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

count % of corpus

4 results for “sketch-and-project”

Sharp Analysis of Sketch-and-Project Methods via a Connection to Randomized Singular Value Decompositionmath.OC

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.

sketch-and-project convergence rate randomized singular value decomposition spectral bounds sparse sketching

2022-08-20abs ↗pdf ↗

A Sketch-and-Project Analysis of Subsampled Natural Gradient Algorithmscs.LG

New analysis shows SNG's effectiveness in small samples.

problem Limited understanding of SNG in small data settings.

method Sketch-and-project analysis of SNG.

result Global convergence and rate characterization for SNG.

subsampled natural gradient sketch-and-project stochastic preconditioning convergence rate spectral decay

2025-08-28abs ↗pdf ↗

Turbocharging Gaussian Process Inference with Approximate Sketch-and-Projectcs.LG

ADASAP accelerates GP inference for large datasets.

problem Scaling Gaussian process inference to large datasets.

method Approximate sketch-and-project algorithm for solving linear systems.

result Sketch-and-project rapidly converges to true posterior mean.

Gaussian processes sketch-and-project Bayesian optimization large datasets accelerated inference

2025-05-19abs ↗pdf ↗

Inference of Online Newton Methods with Nesterov's Accelerated Sketchingstat.ML

Paper proposes an efficient online Newton method with Nesterov's acceleration for streaming data.

problem Efficient inference of online Newton methods with robustness to noise and ill-conditioning.

method Online Newton method with Hessian averaging and Nesterov's accelerated sketch-and-project solver.

result Global almost-sure convergence and asymptotic normality of the last iterate with non-asymptotic convergence guarantees.

online Newton method Hessian averaging Nesterov's acceleration streaming data robust inference

2026-04-25abs ↗pdf ↗