AI Paper Atlas

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

Bayesian Extensive-Rank Matrix Factorization with Rotational Invariant Priors

Farzad Pourkamali, Nicolas Macris

NeurIPS 2023 · Learning theory and algorithms › Matrix and tensor methods · approach: Matrix completion and factorization · 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
Use the algorithmic RIE instead of the Oracle estimatorRIE for X · Matrix factorization with rotation invariant priors (N=2000, M=4000), Wishart Xnormalized MSENo clear effect
Use the square-root of the X^2 estimator instead of the full RIE for XRIE for X · Matrix factorization with rotation invariant priors (N=2000, M=4000), Wishart Xnormalized MSEHurt
Use the algorithmic RIE instead of the Oracle estimatorRIE for Y · Matrix factorization with rotation invariant priors (N=2000, M=4000), uniform spectrum on [1,3]normalized MSENo clear effect
Apply simple thresholding on the RIE outputRIE for sparse Bernoulli-Rademacher Y · Matrix factorization with rotation invariant priors (N=2000, M=4000), non-rotational-invariant priornormalized MSEImproved
Use the denoising RIE for the whole product XY instead of the product of MF RIEsRIE · Matrix factorization with rotation invariant priors (N=2000, M=4000), shifted Wigner X c=1normalized MSEImproved

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