Generalization and Memorization: The Bias Potential Model
arXiv:2011.14269
Abstract
Models for learning probability distributions such as generative models and density estimators behave quite differently from models for learning functions. One example is found in the memorization phenomenon, namely the ultimate convergence to the empirical distribution, that occurs in generative adversarial networks (GANs). For this reason, the issue of generalization is more subtle than that for supervised learning. For the bias potential model, we show that dimension-independent generalization accuracy is achievable if early stopping is adopted, despite that in the long term, the model either memorizes the samples or diverges.
Added new section on regularized model
References in corpus (7)
- Language Models are Few-Shot Learners
- Understanding deep learning requires rethinking generalization
- A Variational Approach to Enhanced Sampling and Free Energy Calculations
- Mode Regularized Generative Adversarial Networks
- CAN: Creative Adversarial Networks, Generating "Art" by Learning About Styles and Deviating from Style Norms
- A Priori Estimates of the Population Risk for Residual Networks
- Estimating Densities with Non-Parametric Exponential Families