AI Paper Atlas

Research map / Optimization / Implicit bias and generalization

On the Utility of Equal Batch Sizes for Inference in Stochastic Gradient Descent

Rahul Singh, Abhinek Shukla, Dootika Vats

JMLR 2025 · Optimization › Implicit bias and generalization · approach: SGD noise and flat minima · 3 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 equal batch sizes (EBS) instead of increasing batch sizes (IBS) (ablation)batch-means covariance estimator for ASGD · Linear regression, d=5 and d=20, 1000 replicationsrelative Frobenius error, coverage, region volumeImproved
add lugsail bias correction to EBS (Sigma_L = 2 Sigma_2b - Sigma_b) (ablation)EBS batch-means estimator · Linear regression and LAD regressionbias, coverage, volumeImproved
use polynomial batch size floor(c n^beta) instead of power-of-two doubling batch size (ablation)EBS estimator · Linear regression d=5monotonic behavior in sample sizeImproved
use simultaneous hyper-rectangular region C(z*) rather than ellipsoid with IBSIBS estimator · Linear regression and LAD regressioncoverage versus volumeMixed
use batch-size exponent beta=(1+alpha)/2 instead of numerically optimal value for finite n (ablation)EBS estimator · alpha=0.51, n in thousandsmean-square error bound: 0.66Mixed
classify using lower confidence bound of predicted probability with EBS standard errors (ablation)logistic classifier trained by ASGD · Santander, Covertype, Spambase, diabetes datasetstest misclassification rateImproved

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