AI Paper Atlas

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

When Does Adaptation Win? Scaling Laws for Meta-Learning in Quantum Control

Nima Leclerc, Chris Miller, Nicholas Peter Brawand

ICML 2026 · 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
add K=10 task-specific adaptation stepsFOMAML meta-init · Two-qubit CZ gate, 10x OOD noisegate fidelity: 54.2% -> 95.7%Improved
add K=10 adaptation stepsFOMAML meta-init · Single-qubit X gate, mild OODfidelity F: 0.959 -> 0.960No clear effect
add K=10 adaptation stepsfixed-average baseline · Single-qubit X gate, mild OODfidelity F: 0.881 -> 0.935Improved
adaptation when task variance is small (sigma^2 < 0.002)FOMAML · Single-qubit X gateadaptation gap: G_inf ~ 0No clear effect
increase task varianceadaptation gap asymptote · Single-qubit X gateasymptotic gap G_inf: linear scaling, R2 = 0.94Improved
add adaptation steps (K) beyond about 20FOMAML · Single-qubit X gateadaptation gap: beta = 0.083No clear effect
adaptation alone without task parameter xi vs blind baseline (ablation)FOMAML · Two-qubit gate, mild OODfidelity: +0.184Improved
adaptation alone without task parameter xi vs blind baseline (ablation)FOMAML · Two-qubit gate, strong OOD 10xfidelity: +0.158Improved
use 30% noisy xi instead of exact xi (ablation)FOMAML · Two-qubit gatefidelityNo clear effect
increase inner-loop learning rate beyond 2e-2 (ablation)adaptation rate beta · Single-qubit X gateadaptation rate betaHurt
increase inner-loop learning rate up to 2e-2 (ablation)adaptation rate beta · Single-qubit X gateadaptation rate betaImproved
use meta-initialization instead of non-adaptive GRAPEFOMAML (K=0) · Single-qubit X gategate fidelity (%): 97.9% -> 98.9%Improved

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