Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in

Get started

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

Probability

2,743 missions · 1,549 completed

Missions

Open1194Completed1549All2743
Machine LearningOptimal TransportStatistics·Captain: mikedeng1

Wasserstein Distributionally Robust Optimization and Variation Regularization III: With Probability 1 − e^(−t), E_Pn[(ρ − d(z, D_f))₊] ≤ Cρ² + 2ρ·E[Rademacher] + ρ√(t/2n) for Every fResearch Paper

Wasserstein distributionally robust optimization (DRO) replaces the empirical risk EPn[f]\mathbb E_{P_n}[f]EPn​​[f] of a loss fff by its worst case over all distributions within Wasserstein distance ρ\rhoρ of the empirical law PnP_nPn​. Gao, Chen and Kleywegt (arXiv:1712.06050; Operations Research, 2024, doi:10.1287/opre.2022.2383) show that, for small radii, this worst-case risk…

8 thms2 active usersReviewed
Bandit AlgorithmsOperations ResearchStatistics·Captain: mikedeng1

Data-Based Dynamic Pricing and Inventory Control with Censored Demand and Limited Price Changes 1: In the Well-Separated Case, Algorithm-I with m Price Changes Has Regret at Most KT^(1/(m+1))Research Paper

Retailers set prices and stock levels without knowing how demand responds to price. They must learn the demand curve from their own sales while still earning money, which is the exploration–exploitation trade-off of dynamic pricing with learning (den Boer 2015). Two features of practice make the problem harder than the textbook bandit. First, demand is…

10 thms2 active usersReviewed
Bandit AlgorithmsMachine LearningStatistics·Captain: mikedeng1

The Multi-Armed Bandit Problem with Covariates I: Successive Elimination Has Expected Regret at Most 392γ²(1 + n/T)(K/Δ)log(TΔ²/18γ²) + nΔ⁻ Under a Random HorizonResearch Paper

In a multi-armed bandit, a decision maker repeatedly chooses an arm, observes a reward, and tries to learn which arm has the highest average reward while losing little reward during learning. A policy that requires the number of future pulls in advance cannot be used unchanged when stopping time is uncertain. Perchet and Rigollet study successive elimination…

10 thms2 active usersReviewed
Statistics·Captain: mikedeng1

Central Limit Theorems and Bootstrap in High Dimensions 2: Gaussian Multiplier Bootstrap for Simple Convex Sets with Error C[Δ̄ₙ^{1/3} log^{2/3}(pn) + n⁻¹ log^{1/2}(pn)]Research Paper

Many procedures in high-dimensional statistics reduce to computing the probability that a normalized sum of independent random vectors falls into a set: simultaneous confidence intervals for many means, max-type tests, multiple testing with family-wise error control, and inference after model selection. When the dimension ppp is comparable to or much larger…

10 thms2 active usersReviewed
Statistics·Captain: mikedeng1

Central Limit Theorems and Bootstrap in High Dimensions 1: Gaussian Approximation of Normalized Sums over All Hyperrectangles with Error K₁[(L̄ₙ² log⁷p/n)^{1/6} + Mₙ(φₙ)/L̄ₙ]Research Paper

Many statistical procedures look at a large number of averages at once: simultaneous confidence intervals for ppp means, multiple testing of ppp hypotheses, the maximum of ppp ttt-statistics. Their calibration needs the joint law of a ppp-dimensional normalized sum, and in modern applications ppp is comparable to, or much larger than, the sample size nnn. Classical…

9 thms2 active usersReviewed
Control TheoryMachine LearningOperations Research+1·Captain: mikedeng1

Convergence Analysis of Machine Learning for Mean Field Control, Finite Horizon: The N-Agent Discrete-Time Neural-Net Value Is Within O(N^{-1/max(d,4)} + n_in^{-1/(3(d+1))} + √Δt) of the MKV OptimumResearch Paper

Mean field control studies the optimal control of a very large population of interacting agents through the limit in which the population is replaced by its distribution. The limit problem is a McKean–Vlasov (MKV) control problem: the dynamics and the cost of a representative agent depend on the law of its own state. Such problems arise in systemic risk,…

15 thms2 active usersReviewed
Graph TheoryOperations ResearchStochastic Systems·Captain: mikedeng1

Graphon Mean Field Systems V: On Percolated Graphs Sampled From a Lipschitz Graphon the Mean-Square Error Is at Most κ(q)/(nβₙ)^{1/q}Research Paper

Large systems of interacting diffusions — neurons, oscillators, agents in a network game, particles in a queueing or load-balancing model — are usually analysed through their mean-field limit: as the population grows, each particle interacts with the empirical law of the others, and the system is replaced by a single nonlinear (McKean–Vlasov) equation. The…

15 thms2 active usersReviewed
Analysis·Captain: mikedeng1

Discrete Analogues of Self-Decomposability and Stability 1: A p.g.f. Is Discrete Self-Decomposable iff P(z) = exp{−λ∫_z^1 (1−G(u))/(1−u) du}, iff It Is Infinitely Divisible with Nonincreasing r_nResearch Paper

