all AI news
On the inability of Gaussian process regression to optimally learn compositional functions. (arXiv:2205.07764v2 [stat.ML] UPDATED)
Sept. 28, 2022, 1:13 a.m. | Matteo Giordano, Kolyan Ray, Johannes Schmidt-Hieber
stat.ML updates on arXiv.org arxiv.org
We rigorously prove that deep Gaussian process priors can outperform Gaussian
process priors if the target function has a compositional structure. To this
end, we study information-theoretic lower bounds for posterior contraction
rates for Gaussian process regression in a continuous regression model. We show
that if the true function is a generalized additive function, then the
posterior based on any mean-zero Gaussian process can only recover the truth at
a rate that is strictly slower than the minimax rate by …
More from arxiv.org / stat.ML updates on arXiv.org
Jobs in AI, ML, Big Data
Senior Machine Learning Engineer (MLOps)
@ Promaton | Remote, Europe
Data Analyst (CPS-GfK)
@ GfK | Bucharest
Consultant Data Analytics IT Digital Impulse - H/F
@ Talan | Paris, France
Data Analyst
@ Experian | Mumbai, India
Data Scientist
@ Novo Nordisk | Princeton, NJ, US
Data Architect IV
@ Millennium Corporation | United States