AI Paper Atlas

Research map / Learning theory and algorithms / Kernels and regression theory

Sub-optimality of the Naive Mean Field approximation for proportional high-dimensional Linear Regression

Jiaze Qiu

NeurIPS 2023 · Learning theory and algorithms › Kernels and regression theory · approach: High-dimensional linear regression theory · 0 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 NMF distribution to build 95% credible regions for Gaussian spike-and-slab prior in the proportional regimeNaive Mean Field approximation · Gaussian spike-and-slab prior, iid Gaussian design, n/p = alphaaverage coverage rate vs 95% nominalHurt
build credible intervals from quantiles of B given the NMF mean estimate instead of NMF posterior quantilesNMF-based credible regions · proportional asymptotics, pi = pi*asymptotic coverageImproved
use NMF log-normalizing constant instead of the true oneNMF free energy · Gaussian spike-and-slab priorlog-normalizing constant accuracyHurt
NMF in the regime p = o(n) instead of p = Theta(n)NMF approximation for linear regression · high-dimensional linear regressionapproximation qualityImproved
NMF in the setting where posterior mean estimation error is measuredNMF with spike-and-slab prior · mean square errorMSENo clear effect
set q close to 1 in the spike-and-slab prior when solving the fixed point equationfixed-point evaluation of theory · Gaussian spike-and-slabfixed point convergenceHurt
check theory by gradient descent on the NMF objective with n=8000asymptotic predictions · Gaussian spike-and-slabagreement with simulationImproved

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