AI Paper Atlas

Research map / Optimization / Implicit bias and generalization

Gaussian Process Parameter Estimation Using Mini-batch Stochastic Gradient Descent: Convergence Guarantees and Empirical Benefits

Hao Chen, Lili Zheng, Raed Al Kontar, Garvesh Raskutti

JMLR 2022 · Optimization › Implicit bias and generalization · approach: SGD noise and flat minima

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 nearest-neighbor minibatches instead of uniform minibatches (ablation)sgGP · LevyRMSE: 0.594 -> 0.264Improved
use nearest-neighbor minibatches instead of uniform minibatches (ablation)sgGP · PM2.5RMSE: 0.570 -> 0.286Improved
use nearest-neighbor minibatches instead of uniform minibatches (ablation)sgGP · ProteinRMSE: 0.829 -> 0.659Improved
use nearest-neighbor minibatches instead of uniform minibatches (ablation)sgGP · QueryRMSE: 0.128 -> 0.054Improved
use nearest-neighbor minibatches instead of uniform minibatches (ablation)sgGP · EnergyRMSE: 0.711 -> 0.786Hurt
use nearest-neighbor minibatches instead of uniform minibatches (ablation)sgGP · BoreholeRMSE: 0.173 -> 0.172No clear effect
use nearest-neighbor minibatches instead of uniform minibatches (ablation)sgGP · Levy (noise variance estimate)learned noise std (true 0.174): 0.549 -> 0.200Improved
train GP with minibatch SGD (nn) instead of exact GP with full-data inferencesgGP (nn) vs EGP · PM2.5training time (min): 372.88 -> 4.24Improved
train GP with minibatch SGD (nn) instead of exact GP with full-data inferencesgGP (nn) vs EGP · Proteintraining time (min): 453.40 -> 2.63Improved
train GP with minibatch SGD (nn) instead of exact GPsgGP (nn) vs EGP · EnergyRMSE: 0.802 -> 0.786Improved
use sgGP (nn) instead of SVGPsgGP (nn) vs SVGP · Boreholetraining time (min): 1380.86 -> 65.19Improved
use sgGP (nn) instead of VecchiasgGP (nn) vs Vecchia · ProteinRMSE: 0.597 -> 0.659Hurt

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