Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,742 papers · 148 categories

Trend · papers per month

220441661881 · Jun 202019922001200920172026
48 results for sketching algorithms

A fast sketching algorithm solves regularized least squares problems efficiently.

problem Solving large-scale optimization problems with convex or nonconvex regularization.
method Sketching for Regularized Optimization (SRO) algorithm that generates a sketch of the original data matrix and solves the sketched problem.
result General theoretical results for the approximation error between the original and sketched problems, including minimax rates for sparse signal estimation.

Unified bounds for sketched bilinear forms in machine learning and statistics.

problem Uniform bounds on sketched bilinear forms for modern analyses.
method Generic chaining and new techniques for handling suprema over pairs of sets.
result Improved convergence bounds for sketched Federated Learning and bandit algorithms.

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

problem Heavy spectral tails in streaming matrices lead to linear regret in sketch-based linear bandits.
method Dyadic Block Sketching, a multi-scale matrix sketching approach.
result Achieves sublinear regret bounds without prior knowledge of streaming matrix properties.

Sketch-BERT learns vector sketches using BERT-like self-supervised learning.

problem Lack of effective vector sketch representation for recognition and retrieval tasks.
method Generalized BERT to sketch domain with novel embedding networks and self-supervised sketch gestalt learning.
result Improved performance on sketch recognition, retrieval, and gestalt tasks.

We consider statistical as well as algorithmic aspects of solving large-scale least-squares (LS) problems using randomized sketching algorithms. For a LS problem with input data (X,Y)Rn×p×Rn(X, Y) \in \mathbb{R}^{n \times p} \times \mathbb{R}^n, sketching algorithms use a sketching matrix, SRr×nS\in\mathbb{R}^{r \times n} with $r \…

2014-06-23abs ↗pdf ↗

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

problem Optimizing positions of CountSketch non-zero entries for better data compression.
method Learning algorithm that optimizes both values and positions of CountSketch non-zero entries.
result Improves accuracy for low rank approximation and other problems like k-means clustering.

Iterative Hessian sketch (IHS) is an effective sketching method for modeling large-scale data. It was originally proposed by Pilanci and Wainwright (2016; JMLR) based on randomized sketching matrices. However, it is computationally intensive due to the iterative sketch process. In this paper, we analyze the IHS algorit…

2019-02-20abs ↗pdf ↗

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 mm allows a O(md)\mathcal{O}(md) update time for both algorithms, as opposed to Ω(d2)Ω(d^2) req…

2018-09-28abs ↗pdf ↗

New algorithm converts data into sub-gaussian designs efficiently.

problem Efficiently converting large datasets into sub-gaussian random designs for robust performance.
method Algorithmic Gaussianization through sketching and averaging, using LESS embeddings.
result Efficient data sketches nearly indistinguishable from sub-gaussian designs.

FetchSGD reduces communication in federated learning with sketching.

problem Communication bottlenecks and convergence issues in federated learning.
method FetchSGD uses Count Sketch to compress and merge model updates efficiently.
result FetchSGD achieves high compression rates and good convergence without sparse client participation.

One-pass private sketch supports various machine learning tasks.

problem Efficiently supporting multiple machine learning tasks with differential privacy.
method Randomized contingency tables indexed with locality-sensitive hashing, constructed in one pass.
result Competitive error bounds for DP kernel density estimation, faster than existing methods.

New algorithm reduces rank constrained optimization problems.

problem Rank constrained optimization problems in machine learning and statistics.
method Recursive Importance Sketching (RISRO) algorithm.
result RISRO offers clear advantages over existing algorithms and converges efficiently.

Large-scale distributed training of neural networks is often limited by network bandwidth, wherein the communication time overwhelms the local computation time. Motivated by the success of sketching methods in sub-linear/streaming algorithms, we introduce Sketched SGD, an algorithm for carrying out distributed SGD by c…

2019-03-12abs ↗pdf ↗

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…

2019-12-02abs ↗pdf ↗

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

problem Improving convergence rates of sketch-and-project methods for solving linear systems and non-linear optimization problems.
method Developing a theoretical framework and new spectral bounds for the expected sketched projection matrix.
result The convergence rate improves linearly with sketch size and even faster with certain spectral decays.

