Get Started
Research questionCan Gaussian-width restricted-eigenvalue guarantees survive heavy-tailed measurements under only a uniform small-ball condition?Restricted eigenvalue bounds support stable recovery, but heavy-tailed measurements can make empirical control depend on simultaneous threshold occupancy rather than geometric width alone. This creates a gap between Gaussian-design behavior and what uniform small-ball assumptions can guarantee.
Research Paper
Statistical Machine Learning
Latest papersRecent research connected to this question, newest first.Restricted Eigenvalues Beyond Gaussian Width: Threshold Occupancy under Heavy TailsThe evidence is theoretical and concerns isotropic heavy-tailed designs, polyhedral descent cones, finite-moment assumptions, and uniform small-ball conditions. It includes explicit counterexamples, threshold-occupancy bounds involving VC dimension, and a distribution-free fallback based on affine dimension and squared enclosing radius.research paper · Sep 3, 2026
Related questions
How many linear samples are needed to approximate Lipschitz operators under Gaussian measures, and how fast can errors decay?Can reducing the complexity of a linear generative prior improve expected reconstruction error in noiseless Gaussian compressed sensing?How can we determine the sample-size threshold for maximum-likelihood existence in colored Gaussian graphical models?How can noisy Lipschitz regression recover an unknown function uniformly on a general metric space?
Home
Topics
Search
Library