MML-12-08: Adaptive Learning Rate Algorithms: AdaGrad, RMSProp, Adam & AdamW – Practice Quiz

MML-12-08: Adaptive Learning Rate Algorithms: AdaGrad, RMSProp, Adam & AdamW. 45 independently reviewed questions, including single-select and multiselect MCQs. Cognitive scope: Tier 2–3. Prerequisites: QS 12.7.

Learning goals: Interpret diagonal preconditioning.; Compute AdaGrad accumulators and sparse-coordinate behavior.; Analyze RMSProp exponential memory.; Compute Adam moment recursions.; Apply initialization bias corrections.; Diagnose numerical stability and state handling.; Distinguish coupled regularization from AdamW decay.; Compare optimizer invariance and practical limitations.

Progress from conceptual checks to worked calculations, ML diagnostics and derivations within the assigned scope. Every question includes content-based feedback for every choice and authoritative references. Select every correct choice when marked multiselect.

Photo by Clickout pixel on Pexels. Licensed under the Pexels License: https://www.pexels.com/license/.