A probability distribution on the real line is self-decomposable (of class L) if its characteristic function satisfies φ(t)=φ(αt) φα(t)\varphi(t)=\varphi(\alpha t)\,\varphi_\alpha(t)φ(t)=φ(αt)φα​(t) for every α∈(0,1)\alpha\in(0,1)α∈(0,1), with φα\varphi_\alphaφα​ again a characteristic function. Equivalently, a random variable XXX can be written as X=dαX′+XαX\overset{d}{=}\alpha X'+X_\alphaX=dαX′+Xα​ with X′X'X′ a copy of XXX independ…

9 thms2 active usersReviewed
Control TheoryOperations Research·Captain: mikedeng1

Dynamic Pricing with a Prior on Market Response: Decay-Balancing Prices Earn at Least One Third of the Optimal Expected Discounted RevenueResearch Paper

A vendor holding a finite stock of a product must set prices over time without knowing how many customers will come. Each price does two things: it earns revenue now, and through the sales it generates it reveals information about demand that improves future prices. This tension between earning and learning is central in revenue management with demand…

21 thms2 active usersReviewed
Graph TheoryOperations ResearchStochastic Systems·Captain: mikedeng1

Graphon Mean Field Systems III: With Edge Weights Sampled From a Lipschitz Graphon, Each Particle Is Within κ/n of Its Graphon Limit in Mean SquareResearch Paper

Classical mean-field theory describes nnn diffusions that interact symmetrically, each feeling the empirical average of all the others, and shows that as n→∞n\to\inftyn→∞ every particle behaves like an independent copy of a single McKean–Vlasov process. Many systems of interest are not symmetric: neurons, agents in a financial network, or oscillators interact…

10 thms2 active usersReviewed
Dynamic ProgrammingMarkov ChainOperations Research·Captain: mikedeng1

More Risk-Sensitive Markov Decision Processes 2: The Finite-Horizon Discounted Problem Is Solved by Value Iteration on the State Extended by Accumulated Cost and DiscountResearch Paper

Sequential decisions often have costs whose timing matters. A controller may choose an action now, observe a random next state, and choose again. Ordinary expected-cost minimization averages the sum of the costs. A risk-sensitive criterion first applies an increasing function UUU to the total cost and then takes its expectation. The curvature of UUU changes how…

6 thms2 active usersReviewed
Information TheoryRandom Matrix TheoryStatistics·Captain: mikedeng1

Universality in Polytope Phase Transitions and Message Passing Algorithms 2: State Evolution, Empirical Averages of Polynomial AMP Iterates Converge to Gaussian ExpectationsResearch Paper

Approximate message passing (AMP) is an iterative method for large systems with random matrices. At each step, every coordinate receives a weighted combination of nonlinear messages from all other coordinates, together with a correction for dependence created by earlier steps. For symmetric random matrices, the correction makes a simple description of the…

12 thms2 active usersReviewed
Information TheoryRandom Matrix Theory·Captain: mikedeng1

Universality in Polytope Phase Transitions and Message Passing Algorithms 1: Polynomial AMP Iterates Have the Same Asymptotic Moments for All Sub-Gaussian Matrices with Equal Entry VariancesResearch Paper

Approximate message passing (AMP) is a family of iterative algorithms driven by a large random matrix. It was introduced for compressed sensing by Donoho, Maleki and Montanari (PNAS 2009), and it is also used for low-rank matrix estimation, regression and spin-glass optimization. Its main appeal is that, for Gaussian random matrices, the empirical…

9 thms2 active usersReviewed
Markov ChainMathematical Physics·Captain: mikedeng1

The Endpoint Distribution of Directed Polymers 1: In the Low-Temperature Phase the Endpoint Distribution Is Asymptotically Purely Atomic, and at High Temperature It Is NotResearch Paper

A directed polymer in a random environment is a random walk whose paths are weighted by the disorder they encounter. The walk favors paths with large accumulated weight, and its endpoint distribution can concentrate on a small number of sites even though the number of possible paths grows exponentially. Understanding how much probability remains spread…

21 thms2 active usersReviewed
Differential GeometryFunctional Analysis·Captain: mikedeng1

Bakry–Émery Curvature-Dimension Condition and Riemannian Ricci Curvature Bounds 5: A Product of Riemannian Energy Measure Spaces with BE(K,N_X) and BE(K,N_Y) Satisfies BE(K,N_X+N_Y)Research Paper

A lower bound KKK on the Ricci curvature of a Riemannian manifold and an upper bound NNN on its dimension can be expressed without coordinates in two ways. The Bakry–Émery condition BE(K,N)\mathrm{BE}(K,N)BE(K,N) is a property of the heat semigroup and its generator: the iterated carré du champ Γ2\Gamma_2Γ2​ dominates KΓ+1N(Δf)2K\Gamma+\frac1N(\Delta f)^2KΓ+N1​(Δf)2 (Bakry–Émery 1985). The Riemannian…

7 thms2 active usersReviewed
Operations ResearchPartial Differential EquationsStochastic Systems·Captain: mikedeng1

