| { |
| "schema_version": 1, |
| "title": "Reproduction: Loss-Aware Distributionally Robust Optimization via Trainable Optimal Transport Ambiguity Sets", |
| "emoji": "🧭", |
| "space_id": "squaredcuber/repro-loss-aware-distributionally-robust-optimization-via-trainable-optimal-transport-ambiguity", |
| "paper": { |
| "arxiv_id": "2509.12689" |
| }, |
| "tags": [ |
| "icml2026-repro", |
| "paper-K1EPPO9t2c" |
| ], |
| "updated_at": "2026-07-20T11:17:19+00:00", |
| "root": { |
| "slug": "index", |
| "title": "Reproduction: Loss-Aware Distributionally Robust Optimization via Trainable Optimal Transport Ambiguity Sets", |
| "file": "pages/index.md", |
| "children": [ |
| { |
| "slug": "executive-summary", |
| "title": "Executive summary", |
| "file": "pages/executive-summary/page.md", |
| "children": [] |
| }, |
| { |
| "slug": "claim-1-the-paper-formulates-learning-the-ambiguity-set-for-ot-dro-as-a-bilevel-problem-in-which-the-upper-level-tunes-the-ambiguity-set-geometry-parameter-theta-and-the-lower-level-solves-a-standard-ot-dro-problem-section-4-2", |
| "title": "Claim 1: The paper formulates learning the ambiguity set for OT-DRO as a bilevel problem in which the upper level tunes the ambiguity-set geometry parameter theta and the lower level solves a standard OT-DRO problem (Section 4.2).", |
| "file": "pages/claim-1-the-paper-formulates-learning-the-ambiguity-set-for-ot-dro-as-a-bilevel-problem-in-which-the-upper-level-tunes-the-ambiguity-set-geometry-parameter-theta-and-the-lower-level-solves-a-standard-ot-dro-problem-section-4-2/page.md", |
| "children": [] |
| }, |
| { |
| "slug": "claim-2-theorem-5-1-establishes-that-the-proposed-hypergradient-descent-procedure-converges-to-a-critical-point-of-the-bilevel-problem-under-mild-conditions-including-square-summable-step-sizes-section-5-1-theorem-5-1", |
| "title": "Claim 2: Theorem 5.1 establishes that the proposed hypergradient descent procedure converges to a critical point of the bilevel problem under mild conditions, including square-summable step sizes (Section 5.1, Theorem 5.1).", |
| "file": "pages/claim-2-theorem-5-1-establishes-that-the-proposed-hypergradient-descent-procedure-converges-to-a-critical-point-of-the-bilevel-problem-under-mild-conditions-including-square-summable-step-sizes-section-5-1-theorem-5-1/page.md", |
| "children": [] |
| }, |
| { |
| "slug": "claim-3-algorithm-1-computes-hypergradients-through-the-nonsmooth-conservative-implicit-function-theorem-allowing-differentiation-through-conic-ot-dro-programs-without-assuming-the-solution-map-is-continuously-differentiable-section-5-algorithm-1", |
| "title": "Claim 3: Algorithm 1 computes hypergradients through the nonsmooth conservative implicit function theorem, allowing differentiation through conic (OT-DRO) programs without assuming the solution map is continuously differentiable (Section 5, Algorithm 1).", |
| "file": "pages/claim-3-algorithm-1-computes-hypergradients-through-the-nonsmooth-conservative-implicit-function-theorem-allowing-differentiation-through-conic-ot-dro-programs-without-assuming-the-solution-map-is-continuously-differentiable-section-5-algorithm-1/page.md", |
| "children": [] |
| }, |
| { |
| "slug": "claim-4-in-portfolio-optimization-experiments-with-k-2-j-30-n-b-20-gamma-0-05-beta-0-1-the-relative-improvement-of-the-learned-ambiguity-set-over-a-fixed-wasserstein-ball-increases-as-sample-size-decreases-section-6-1-figure-2", |
| "title": "Claim 4: In portfolio optimization experiments with k=2, J=30, n_b=20, gamma=0.05, beta=0.1, the relative improvement of the learned ambiguity set over a fixed Wasserstein ball increases as sample size decreases (Section 6.1, Figure 2).", |
| "file": "pages/claim-4-in-portfolio-optimization-experiments-with-k-2-j-30-n-b-20-gamma-0-05-beta-0-1-the-relative-improvement-of-the-learned-ambiguity-set-over-a-fixed-wasserstein-ball-increases-as-sample-size-decreases-section-6-1-figure-2/page.md", |
| "children": [] |
| }, |
| { |
| "slug": "claim-5-figure-3-shows-the-learned-ambiguity-set-still-enforces-the-coverage-constraint-containing-the-true-data-generating-distribution-with-the-specified-high-probability-despite-being-shaped-to-reduce-loss-section-6-1-figure-3", |
| "title": "Claim 5: Figure 3 shows the learned ambiguity set still enforces the coverage constraint, containing the true data-generating distribution with the specified high probability despite being shaped to reduce loss (Section 6.1, Figure 3).", |
| "file": "pages/claim-5-figure-3-shows-the-learned-ambiguity-set-still-enforces-the-coverage-constraint-containing-the-true-data-generating-distribution-with-the-specified-high-probability-despite-being-shaped-to-reduce-loss-section-6-1-figure-3/page.md", |
| "children": [] |
| }, |
| { |
| "slug": "claim-6-across-10-independent-linear-regression-trials-the-learned-decision-focused-ambiguity-set-consistently-yields-less-conservative-lower-average-loss-decisions-than-baseline-ot-dro-ambiguity-sets-section-6-2-figure-5", |
| "title": "Claim 6: Across 10 independent linear regression trials, the learned decision-focused ambiguity set consistently yields less conservative (lower average loss) decisions than baseline OT-DRO ambiguity sets (Section 6.2, Figure 5).", |
| "file": "pages/claim-6-across-10-independent-linear-regression-trials-the-learned-decision-focused-ambiguity-set-consistently-yields-less-conservative-lower-average-loss-decisions-than-baseline-ot-dro-ambiguity-sets-section-6-2-figure-5/page.md", |
| "children": [] |
| }, |
| { |
| "slug": "conclusion", |
| "title": "Conclusion", |
| "file": "pages/conclusion/page.md", |
| "children": [] |
| } |
| ] |
| }, |
| "agent_view_tokens": 12155, |
| "revision": "1784546239009186900" |
| } |
|
|
