Memorizing without overfitting: Bias, variance, and interpolation in over-parameterized models

The bias-variance trade-off is a central concept in supervised learning. In classical statistics, increasing the complexity of a model (e.g., number of parameters) reduces bias but also increases variance. Until recently, it was commonly believed that optimal performance is achieved at intermediate model complexities which strike a balance between bias and variance. Modern Deep Learning methods flout this dogma, achieving state-of-the-art performance using "over-parameterized models" where the number of fit parameters is large enough to perfectly fit the training data. As a result, understanding bias and variance in over-parameterized models has emerged as a fundamental problem in machine learning. Here, we use methods from statistical physics to derive analytic expressions for bias and variance in three minimal models for over-parameterization (linear regression and two-layer neural networks with linear and nonlinear activation functions), allowing us to disentangle properties stemming from the model architecture and random sampling of data. All three models exhibit a phase transition to an interpolation regime where the training error is zero. At the interpolation transition for each model, the test error diverges due to diverging variance (while bias remains finite). In contrast with classical intuition, we also show that over-parameterized models can overfit even in the absence of noise and exhibit bias even if the student and teacher models match. We synthesize these results to construct a holistic understanding of generalization error and the bias-variance trade-off in over-parameterized models and relate our results to random matrix theory.