AI Paper Atlas

Research map / Optimization / Optimizers

A Statistical Online Inference Approach in Averaged Stochastic Approximation

Chuhan Xie, Zhihua Zhang

NeurIPS 2022 · Optimization › Optimizers · approach: Stochastic gradient MCMC · 1 citations (OpenAlex)

Read the paper

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 random scaling instead of batch meansconstant step size SGD inference · Linear regression d=5, eta=0.01, n=5,000coverage rate (%): 69.8(1.451) -> 92.8(0.817)Improved
use random scaling instead of batch meansconstant step size SGD inference · Linear regression d=5, eta=0.01, n=40,000coverage rate (%): 86.7(1.073) -> 94.9(0.695)Improved
use random scaling instead of spectral varianceconstant step size SGD inference · Linear regression d=5, eta=0.01, n=5,000coverage rate (%): 88.6(1.005) -> 92.8(0.817)Improved
use random scaling instead of spectral varianceconstant step size SGD inference · Linear regression d=5, eta=0.1, n=40,000coverage rate (%): 92.7(0.822) -> 93.0(0.806)No clear effect
use random scaling instead of batch meansconstant step size SGD inference · Linear regression d=5, eta=0.1, n=40,000coverage rate (%): 92.8(0.817) -> 93.0(0.806)No clear effect
use random scaling instead of batch meansconstant step size SGD inference · Linear regression d=5, eta=0.01, n=40,000CI length: 0.015(0.001) -> 0.026(0.010)Hurt
use random scaling instead of spectral varianceconstant step size SGD inference · Linear regression d=5, eta=0.01, n=40,000CI length: 0.018(0.003) -> 0.026(0.010)Hurt
use random scaling instead of batch meansconstant step size SGD inference · Logistic regression d=5, eta=0.01, n=40,000coverage rate for beta*_1 (%): 55.9(1.570) -> 95.1(0.682)Improved
use random scaling instead of spectral varianceconstant step size SGD inference · Logistic regression d=5, eta=0.01, n=40,000coverage rate for beta*_1 (%): 89.7(0.961) -> 95.1(0.682)Improved
increase step size from 0.01 to 0.1 for batch meansbatch means inference · Linear regression d=5, n=5,000coverage rate (%): 69.8(1.451) -> 92.9(0.812)Improved
increase step size from 0.01 to 0.1 for random scalingrandom scaling inference · Linear regression d=5, n=5,000coverage rate (%): 92.8(0.817) -> 94.3(0.733)No clear effect
increase sample size from n=5,000 to n=40,000 for batch meansbatch means inference · Linear regression d=5, eta=0.01coverage rate (%): 69.8(1.451) -> 86.7(1.073)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