AI Paper Atlas

Research map / Optimization / Nonconvex and smooth optimization

Accelerating Adaptive Cubic Regularization of Newton's Method via Random Sampling

Xi Chen, Bo Jiang, Tianyi Lin, Shuzhong Zhang

JMLR 2022 · Optimization › Nonconvex and smooth optimization · approach: Adaptive first-order convex methods

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 Hessian sub-sampling with acceleration (SACR) versus the full-Hessian accelerated method ACRaccelerated adaptive cubic regularization · regularized logistic regression, 8 LIBSVM datasetslog norm of gradient vs epochsImproved
use SACR instead of LBFGS, MLBFGS and SGDregularized logistic regression solver · regularized logistic regression, 8 LIBSVM datasetslog norm of gradient vs epochsImproved
add acceleration phase to sub-sampled cubic regularization (SACR versus SCR, SCR-KL, SCR-BGM)sub-sampled cubic regularization · regularized logistic regression, 8 LIBSVM datasetslog norm of gradient vs epochsImproved
switch from the accelerated phase to plain SCR near the optimumSACR hybrid implementation · regularized logistic regression, 8 LIBSVM datasetslocal convergenceImproved
compare SACR to other sub-sampled cubic methods once iterates reach the local regionsub-sampled cubic regularization · regularized logistic regression, 8 LIBSVM datasetslog norm of gradient vs epochsNo 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