all AI news
Sliding down the stairs: how correlated latent variables accelerate learning with neural networks
April 15, 2024, 4:42 a.m. | Lorenzo Bardone, Sebastian Goldt
cs.LG updates on arXiv.org arxiv.org
Abstract: Neural networks extract features from data using stochastic gradient descent (SGD). In particular, higher-order input cumulants (HOCs) are crucial for their performance. However, extracting information from the $p$th cumulant of $d$-dimensional inputs is computationally hard: the number of samples required to recover a single direction from an order-$p$ tensor (tensor PCA) using online SGD grows as $d^{p-1}$, which is prohibitive for high-dimensional inputs. This result raises the question of how neural networks extract relevant directions …
abstract arxiv cond-mat.stat-mech cs.lg data extract features gradient however information inputs math.pr math.st networks neural networks performance samples stat.ml stat.th stochastic type variables
More from arxiv.org / cs.LG updates on arXiv.org
Jobs in AI, ML, Big Data
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Lead GNSS Data Scientist
@ Lurra Systems | Melbourne
Senior Machine Learning Engineer (MLOps)
@ Promaton | Remote, Europe
Software Engineer, Machine Learning (Tel Aviv)
@ Meta | Tel Aviv, Israel
Senior Data Scientist- Digital Government
@ Oracle | CASABLANCA, Morocco