AI Paper Atlas

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

Smoothed Analysis of Discrete Tensor Decomposition and Assemblies of Neurons

Nima Anari, Constantinos Daskalakis, Wolfgang Maass, Christos Papadimitriou, Amin Saberi, Santosh Vempala

NeurIPS 2018 · Learning theory and algorithms › Matrix and tensor methods · approach: Randomized tensor decomposition algorithms · 6 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 echelon-tree analysis to handle coordinate-wise perturbations satisfying the nondeterminism conditionRank-one tensor components · Perturbed rank-one tensor componentsfailure probability for minimum singular value bound: n^{2{\ell}} p^{(1-c)n}Improved
Randomly perturb set memberships before tensor decompositionVenn diagram reconstruction · Venn diagram reconstruction from ℓ-wise intersectionsreconstruction guaranteeImproved
Use set-system construction to represent association graphsAssociation graphs · Association graph representationmaximum degree guaranteed representable: 2K/aImproved
Use block designs to represent association treesAssociation trees · Association tree representationmaximum degree guaranteed representable: 2K^2/a^2Improved
Allow randomized set sampling in the soft constructionSoft-model association graphs · Soft-model association graph representationmaximum degree guaranteed realizable: \frac{1}{e}\cdot \frac{K}{a}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