Ridgeless Regression with Random Features
This work bridges interpolation theory and practical algorithms for machine learning researchers, but it appears incremental as it builds on existing theoretical studies.
The paper tackles the problem of understanding the generalization ability of ridgeless regression with random features and stochastic gradient descent, finding that random features error shows a double-descent curve and proposing a tunable kernel algorithm that optimizes spectral density during training.
Recent theoretical studies illustrated that kernel ridgeless regression can guarantee good generalization ability without an explicit regularization. In this paper, we investigate the statistical properties of ridgeless regression with random features and stochastic gradient descent. We explore the effect of factors in the stochastic gradient and random features, respectively. Specifically, random features error exhibits the double-descent curve. Motivated by the theoretical findings, we propose a tunable kernel algorithm that optimizes the spectral density of kernel during training. Our work bridges the interpolation theory and practical algorithm.