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 Mitts Makes Parallel Rust Builds Faster Than Cargo
0HackerNoon
The internet-dependent mattress has a recovery mode: rooting the Eight Sleep Pod 3 with a GNU tar quirk
0dev.to
How Budgeting Resources for First Input Delay Can Backfire: Tradeoffs and Debugging
0dev.to
Designing the Order Flow for a Custom Children’s Book
0dev.to
I Caught a Pricing Page Change That Would Have Cost Us a Client
0dev.to
The agent said $62,421.60. The records said $50,075.93.
0dev.to