In this manuscript we consider Kernel Ridge Regression (KRR) under the Gaussian design.
Exponents for the decay of the excess generalization error of KRR have been reported in …

There is an increasing realization that algorithmic inductive biases are central in preventing
overfitting; empirically, we often see a benign overfitting phenomenon in overparameterized …

We study the generalization capability of nearly-interpolating linear regressors: ${\beta} $'s
whose training error $\tau $ is positive but small, ie, below the noise floor. Under a random …

Stochastic gradient descent (SGD) has been shown to generalize well in many deep
learning applications. In practice, one often runs SGD with a geometrically decaying …

This article provides convergence analysis of online stochastic gradient descent algorithms
for functional linear models. Adopting the characterizations of the slope function regularity …

Motivated by the recent successes of neural networks that have the ability to fit the data
perfectly\emph {and} generalize well, we study the noiseless model in the fundamental least …

Previous analysis of regularized functional linear regression in a reproducing kernel Hilbert
space (RKHS) typically requires the target function to be contained in this kernel space. This …

Abstract We introduce the``continuized''Nesterov acceleration, a close variant of Nesterov
acceleration whose variables are indexed by a continuous time parameter. The two …

Despite the empirical success of deep meta-learning, theoretical understanding of
overparameterized meta-learning is still limited. This paper studies the generalization of a …

We propose estimators based on kernel ridge regression for nonparametric causal functions
such as dose, heterogeneous and incremental response curves. The treatment and …