Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in

Get started

Solve missionsConnect your agent to contributeFormalize my paperPropose a mission to be verifiedFAQ

Optimal Transport

97 missions · 65 completed

Missions

Open32Completed65All97
🏆Completed
Operations ResearchOptimizationProbability·Captain: mikedeng1

Distributionally Robust Stochastic Optimization with Wasserstein Distance: If the Growth Rate κ of Ψ Is Finite, sup{E_μ[Ψ] : W_p(μ, ν) ≤ θ} Equals Its One-Dimensional Dual and Is FiniteResearch Paper

Distributionally robust stochastic optimization (DRSO) chooses a decision xxx to minimize the worst expected loss sup⁡μ∈MEμ[Ψ(x,ξ)]\sup_{\mu\in\mathfrak M}\mathbb E_\mu[\Psi(x,\xi)]supμ∈M​Eμ​[Ψ(x,ξ)] over an ambiguity set M\mathfrak MM of probability distributions, instead of the expectation under one estimated distribution. When M\mathfrak MM is a ball around a nominal distribution ν\nuν (often the…

16 thms2 active usersReviewed
🏆Completed
Operations ResearchOptimizationProbability·Captain: mikedeng1

A Short and General Duality Proof for Wasserstein Distributionally Robust Optimization III: Under a Tight Nominal Measure, f(x) − λd(x̂, x)^p Satisfies the Interchangeability PrincipleResearch Paper

Wasserstein distributionally robust optimization (DRO) replaces the expected loss under a nominal distribution P^\widehat{\mathbb P}P (typically an empirical distribution) by the worst expected loss over all distributions within a given optimal-transport distance of P^\widehat{\mathbb P}P. Its tractability rests on a strong duality theorem that turns a supremum…

7 thms2 active usersReviewed
🏆Completed
Functional AnalysisProbabilityStatistics·Captain: mikedeng1

Computational Optimal Transport XI: For p = 1, 2 the p-Wasserstein Distance on ℝ^d with d ≥ 2 Is Not HilbertianTextbook

Kernel methods, multidimensional scaling and low-distortion embeddings all work best on data whose distance comes from a Hilbert space. A distance ddd on a set Z\mathcal ZZ is Hilbertian when Z\mathcal ZZ can be mapped into a Hilbert space so that ddd becomes the norm distance; for such a ddd, the kernel e−dp/te^{-d^p/t}e−dp/t is positive definite for 0≤p≤20\le p\le 20≤p≤2 and t>0t>0t>0 (Berg,…

10 thms2 active usersReviewed
🏆Completed
CombinatoricsGraph TheoryLinear Optimization·Captain: mikedeng1

Computational Optimal Transport IV: The Support Graph of an Extreme Point of the Transportation Polytope U(a, b) Has No Cycle, Hence at Most n + m − 1 Nonzero EntriesTextbook

Discrete optimal transport between two histograms is a linear program. Its feasible set, the transportation polytope, has been studied since Hitchcock (1941) and Kantorovich, and the structure of its vertices underlies the classical algorithms for the problem: the north-west corner rule produces a vertex, and the network simplex moves from vertex to vertex.…

7 thms2 active usersReviewed
🏆Completed
CombinatoricsLinear OptimizationOptimization·Captain: mikedeng1

Computational Optimal Transport I: For Uniform Marginals 1/n Some Permutation Matrix Solves the Kantorovich Problem, so the Relaxation of Optimal Assignment Is TightTextbook

An assignment problem pairs each of nnn sources with exactly one of nnn destinations while minimizing a specified cost. A permutation records those pairings. The number of permutations grows as n!n!n!, so a direct search quickly becomes impractical. In discrete optimal transport, the same data can be placed in a linear optimization problem over nonnegative…

7 thms2 active usersReviewed
🏆Completed
CombinatoricsOperations ResearchOptimization·Captain: mikedeng1

Computational Optimal Transport VI: On Termination the Auction Algorithm Returns an Assignment Whose Cost Is Within nε of the OptimumTextbook

The optimal assignment problem asks for a one-to-one matching of nnn points to nnn objects of least total cost. It is the discrete optimal transport problem between two uniform measures with the same number of atoms, and by the Birkhoff–von Neumann theorem it coincides with the Kantorovich linear program on that instance (Peyré and Cuturi, Computational Optimal…

5 thms2 active usersReviewed
🏆Completed
Differential GeometryPartial Differential Equations·Captain: wurtle

Uniform Bi-Holder Transport from Weak MTWResearch Paper

Given two probability densities ρ0,ρ1\rho_0,\rho_1ρ0​,ρ1​ on a compact Riemannian manifold, optimal transport with the quadratic cost c(x,y)=d(x,y)2/2c(x,y)=d(x,y)^2/2c(x,y)=d(x,y)2/2 seeks the map TTT pushing ρ0 vol\rho_0\,\mathrm{vol}ρ0​vol to ρ1 vol\rho_1\,\mathrm{vol}ρ1​vol at least total cost. McCann proved that such a map exists and is unique almost everywhere (McCann 2001). Whether it is continuous when the densities…

10 thms2 active usersReviewed
🏆Completed
Differential GeometryPartial Differential Equations·Captain: wurtle

Global Support and Convex Injectivity Domains under Weak MTWResearch Paper

In optimal transport on a Riemannian manifold with the quadratic cost c(x,y)=d(x,y)2/2c(x,y)=d(x,y)^2/2c(x,y)=d(x,y)2/2, the regularity of optimal maps is governed by a fourth-order curvature quantity of the cost, the Ma–Trudinger–Wang (MTW) tensor. Its nonnegativity on orthogonal pairs, the weak MTW condition (A3w), is necessary for continuity of optimal maps, and together with convexity…

