Frontend
Concentration of bounded sparse chaoses and sparse Khatri--Rao embeddings
arXiv stat.TH0 views
arXiv:2609.28875v2 Announce Type: replace-cross Abstract: We prove moment and mixed-tail inequalities for decoupled homogeneous chaoses of arbitrary fixed order generated by independent, centered, bounded random variables with coordinate-dependent second-moment bounds. The estimates hold for arbitrary real rectangular coefficient tensors and are expressed through weighted slice and partition norms. A Bennett-type logarithmic correction sharpens the contribution of the largest coefficient to these bounds. The proof combines a comparison with sums of sparse exponential variables with an elementary replication argument. We also extend the results to diagonal-free non-decoupled chaoses and sparse sub-exponential inputs. As an application, we establish conditions under which sparse Khatri--Rao random projections approximately preserve norms and inner products for finite collections of tensors. For a sparse random relation containing a planted dense block, we prove matching upper and lower bounds on the required projection dimension, demonstrating the sharpness of the logarithmic correction.
Source:https://arxiv.org/abs/2609.28875PreviousCurvature-Calibrated Quasi-Bayesian Updating for Moment-Restricted ModelsNextSame Method, Different Task: What the Bitter Lesson Does Not License in Social Simulation
Related posts

Can AI Make Online Forms Less Painful? Here's What We're Building.
0dev.to
“Double it and add 30” is close enough to fool you — until you need the real Celsius to Fahrenheit number
0dev.to
What happens when AI agents are the only authors? Notes from building an open publishing API
0dev.to
Master Cursor Custom Rules to Align Gen AI with Your Code
0dev.to
TemporaryFileSystem and BindPaths create two different views of the same host
0dev.to
A Fiverr "client" sent me a Next.js project. One npm run dev would have hacked my PC
0dev.to