Backend
Distributionally Robust Risk Evaluation with Low-Rank Perturbations
arXiv stat.ML0 views
arXiv:2611.17447v1 Announce Type: cross Abstract: We study distributionally robust risk under perturbations restricted to low-rank matrices whose row and column spaces are shared across observations, focusing on how much worst-case risk this restriction sacrifices and how to compute the restricted worst case. Under moment or Wasserstein budgets, we derive quantitative bounds on the gap between the unrestricted and low-rank worst-case risks, characterize when the gap vanishes, and identify the smallest lossless row and column dimensions. To generate worst-case perturbations, we apply projected gradient ascent to a curvature-corrected concave problem and derive computable risk certificates. We establish global sublinear convergence for the corrected objective and linear convergence to a worst-case distribution when the budget constraint is sufficiently active.
Source:https://arxiv.org/abs/2611.17447PreviousElliptic Sampling: Optimal Interpolant Schedules for Gaussians and BeyondNextSURFACE: Preference Distribution Matching on Pareto Fronts via Scalarization Steering
Related posts

How to Build a Custom Business Dashboard (2026 Guide)
0dev.to WebDev

Most People Are Using AI Wrong. Here’s How to Turn It Into a Personal Assistant
0dev.to WebDev
How to screenshot or PDF any website by API, without running your own browser
0dev.to WebDev
Top Trends in Hotel Billing Software for 2027: What’s New
0dev.to WebDev
A PNG Wearing a .webp Filename Cost My Services Page 441 KiB
0dev.to WebDev
How I keep bots out of my own analytics, with no cookies and no third-party scripts
0dev.to WebDev