AI Paper Atlas

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

Meta-Learning PAC-Bayes Priors in Model Averaging

Yimin Huang, Weiran Huang, Liang Li, Zhenguo Li

AAAI 2020 · Learning theory and algorithms › Kernels and regression theory · approach: PAC-Bayes bounds · 7 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
add sequential batch sampling to RBMRBM · Example 1 Model 1 (0,5)MSPE: 48.23 -> 14.08Improved
add sequential batch sampling to RBMRBM · Example 1 Model 1 (0,1)MSPE: 2.03 -> 1.71Improved
add sequential batch sampling to RBMRBM · Example 1 Model 3 (0.9,5)MSPE: 38.51 -> 29.44Improved
add sequential batch sampling to RBMRBM · Example 1 Model 1 (0.9,1)MSPE: 3.71 -> 3.25Improved
replace SOIL with RBM (risk-bound weights)SOIL · Example 1 Model 1 (0,5)MSPE: 53.21 -> 48.23Improved
replace SOIL with RBMSOIL · Example 1 Model 1 (0.9,1)MSPE: 2.17 -> 3.71Hurt
use historical-data prior (HDR) instead of non-informative priorRBM · BGSMSPE: 13.54 -> 13.06Improved
use historical-data prior (HDR) instead of non-informative priorRBM · BardetMSPE: 0.0054 -> 0.0050Improved
use historical-data prior (HDR) instead of SOILSOIL · BGSMSPE: 16.74 -> 13.06Improved
use HDR meta-learned prior instead of MLAP/MAMLMLAP_M · Permuted MNIST 200 swapstest error (%): 3.4 -> 0.72Improved
use HDR instead of MAMLMAML · Permuted MNIST 200 swapstest error (%): 3.77 -> 0.72Improved
increase number of training tasksHDR · Permuted MNISTtest errorNo clear effect

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