An Online Bootstrap for Time Series
Resampling methods such as the bootstrap have proven invaluable in the field of machine
learning. However, the applicability of traditional bootstrap methods is limited when dealing …
learning. However, the applicability of traditional bootstrap methods is limited when dealing …
Bagging Improves Generalization Exponentially
Bagging is a popular ensemble technique to improve the accuracy of machine learning
models. It hinges on the well-established rationale that, by repeatedly retraining on …
models. It hinges on the well-established rationale that, by repeatedly retraining on …
Gaussian Approximation and Multiplier Bootstrap for Polyak-Ruppert Averaged Linear Stochastic Approximation with Applications to TD Learning
In this paper, we obtain the Berry-Esseen bound for multivariate normal approximation for
the Polyak-Ruppert averaged iterates of the linear stochastic approximation (LSA) algorithm …
the Polyak-Ruppert averaged iterates of the linear stochastic approximation (LSA) algorithm …
[PDF][PDF] THE STOCHASTIC GRADIENT DESCENT FROM A NONLINEAR TIME SERIES PERSPECTIVE
This paper revisits the statistical behaviors of Stochastic Gradient Descent (SGD) through a
novel perspective of time series analysis. Traditional approaches, mostly treating SGD as …
novel perspective of time series analysis. Traditional approaches, mostly treating SGD as …
SUBSAMPLED ENSEMBLE CAN IMPROVE GENERALIZA-TION TAIL EXPONENTIALLY
TT EXPONENTIALLY - openreview.net
Ensemble learning is a popular technique to improve the accuracy of machine learning
models. It hinges on the rationale that aggregating multiple weak models can lead to better …
models. It hinges on the rationale that aggregating multiple weak models can lead to better …