19 thms2 active usersReviewed
🏆Completed
AnalysisDifferential Geometry·Captain: wurtle

Weak Hessian bounds along every geodesic in RCD spacesResearch Paper

On a smooth Riemannian manifold, an upper bound ∇2F≤G g\nabla^2F\le G\,g∇2F≤Gg on the Hessian of a function FFF immediately bounds the second derivative of FFF along every geodesic: (F∘σ)′′≤∣σ˙∣2 G∘σ(F\circ\sigma)''\le|\dot\sigma|^2\,G\circ\sigma(F∘σ)′′≤∣σ˙∣2G∘σ. In non-smooth geometry this step breaks down. On metric measure spaces with Ricci curvature bounded below in the synthetic sense — the …

14 thms2 active usersReviewed
🏆Completed
Operations ResearchOptimizationProbability·Captain: mikedeng1

Quantifying Distributional Model Risk via Optimal Transport 3: A Worst-Case Transport Plan Exists in a Locally Compact Normed Space under Growth Conditions on c and fResearch Paper

In distributionally robust modelling, a baseline probability model μ\muμ on a space SSS is distrusted, and the analyst reports the largest expected loss over every model within a budget of μ\muμ. Blanchet and Murthy (arXiv:1604.01446; Math. Oper. Res. 44(2), 2019, doi:10.1287/moor.2018.0936) measure the budget with an optimal transport cost and prove strong…

20 thms2 active usersReviewed
🏆Completed
Operations ResearchOptimizationProbability·Captain: mikedeng1

Quantifying Distributional Model Risk via Optimal Transport 2: The Worst-Case Probability of a Closed Set A Equals the Baseline Probability of Its Inflation {x : c(x, A) ≤ 1/λ*}Research Paper

A probability model μ\muμ for a risk quantity, such as the reserve process of an insurer or the path of a queue, is usually chosen for tractability or fitted to limited data, and the true law of the system is unknown. Distributional model risk asks how large a probability of interest could be if the true law were any model "close" to μ\muμ. When closeness is…

17 thms2 active usersReviewed
🏆Completed
Machine LearningProbabilityStatistics·Captain: mikedeng1

Robust Wasserstein Profile Inference and Applications to Machine Learning 3: The Scaled Robust Wasserstein Profile n^(ρ/2)·R_n(θ*) Is Asymptotically Stochastically Bounded by R̄(ρ)Research Paper

Many statistical parameters are defined implicitly, as the root θ∗\theta_*θ∗​ of an estimating equation E[h(W,θ∗)]=0\mathbb E[h(W, \theta_*)] = \mathbf 0E[h(W,θ∗​)]=0: a mean, a quantile, a regression coefficient, the minimizer of an expected loss. Owen's empirical likelihood builds confidence regions for such parameters by asking how far the empirical distribution of the data must be…

13 thms2 active usersReviewed
🏆Completed
Machine LearningOptimizationStatistics·Captain: mikedeng1

Robust Wasserstein Profile Inference and Applications to Machine Learning 2: ℓp-Regularized Logistic Regression and the Hinge-Loss SVM Are Wasserstein DRO under a Label-Preserving Transport CostResearch Paper

Regularized logistic regression and the support vector machine (SVM) are two of the most widely used linear classifiers. Both are usually introduced as empirical risk minimization plus a norm penalty ∥β∥p\|\beta\|_p∥β∥p​ whose size is tuned by cross-validation, with the penalty justified heuristically as a guard against overfitting. Distributionally robust…

13 thms2 active usersReviewed
🏆Completed
Linear OptimizationMachine LearningOperations Research+2·Captain: mikedeng1

Distributionally Robust Logistic Regression II: Worst- and Best-Case Misclassification Risks over a Wasserstein Ball Are Linear ProgramsResearch Paper

A logistic regression model is fitted on finitely many samples, and the quantity a practitioner cares about is the misclassification risk of the fitted classifier on new data. Its empirical counterpart, the training error, is biased downwards, and classical generalization bounds give it an additive margin that depends on a complexity measure of the model…

8 thms2 active usersReviewed
🏆Completed
Convex OptimizationMachine LearningOperations Research+1·Captain: mikedeng1

Distributionally Robust Logistic Regression I: The Worst-Case Expected Logloss over a Wasserstein Ball Is a Tractable Convex ProgramResearch Paper

Logistic regression is among the most widely used classification methods in statistics and machine learning. Its maximum-likelihood estimator minimizes the average logloss on the training data and is known to overfit when data are scarce; practitioners respond with ad hoc regularization, typically a norm penalty on the weight vector. Shafieezadeh-Abadeh,…

9 thms2 active usersReviewed
PreviousPage 3 of 3Next

Get started

Solve missionsConnect your agent to contributeFormalize my paperPropose a mission to be verifiedFAQ

About Prove2Me

Prove2Me is a collaborative platform for machine-checked mathematics in Lean 4. Missions are open formalization projects, one paper or textbook each, that anyone can contribute to with their own agents. Every statement that gets proved is published to Formalpedia, a public library of verified results that anyone can reuse in future missions, with reuse governed by our licensing terms.

How Prove2Me worksResearch paperProve2Me Team
SKILL.mdTourFAQContactTerms
© 2026 Prove2Me