DiPS learns to optimize sketching policies for better recommendation quality.

problem Optimizing sketching policies for long-term user interest prediction in recommender systems.
method Differentiable policy for sketching that learns from training data.
result DiPS requires up to 50% fewer sketch items to achieve the same recommendation quality.

Improved sketching for logistic and 1\ell_1 regression with near-linear dimensions.

problem Efficiently approximate 1\ell_1 and logistic regression problems.
method New sketching techniques achieving near-linear dimensions for both problems.
result Achieved near-linear sketching dimensions for 1\ell_1 and logistic regression.

Recent work has explored transforming data sets into smaller, approximate summaries in order to scale Bayesian inference. We examine a related problem in which the parameters of a Bayesian model are very large and expensive to store in memory, and propose more compact representations of parameter values that can be use…

2018-10-02abs ↗pdf ↗

Tensor CANDECOMP/PARAFAC (CP) decomposition has wide applications in statistical learning of latent variable models and in data mining. In this paper, we propose fast and randomized tensor CP decomposition algorithms based on sketching. We build on the idea of count sketches, but introduce many novel ideas which are un…

2015-06-14abs ↗pdf ↗

Sketch-GNN reduces GNN training time and memory usage to sublinear scales.

problem Training GNNs on large graphs is computationally expensive and memory-intensive.
method Develops a sketch-based algorithm that trains GNNs on compact sketches of graph adjacency and node embeddings.
result Training time and memory usage grow sublinearly with respect to graph size.

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…

2018-05-21abs ↗pdf ↗

Paper proposes a new method for density estimation using tree tensor-network states.

problem Density estimation for complex graphical models with loops.
method Determines tree topology with Chow-Liu algorithm and uses sketching techniques to define tensor-network components.
result Sample complexity guarantees and empirical validation provided.

FedSKETCH and FedSKETCHGATE improve privacy and efficiency in federated learning.

problem Communication and privacy challenges in federated learning.
method Compression of local gradients using count sketch to protect privacy and reduce communication.
result Sharp convergence guarantees and experimental validation of the methods.

MLE and CVE are equivalent under exponential families, leading to faster and more stable EM algorithms.

problem Finding maximum likelihood estimators (MLE) efficiently and stably.
method Proved equivalence between MLE and CVE under exponential families, leading to an EM algorithm.
result EM algorithm achieves the same asymptotic variance as MLE and is faster and more stable.

We present the first sublinear memory sketch that can be queried to find the nearest neighbors in a dataset. Our online sketching algorithm compresses an N element dataset to a sketch of size O(Nblog3N)O(N^b \log^3 N) in O(N(b+1)log3N)O(N^{(b+1)} \log^3 N) time, where b<1b < 1. This sketch can correctly report the nearest neighbors of any …

2019-02-18abs ↗pdf ↗

Paper improves tensor approximation for streaming data.

problem Challenges in finding accurate low-tubal-rank tensor approximations in streaming settings.
method Extends Frequent Directions for efficient low-tubal-rank tensor approximation.
result The new algorithm achieves arbitrarily small approximation error with linear sketch size growth.

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

problem Efficiency bottleneck in power method for large target ranks.
method Developed an algorithmic and theoretical framework for accelerating the power method using fast sketching.
result Simple and provably efficient methods for singular value decomposition, low-rank factorization, and Nyström approximation.

We introduce features for massive data streams. These stream features can be thought of as "ordered moments" and generalize stream sketches from "moments of order one" to "ordered moments of arbitrary order". In analogy to classic moments, they have theoretical guarantees such as universality that are important for lea…

2017-08-31abs ↗pdf ↗

Unified methodology for statistical inference in least squares and PCA via randomized sketching.

problem Statistical inference in least squares and PCA problems.
method Randomized sketching and projections, asymptotic normality of quadratic forms.
result Unified statistical inference methods for various sketching distributions.