AI Paper Atlas

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

Schatten Norms in Matrix Streams: Hello Sparsity, Goodbye Dimension

Vladimir Braverman, Robert Krauthgamer, Aditya Krishnan, Roi Sinoff

ICML 2020 · Learning theory and algorithms › Matrix and tensor methods · approach: Matrix completion and factorization · 5 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
Use adaptive importance sampling over row cycles in multiple row-order passesSchatten p estimation for k-sparse matrices · Row-order streams, even pspace dependence on matrix dimension: O_p(ε^{-2}k^{3p/2 - 3}) wordsImproved
Restrict the input to Laplacian matricesRow-order Schatten p algorithm · k-sparse Laplacian matricesspace: O_p(ε^{-2}k^{p/2}) wordsImproved
Assume nonzero entries lie in [α, β]Row-order Schatten p algorithm · k-sparse matrices with bounded positive nonzero entriesspace: O_p(ε^{-2}k^{p/2 - 1}(β/α)^{p/2-2}) wordsImproved
Use s sampled rows to cover multiple cycle segmentsRow-order Schatten p algorithm · k-sparse matrices, even ppasses: ⌊p/(2(s+1))⌋+1 passesImproved
Use the two-set sampling/BFS constructionRow-order Schatten p algorithm · k-sparse matrices, even ppasses: ⌊p/6⌋+1 passesImproved
Remove the sparsity requirement and use the p=4 methodSchatten 4-norm estimation · Arbitrary matrices in row-order streamsspace: tilde{O}_p(ε^{-2}) versus tilde{O}_p(ε^{-2}k)Improved

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