AI Paper Atlas

Research map / Optimization / Optimizers

Meta-Descent for Online, Continual Prediction

Andrew Jacobsen, Matthew Schlegel, Cameron Linke, Thomas Degris, Adam White, Martha White

AAAI 2019 · Optimization › Optimizers · approach: SGD momentum and step-size schedules · 11 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
Combine AdaGain with RMSProp instead of using AdaGain with vanilla SGD (ablation)AdaGain · Rosenbrock functionoptimization performanceImproved
Use the linear-complexity approximation instead of full quadratic AdaGain (ablation)AdaGain with RMSProp · Rosenbrock functionoptimization performanceNo clear effect
Estimate the Jacobian with finite differences instead of analytic derivatives (ablation)Linear-complexity AdaGain · Rosenbrock functionoptimization performanceNo clear effect
Remove RMSProp from AdaGain (ablation)AdaGain · Rosenbrock functionoptimization performanceHurt
Use AdaGain rather than AMSGrad for online predictionTD(λ) on mobile robot data · Nexting robot sensor predictionsSMAPEImproved
Use AdaGain rather than Adam for off-policy TD(λ)Baird's counterexample · Baird's counterexamplevalue errorImproved
Adapt per-feature step-sizes with AdaGain rather than using a global step-sizeTD(λ) · Baird's counterexampledivergenceImproved
Use AdaGain rather than AMSGradOnline continual prediction · Stateless tracking problemMSEMixed
Use AdaGain rather than AdaGradOnline continual prediction · Stateless tracking problemMSEImproved
Use AdaGain rather than SMDOnline continual prediction · Rosenbrock functionoptimization performanceImproved
Use AdaGain rather than AMSGradOnline continual prediction · Mobile robot sensor predictionsadaptation speedImproved

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