AI Paper Atlas

Research map / Learning theory and algorithms / Matrix and tensor methods

Block Subsampled Randomized Hadamard Transform for Nyström Approximation on Distributed Architectures

Oleg Balabanov, Matthias Beaupère, Laura Grigori, Victor Lederer

ICML 2023 · Learning theory and algorithms › Matrix and tensor methods · approach: Randomized sketching for matrices · 1 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Replace Gaussian sketch with block SRHT in distributed Nyström / tall-skinny sketchingblock SRHT sketch · Distributed Nyström approximation (n=65536, 8x8 grid)runtime of Y=AΩ^T and ΩY: Gaussian up to 2.5x slowerImproved
Use block SRHT instead of Gaussian sketch for applying Ω to tall-skinny Vblock SRHT sketch · n=10^7, d=200, l=2000, up to p=1536 coresoverall runtime speedup: more than 2.5x speedupImproved
Use block SRHT instead of Gaussian sketch in weak scaling testblock SRHT sketch · n=10^5 x p, l=2000, up to p=1536runtime: about 2.5x reductionImproved
Use block SRHT instead of Gaussian sketch for Nyström approximation accuracyblock SRHT sketch · Nyström approximation, MNIST/YearPredictionMSD, trace-norm errorlow-rank approximation errorNo clear effect
Use block SRHT (memory) instead of Gaussian for n=10^8 sketchblock SRHT sketch · n=10^8, l=2000, distributedfeasibility / memoryImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy