimensional data using popular PCA based anomaly scores. The naive algorithms for computing these scores explicitly compute the PCA of the covariance matrix which uses space quadratic in the dimensionality of the data. We give the first streaming algorithms that use …

A new method reduces the bias in estimating inverse covariance matrices from sketches.

Paper develops a bootstrap method for estimating sketched SVD errors.

Sketch Tomography improves quantum state estimation accuracy.

A new method improves convergence in low-rank approximation.

We accelerate the power method for strong low-rank approximation using fast sketching.

New algorithm for efficient prediction intervals in neural networks.

Develops accelerated methods for optimization using low-dimensional projected-gradient information.

This paper studies how to sketch element-wise functions of low-rank matrices. Formally, given low-rank matrix A = [Aij] and scalar non-linear function f, we aim for finding an approximated low-rank representation of the (possibly high-rank) matrix [f(Aij)]. To this end, we propose an efficient sketching-based algorithm…

We study how well one can recover sparse principal components of a data matrix using a sketch formed from a few of its elements. We show that for a wide class of optimization problems, if the sketch is close (in the spectral norm) to the original data matrix, then one can recover a near optimal solution to the optimiza…

This paper describes a suite of algorithms for constructing low-rank approximations of an input matrix from a random linear image of the matrix, called a sketch. These methods can preserve structural properties of the input matrix, such as positive-semidefiniteness, and they can produce approximations with a user-speci…

A new method uses matrix sketches for efficient graph clustering in dynamic environments.

Two new algorithms select matrix rows and columns to preserve distances.

A parallel optimization method for convex functions using Hessian sketching and debiasing.

We address the statistical and optimization impacts of the classical sketch and Hessian sketch used to approximately solve the Matrix Ridge Regression (MRR) problem. Prior research has quantified the effects of classical sketch on the strictly simpler least squares regression (LSR) problem. We establish that classical …

Several important applications, such as streaming PCA and semidefinite programming, involve a large-scale positive-semidefinite (psd) matrix that is presented as a sequence of linear updates. Because of storage limitations, it may only be possible to retain a sketch of the psd matrix. This paper develops a new algorith…

Fast matrix algorithms have become the fundamental tools of machine learning in big data era. The generalized matrix regression problem is widely used in the matrix approximation such as CUR decomposition, kernel matrix approximation, and stream singular value decomposition (SVD), etc. In this paper, we propose a fast …

We derive optimal statistical and computational complexity bounds for exp-concave stochastic minimization in terms of the effective dimension. For common eigendecay patterns of the population covariance matrix, this quantity is significantly smaller than the ambient dimension. Our results reveal interesting connections…

Skeinformer accelerates self-attention for long sequences with linear complexity.

Linear regression is a classic method of data analysis. In recent years, sketching -- a method of dimension reduction using random sampling, random projections, or both -- has gained popularity as an effective computational approximation when the number of observations greatly exceeds the number of variables. In this p…

We construct a matrix $M\in R^{m\otimes d^c}$ with just $m=O(c\,λ\,\varepsilon^{-2}\text{poly}\log1/\varepsilonδ)$ rows, which preserves the norm $\|Mx\|_2=(1\pm\varepsilon)\|x\|_2$ of all $x$ in any given $λ$ dimensional subspace of $R^d$ with probability at least $1-δ$. This matrix can be applied to tensors $x^{(1)}…

We introduce a "learning-based" algorithm for the low-rank decomposition problem: given an $n \times d$ matrix $A$, and a parameter $k$, compute a rank-$k$ matrix $A'$ that minimizes the approximation loss $\|A-A'\|_F$. The algorithm uses a training set of input matrices in order to optimize its performance. Specifical…

A fast sketching algorithm solves regularized least squares problems efficiently.

Randomized SVD shows phase transitions in noisy data.

Given a matrix $A\in \mathbb{R}^{n\times d}$ and a vector $b\in \mathbb{R}^n$, we consider the regression problem with $\ell_\infty$ guarantees: finding a vector $x'\in \mathbb{R}^d$ such that $\|x'-x^*\|_\infty \leq \fracε{\sqrt{d}}\cdot \|Ax^*-b\|_2\cdot \|A^\dagger\|$ where $x^*=\arg\min_{x\in \mathbb{R}^d}\|Ax-b\|…

We prove that two popular linear contextual bandit algorithms, OFUL and Thompson Sampling, can be made efficient using Frequent Directions, a deterministic online sketching technique. More precisely, we show that a sketch of size $m$ allows a $\mathcal{O}(md)$ update time for both algorithms, as opposed to $Ω(d^2)$ req…

Paper accelerates and secures distributed NMF.

Collaborative learning allows participants to jointly train a model without data sharing. To update the model parameters, the central server broadcasts model parameters to the clients, and the clients send updating directions such as gradients to the server. While data do not leave a client device, the communicated gra…

This article explores and analyzes the unsupervised clustering of large partially observed graphs. We propose a scalable and provable randomized framework for clustering graphs generated from the stochastic block model. The clustering is first applied to a sub-matrix of the graph's adjacency matrix associated with a re…

This paper concerns a fundamental class of convex matrix optimization problems. It presents the first algorithm that uses optimal storage and provably computes a low-rank approximation of a solution. In particular, when all solutions have low rank, the algorithm converges to a solution. This algorithm, SketchyCGM, modi…

Paper tackles catastrophic forgetting in sequential learning.

New method solves constrained stochastic optimization problems efficiently.

Improved ridge regression with Frequent Directions for large-scale tasks.

S$^3$Attention improves long sequence attention with smoothed skeleton sketching.

Kernel ridge regression (KRR) is a standard method for performing non-parametric regression over reproducing kernel Hilbert spaces. Given $n$ samples, the time and space complexity of computing the KRR estimate scale as $\mathcal{O}(n^3)$ and $\mathcal{O}(n^2)$ respectively, and so is prohibitive in many cases. We prop…

Improved estimator for least squares using random projections achieves smaller error.

The immense amount of daily generated and communicated data presents unique challenges in their processing. Clustering, the grouping of data without the presence of ground-truth labels, is an important tool for drawing inferences from data. Subspace clustering (SC) is a relatively recent method that is able to successf…