On the Multiple Descent of Minimum-Norm Interpolants and Restricted Lower Isometry of Kernels

Built on

Optimal rates for the regularized least-squares algorithm
Andrea Caponnetto and Ernesto De Vito · 2007
Earlier work this paper cites.
Learning without concentration
Shahar Mendelson · 2014
Earlier work this paper cites.
Bounding the smallest singular value of a random matrix without concentration
Vladimir Koltchinskii and Shahar Mendelson · 2015
Earlier work this paper cites.
Empirical entropy, minimax regret and minimax risk
Alexander Rakhlin, Karthik Sridharan, and Alexandre B. Tsybakov · 2017
Earlier work this paper cites.
Gradient descent provably optimizes over-parameterized neural networks
Original
Simon S Du, Xiyu Zhai, Barnabas Poczos, and Aarti Singh · 2018
Earlier work this paper cites.

Neural tangent kernel: Convergence and generalization in neural networks
Arthur Jacot, Franck Gabriel, and Clément Hongler · 2018
Cited alongside, same era.
Just interpolate: Kernel” ridgeless” regression can generalize
Tengyuan Liang and Alexander Rakhlin · 2018
Cited alongside, same era.
Consistency of interpolation with laplace kernels is a high-dimensional phenomenon
Original
Alexander Rakhlin and Xiyu Zhai · 2018
Cited alongside, same era.
Benign overfitting in linear regression
Original
Peter L Bartlett, Philip M Long, Gábor Lugosi, and Alexander Tsigler · 2019
Cited alongside, same era.
Reconciling modern machine learning and the bias-variance trade-off
Original
Mikhail Belkin, Daniel Hsu, Siyuan Ma, and Soumik Mandal
Cited in the paper.
Overfitting or perfect fitting? risk bounds for classification and regression rules that interpolate
Original
Mikhail Belkin, Daniel Hsu, and Partha Mitra
Cited in the paper.
To understand deep learning we need to understand kernel learning
Original
Mikhail Belkin, Siyuan Ma, and Soumik Mandal
Cited in the paper.
Does data interpolation contradict statistical optimality?
Original
Mikhail Belkin, Alexander Rakhlin, and Alexandre B Tsybakov
Cited in the paper.