Fred Roosta

Exchangeability and Kernel Invariance in Trained MLPs

2018 · arXiv (Cornell University)

In the analysis of machine learning models, it is often convenient to assume that the parameters are IID. This assumption is not satisfied when the parameters are updated through training processes such as SGD. A …

Exchangeability and Kernel Invariance in Trained MLPs

2019

In the analysis of machine learning models, it is often convenient to assume that the parameters are IID. This assumption is not satisfied when the parameters are updated through training processes such as Stochastic Gradient …

Importance Sampling for Nonlinear Models

2025 · arXiv (Cornell University)

While norm-based and leverage-score-based methods have been extensively studied for identifying "important" data points in linear models, analogous tools for nonlinear models remain significantly underdeveloped. By introducing the concept of the adjoint operator of a …