AI Paper Atlas

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

Distributed estimation of the inverse Hessian by determinantal averaging

Michal Derezinski, Michael W. Mahoney

NeurIPS 2019 · Learning theory and algorithms › Matrix and tensor methods · approach: Low-rank approximation theory · 11 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
Weight local Newton-step estimates by the determinant of each local Hessian instead of averaging uniformlyDistributed Newton's method · Abalone, cpusmall, mg, cadataNewton-step estimation errorImproved
Use uniform averaging instead of determinant weightingDistributed Newton's method · Abalone, cpusmall, mg, cadataNewton-step estimation errorHurt
Use determinant weighting of local Hessian inversesDistributed Newton's method · As the number of machines growsNewton-step estimation errorImproved
Use determinant weighting with small local sample sizesDistributed Newton's method · Some libsvm datasetsVariance of Newton-step estimatesHurt

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