Lorenzo Rosasco

NYTRO: When Subsampling Meets Early Stopping

2016 · CINECA IRIS Institutial Research Information System (University of Genoa)

Early stopping is a well known approach to reduce the time complexity for performing training and model selection of large scale learning machines. On the other hand, memory/space (rather than time) complexity is the main …

From inexact optimization to learning via gradient concentration

2021 · arXiv (Cornell University)

Optimization in machine learning typically deals with the minimization of empirical objectives defined by training data. However, the ultimate goal of learning is to minimize the error on future data (test error), for which the …

Scalable Causal Discovery with Score Matching

2023 · arXiv (Cornell University)

This paper demonstrates how to discover the whole causal graph from the second derivative of the log-likelihood in observational non-linear additive Gaussian noise models. Leveraging scalable machine learning approaches to approximate the score function $\nabla …