Review Focus on Error Decomposition
This review examines deep learning theory through the lens of error decomposition, systematically addressing approximation, statistical, and optimization errors.
Development of Error Analyses
We trace the development of error analyses from bounds on individual error components to frameworks that account for all three.
Dual Examples for Analysis Application
Using nonparametric regression and the Deep Ritz Method as dual running examples, we demonstrate how these analyses apply across fundamentally different loss structures.
Analysis Review Across Learning Fields
We then review representative analyses in scientific machine learning, generative learning, reinforcement learning, representation learning, and large language models, showing how learning errors affect solutions, distributions, and predictions through problem-specific arguments.
Key Clarifications in Analysis
Throughout, we clarify which error components are controlled, how they are combined, and what assumptions are needed to