Part of Advances in Neural Information Processing Systems 36 (NeurIPS 2023) Main Conference Track
Zitong Yang, MICHAL LUKASIK, Vaishnavh Nagarajan, Zonglin Li, Ankit Rawat, Manzil Zaheer, Aditya K. Menon, Sanjiv Kumar
The impressive generalization performance of modern neural networks is attributed in part to their ability to implicitly memorize complex training patterns.Inspired by this, we explore a novel mechanism to improve model generalization via explicit memorization.Specifically, we propose the residual-memorization (ResMem) algorithm, a new method that augments an existing prediction model (e.g., a neural network) by fitting the model's residuals with a nearest-neighbor based regressor.The final prediction is then the sum of the original model and the fitted residual regressor.By construction, ResMem can explicitly memorize the training labels.We start by formulating a stylized linear regression problem and rigorously show that ResMem results in a more favorable test risk over a base linear neural network.Then, we empirically show that ResMem consistently improves the test set generalization of the original prediction model across standard vision and natural language processing benchmarks.