Lion Optimizer's Role in CLIP Model Convergence and Zero-Shot Accuracy on Mixed-Domain Data

Abstract

Abstract: We present a method to formulate algorithm discovery as program search, and apply it to discover optimization algorithms for deep neural network training. We leverage efficient search techniques to explore an infinite and sparse program space. To bridge the large generalization gap between proxy and target tasks, we also introduce program selection and simplification strategies. Our method discovers a simple and effective optimization algorithm, \$textbf\Lion\\$ (\$textit\Evo\$textbf\L\\$ved S\$textbf\i\\$gn M\$textbf\o\\$me\$textbf\n\\$tum\\$). It is more memory-efficient than Adam as it only keeps

Research Question

What is the impact of the Lion optimizer on the convergence rate and final zero-shot accuracy of CLIP models when trained on mixed-domain datasets (e.g., LAION-400M + ImageNet-1K)?

Verification Level

Descriptive public verification status only; aggregate claim counts are public, but individual claim records are not exposed here.

Truth-Engine Gate Verdict

This record has not completed Gate 2 of the verification pipeline (a type-checked Lean4 proof for mathematical claims, or a sealed-sandbox reproduction for empirical claims). It is a literature synthesis only. VERIFIED requires an attached reproducible artifact (Lean4 proof source, or repro script and results) before this status can be set; it is not derived from review score or claim count.

Quality Tier

Descriptive public triage only; this tier does not alter current publication or DOI behavior.

Quality Dimensions

Automated triage signals derived from public fields; not human peer review or independent validation.

Correction Record

Public corrections are additive records. Current status does not claim the synthesis is error-free.

Provenance