AI Paper Atlas

Research map / Optimization / Nonconvex and smooth optimization

Closing the Gap: Tighter Analysis of Alternating Stochastic Gradient Methods for Bilevel Problems

NeurIPS 2021 · Optimization › Nonconvex and smooth optimization · approach: Penalty and implicit-gradient bilevel methods · 9 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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 single-timescale ALSET instead of two-timescale SCGDstochastic compositional optimization · 100 Book-to-Market portfolio, iteration 1000ln avg squared gradient norm: 2.57 -> 1.65Helped
use constant stepsizes instead of decreasing stepsizes in ALSET (ablation)ALSET · 100 Book-to-Market portfolio, iteration 1000ln avg squared gradient norm: 1.65 -> 2.06Hurt
use ALSET-const instead of SCGDstochastic compositional optimization · 100 Book-to-Market portfolio, iteration 1000ln avg squared gradient norm: 2.57 -> 2.06Helped
use ALSET instead of SCGD at very early iterationsstochastic compositional optimization · 100 Book-to-Market portfolio, iteration 10ln avg squared gradient norm: 5.32 -> 5.31No 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