AI Paper Atlas

Research map / Learning theory and algorithms / Prediction and decision losses

Path following algorithms for $\ell_2$-regularized $M$-estimation with approximation guarantee

Yunzhang Zhu, Renxiong Liu

NeurIPS 2023 · Learning theory and algorithms › Prediction and decision losses · approach: Determinantal point process inference · 0 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
proposed grid selection and adaptive stopping vs equally spaced log-scale grid with fixed toleranceNewton path following · ridge regression, n=1000, p=500 and 10000runtime vs suboptimalityImproved
proposed grid selection vs Ndiaye's adaptive unilateral schemeNewton path following · l2-regularized logistic regression, simulatedruntime vs suboptimalityImproved
proposed Newton method vs baseline and Ndiaye on real dataNewton path following · a9a (LIBSVM)runtime vs suboptimalityImproved
mixed method (gradient descent then Newton) vs pure gradient descentpath following · ridge regressionruntime vs suboptimalityNo clear effect
mixed method vs pure gradient descentpath following · l2-regularized logistic regressionruntime vs suboptimalityImproved
Newton vs gradient descent and mixed methods as dimension growspath following · p=500 vs p=10000runtimeMixed
vary approximation level epsilon on iterations per grid pointpath following · ridge and logistic regressioniterations per grid pointNo clear effect
smaller initial step size alpha_1Algorithm 1 · theoryapproximation errorMixed

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