all AI news
Tensor cumulants for statistical inference on invariant distributions
April 30, 2024, 4:46 a.m. | Dmitriy Kunisky, Cristopher Moore, Alexander S. Wein
stat.ML updates on arXiv.org arxiv.org
Abstract: Many problems in high-dimensional statistics appear to have a statistical-computational gap: a range of values of the signal-to-noise ratio where inference is information-theoretically possible, but (conjecturally) computationally intractable. A canonical such problem is Tensor PCA, where we observe a tensor $Y$ consisting of a rank-one signal plus Gaussian noise. Multiple lines of work suggest that Tensor PCA becomes computationally hard at a critical value of the signal's magnitude. In particular, below this transition, no low-degree …
abstract arxiv canonical computational cs.cc cs.ds gap inference information math.pr math.st noise observe pca signal statistical statistics stat.ml stat.th tensor type values
More from arxiv.org / stat.ML updates on arXiv.org
Uniform Inference for Subsampled Moment Regression
1 day, 15 hours ago |
arxiv.org
Partial information decomposition as information bottleneck
1 day, 15 hours ago |
arxiv.org
Jobs in AI, ML, Big Data
Data Engineer
@ Lemon.io | Remote: Europe, LATAM, Canada, UK, Asia, Oceania
Artificial Intelligence – Bioinformatic Expert
@ University of Texas Medical Branch | Galveston, TX
Lead Developer (AI)
@ Cere Network | San Francisco, US
Research Engineer
@ Allora Labs | Remote
Ecosystem Manager
@ Allora Labs | Remote
Founding AI Engineer, Agents
@ Occam AI | New York