The Benefits of Reusing Batches for Gradient Descent in Two-Layer Networks: Breaking the Curse of Information and Leap Exponents

About
Privacy
Disclaimer

Graph Chatbot

Related publications (23)

Page 2 of 2

AN l(p) THEORY OF PCA AND SPECTRAL CLUSTERING

Emmanuel Abbé

Principal Component Analysis (PCA) is a powerful tool in statistics and machine learning. While existing study of PCA focuses on the recovery of principal components and their associated eigenvalues, there are few precise characterizations of individual pr ...

Institute of Mathematical Statistics2022

Exact Neural Networks from Inexact Multipliers via Fibonacci Weight Encoding

David Atienza Alonso, Giovanni Ansaloni, Marina Zapater Sancho, Alexandre Sébastien Julien Levisse, William Andrew Simon

Edge devices must support computationally demanding algorithms, such as neural networks, within tight area/energy budgets. While approximate computing may alleviate these constraints, limiting induced errors remains an open challenge. In this paper, we pro ...

2021

Modeling of Stream Metabolism from Reach-scale to the Scale of Entire River Networks

Pier Luigi Segatto

Streams are key components of the global carbon (C) cycle. The river network conceptualization moved from the pipelineâ idea, in which C is solely transported, to the active ecosystemâ concept, in which both terrestrial derived and autochthonous C ...

EPFL2021