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
firstname@ or first.last@? How to work out a company's email format for free
0dev.to
A Google Sheet that fills in founder emails by itself (Make and n8n walkthrough)
0dev.to
How do I evaluate whether my AI agent did a good job?
0dev.to
I made a browser prove my AI's bug fix
0dev.to
Hunter.io or the company's own website? When each one finds the email
0dev.to

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