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
Machine LearningProbabilityStatistics·Captain: mikedeng1

Minimax Statistical Learning with Wasserstein Distances I: Data-Dependent High-Probability Bound on the Local Worst-Case RiskResearch Paper

Training data describe one probability distribution, while a deployed prediction rule may be evaluated under a nearby distribution. Distributionally robust learning measures a rule by its worst expected loss over a specified set of nearby laws. This changes the question from how well the rule fits the observed sample to how well it performs when probability…

11 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
Operations ResearchProbability·Captain: iris

Convolution Bounds on Quantile Aggregation: The Worst-Case Quantile of a Sum with Given Marginals Is at Most the Convolution Bound, with Equality in Five CasesResearch Paper

A bank or an insurer that holds nnn risks X1,…,XnX_1,\dots,X_nX1​,…,Xn​ usually has good statistical information about each risk separately and very little about how they depend on each other. Regulatory capital is computed from a quantile of the aggregate loss X1+⋯+XnX_1+\dots+X_nX1​+⋯+Xn​ (the Value-at-Risk, VaR), so the question "how large can the quantile of the sum be, over all…

19 thms1 active userReviewed
OptimizationProbability·Captain: mikedeng1

Convergence Rates for Regularized Optimal Transport via Quantization: Entropic and f-Divergence Rates for Costs with Bounded Second Derivative via Martingale Quantization of an Optimal PlanResearch Paper

Optimal transport asks how cheaply several prescribed probability distributions can be coupled. Adding a divergence penalty relative to their independent product makes the problem amenable to numerical methods, but changes its value. A quantitative bound on that change tells users of regularized transport how much bias a chosen regularization parameter can…

7 thms1 active userReviewed
OptimizationProbabilityStatistics·Captain: mikedeng1

Bridging Bayesian and Minimax Mean Square Error Estimation via Wasserstein Distributionally Robust Optimization 1: The Gelbrich Minimax and Normal-Prior Maximin Values Coincide (Sandwich Theorem)Research Paper

Estimating an unknown parameter from a noisy linear measurement is the basic problem behind Kalman filtering, signal recovery and linear inverse problems. A Bayesian statistician picks the estimator that minimizes the mean square error under a prior distribution; a minimax statistician guards against the worst prior in some family. The Bayesian answer…

15 thms1 active userReviewed
Partial Differential EquationsProbability·Captain: mikedeng1

Viscosity Solutions to Parabolic Master Equations and McKean–Vlasov SDEs with Closed-Loop Controls 1: A Functional Itô Formula for Path-Dependent Functionals of Semimartingale LawsResearch Paper

Master equations are partial differential equations whose state variable is a probability measure. They arise as the Hamilton–Jacobi–Bellman equations of mean field control problems, where a planner steers a large population through its distribution, and as the limit description of large games. Their basic computational tool is an Itô formula for functions…

14 thms1 active userReviewed
Differential GeometryFunctional AnalysisProbability·Captain: mikedeng1

Bakry–Émery Curvature-Dimension Condition and Riemannian Ricci Curvature Bounds 4: A Riemannian Energy Measure Space Satisfying BE(K,∞) Is an RCD(K,∞) SpaceResearch Paper

Heat flow gives an analytic way to describe how functions spread on a space. Optimal transport gives a metric way to describe how probability measures move on the same space. On a smooth Riemannian manifold, a lower Ricci curvature bound constrains both motions. The problem addressed by Ambrosio, Gigli and Savaré is to identify the corresponding…

7 thms1 active userReviewed
Functional AnalysisProbability·Captain: mikedeng1

Bakry–Émery Curvature-Dimension Condition and Riemannian Ricci Curvature Bounds 3: Lipschitz and Pointwise Gradient Bounds on the Heat Semigroup Make Its Dual Semigroup a W₂ ContractionResearch Paper

