AI Paper Atlas

Research map / Optimization / Optimizers

Adam Can Converge Without Any Modification On Update Rules

Yushun Zhang, Congliang Chen, Naichen Shi, Ruoyu Sun, Zhi-Quan Luo

NeurIPS 2022 · Optimization › Optimizers · approach: Adam convergence and adaptive learning rates · 6 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 small β₂ in the paper's divergent hyperparameter regionAdam on a fixed finite-sum function class · Constructed smooth convex functioniterates and function values: nullHurt
Increase β₂Adam on the constructed function, initialized at x = -5 · Constructed functiongradient norm: β₂ = 0, 0.1,0.3,0.5,0.7,0.9,0.99Improved
Use small β₁ and β₂Adam · MNIST and CIFAR-10optimization error: 1.4 timesHurt
Use small β₁ and β₂Adam · Convex function (defined in the paper)optimization error: 70 timesHurt
Increase β₂Adam with D₀ > 0 · Stochastic quadratic functionsize of convergence region: nullImproved
Reduce batchsize, which increases the number of batches nAdam with β₁ fixed at 0.9 · MNISTtraining loss: nullHurt
Increase nAdam on the constructed function · Function initialized at x = 1optimality gap: n =5, 10 ,15, 20Mixed

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