A lower bound on Ricci curvature can be expressed in two ways that make sense far beyond smooth manifolds. The Eulerian way bounds the gradient of the heat semigroup: Bakry and Émery's Γ2\Gamma_2Γ2​-calculus gives ∣∇Ptf∣2≤e−2Kt Pt∣∇f∣2|\nabla \mathsf P_t f|^2 \le e^{-2Kt}\,\mathsf P_t|\nabla f|^2∣∇Pt​f∣2≤e−2KtPt​∣∇f∣2. The Lagrangian way bounds how heat flow moves probability measures in optimal…

9 thms1 active userReviewed
Differential GeometryFunctional AnalysisProbability·Captain: mikedeng1

Bakry–Émery Curvature-Dimension Condition and Riemannian Ricci Curvature Bounds 6: BE(K,N) on Riemannian Energy Measure Spaces Is Stable Under Sturm–Gromov–Hausdorff ConvergenceResearch Paper

Curvature bounds on a smooth Riemannian manifold control diffusion and the behavior of probability measures. Metric measure spaces extend these questions to limits that need not be smooth. A useful curvature condition must continue to hold when a sequence of spaces converges. Ambrosio, Gigli, and Savaré prove that their analytic Bakry–Émery…

7 thms1 active userReviewed
Control TheoryPartial Differential EquationsProbability·Captain: mikedeng1

Mean Field Games Master Equations with Nonseparable Hamiltonians and Displacement Monotonicity: Under Displacement Monotone H and G, the Master Equation Has a Unique Global Classical SolutionResearch Paper

Mean field games (Lasry–Lions 2006–2007; Huang–Malhamé–Caines 2006) describe Nash equilibria of games with a very large number of symmetric players, each interacting with the others only through the empirical distribution of their states. When all players are also exposed to a common noise, the equilibrium is no longer described by a forward–backward pair…

11 thms1 active userReviewed
Algorithmic Game TheoryProbabilityStochastic Systems·Captain: mikedeng1

From the Master Equation to Mean Field Game Limit Theory: Large Deviations and Concentration of Measure 1: Without Common Noise, n-Player Nash Equilibria Concentrate Dimension-FreeResearch Paper

A large stochastic game has one state process per player. Each player's feedback changes with the empirical distribution of all states, so a finite population remains coupled even when the idiosyncratic Brownian motions are independent. A useful quantitative question is whether a statistic of the entire collection of equilibrium trajectories can deviate…

12 thms1 active userReviewed
Operations ResearchOptimizationProbability·Captain: mikedeng1

Optimal Transport-Based Distributionally Robust Optimization: Structural Properties and Iterative Schemes 5: Worst-Case Displacements √δ G_δ Grow Monotonically in δ Along Straight LinesResearch Paper

A distributionally robust decision evaluates a rule against every data distribution within a specified transport budget of a baseline law. The budget is a modeling choice: increasing it expresses more uncertainty about the data. A robust objective value can increase with that budget, but the value alone does not describe how the adverse distribution…

16 thms1 active userReviewed
Machine LearningProbabilityStatistics·Captain: mikedeng1

Minimax Statistical Learning with Wasserstein Distances III: Excess Local Minimax Risk of Wasserstein ERM When One Hypothesis Is SmoothResearch Paper

In ordinary statistical learning, a hypothesis is chosen from training data drawn from a distribution PPP and judged by its risk under that same PPP. In practice the test distribution often differs from the training one: covariate shift, domain drift, adversarial perturbation of inputs. Distributionally robust learning replaces the risk at PPP by the worst risk…

13 thms1 active userReviewed
Machine LearningProbabilityStatistics·Captain: mikedeng1

Minimax Statistical Learning with Wasserstein Distances II: Excess Local Minimax Risk of Wasserstein ERM for a Uniformly Lipschitz ClassResearch Paper

In statistical learning a hypothesis fff is chosen from a class F\mathcal FF using nnn samples drawn from an unknown distribution PPP, and its quality is measured by the risk R(P,f)=EP[f(Z)]R(P,f) = \mathbf E_P[f(Z)]R(P,f)=EP​[f(Z)]. When the distribution at deployment time may differ from the one that generated the data (domain drift, adversarial perturbation, model misspecification), a natural…

12 thms1 active userReviewed
PreviousPage 4 of 4Next

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