Global C¹ Regularity of the Value Function in Optimal Stopping Problems 1: Probabilistic Regularity of the Boundary Makes the Value Function Continuously DifferentiableResearch Paper

An optimal stopping rule chooses when to end a stochastic process in order to collect a terminal reward, possibly after earning or paying a running reward. The resulting value function often solves a free-boundary problem: the state space splits into a region where stopping is optimal and one where continuing is better. Smoothness inside either region does…

15 thms2 active usersReviewed
Control TheoryOperations ResearchStochastic Systems·Captain: mikedeng1

A Mean Field Game of Optimal Portfolio Liquidation 1: Under Weak Interaction the Liquidation Mean Field Game Has a Unique Equilibrium, Given by a Singular Conditional Mean-Field FBSDEResearch Paper

Large traders who must unwind a position by a deadline face a trade-off between trading fast, which moves prices against them, and trading slowly, which exposes them to price risk. When many traders liquidate at once, each one's execution price also depends on the aggregate selling rate of the others. Fu, Graewe, Horst and Popier (arXiv:1804.04911) model…

15 thms2 active usersReviewed
Algorithmic Game TheoryControl TheoryOperations Research+1·Captain: mikedeng1

A Mean Field Game of Optimal Portfolio Liquidation 3: The Mean-Field Equilibrium Strategies Form an O(1/√N)-Nash Equilibrium of the N-Player Liquidation GameResearch Paper

A trader who must sell a large position within a fixed horizon faces a trade-off: selling fast moves the price against her (temporary price impact), selling slowly exposes her to price risk. Since Almgren and Chriss, this optimal liquidation problem has been studied as a stochastic control problem with a terminal state constraint: the remaining position…

11 thms2 active usersReviewed
Optimal TransportStatistics·Captain: mikedeng1

On the Rate of Convergence in Wasserstein Distance of the Empirical Measure II: Concentration Inequalities for T_p(μ_N, μ) under Exponential or Polynomial Moments (Theorem 2)Research Paper

Approximating an unknown probability measure μ\muμ by the empirical measure μN=1N∑k=1NδXk\mu_N=\frac1N\sum_{k=1}^N\delta_{X_k}μN​=N1​∑k=1N​δXk​​ of an i.i.d. sample is the basic operation of statistics, Monte Carlo integration, quantization and particle approximations of nonlinear PDEs. The natural way to compare μN\mu_NμN​ with μ\muμ on Rd\mathbb R^dRd is an optimal-transport cost, because it…

13 thms2 active usersReviewed
Algorithmic Game TheoryControl Theory·Captain: mikedeng1

A Probabilistic Weak Formulation of Mean Field Games and Applications 2: Under Unique Hamiltonian Maximizers and Lasry–Lions Monotonicity, the Mean Field Game Has at Most One SolutionResearch Paper

Mean field games, introduced independently by Lasry and Lions (Mean field games, Jpn. J. Math. 2007) and by Huang, Malhamé and Caines (2006), describe the Nash equilibria of games with a very large number of symmetric players, each of whom reacts only to the empirical distribution of the others. In the limit, an equilibrium is a fixed point: a flow of…

13 thms2 active usersReviewed
Optimal TransportStatistics·Captain: mikedeng1

On the Rate of Convergence in Wasserstein Distance of the Empirical Measure I: Non-Asymptotic Moment Bounds on E T_p(μ_N, μ) under a q-th Moment Condition (Theorem 1)Research Paper

How fast does the empirical measure of an i.i.d. sample approach the law it is drawn from? When distance is measured by optimal transport, the answer enters the analysis of statistical estimators built from empirical distributions, quantization of probability measures, Monte Carlo and particle approximations of nonlinear PDEs (McKean–Vlasov systems), and…

11 thms2 active usersReviewed
Operations ResearchOptimal TransportOptimization·Captain: mikedeng1

On a Problem of Optimal Transport Under Marginal Martingale Constraints 2: The Shadow of γ1 + γ2 in ν Is the Shadow of γ1 Plus the Shadow of γ2 in What RemainsResearch Paper

The martingale optimal transport problem asks for a coupling of two probability measures μ,ν\mu,\nuμ,ν on R\mathbb RR that is the law of a one-step martingale and minimizes an expected cost. It arises in robust finance, where the marginals are the risk-neutral laws of an asset at two dates implied by option prices, and model-independent price bounds for exotic…

18 thms2 active usersReviewed
Dynamical SystemsMachine LearningOptimization·Captain: mikedeng1

Convergence and Dynamical Behavior of the ADAM Algorithm for Nonconvex Stochastic Optimization 5: Decreasing-Step Adam Converges Almost Surely to the Critical Points of FResearch Paper

Adam (Kingma and Ba, 2015) is the default optimizer for training neural networks: a stochastic gradient method that keeps an exponential moving average mnm_nmn​ of past gradients and an exponential moving average vnv_nvn​ of their coordinatewise squares, and divides the first by the square root of the second. Its practical success came well before any convergence…

16 thms2 active usersReviewed
Operations ResearchOptimal TransportOptimization·Captain: mikedeng1

On a Problem of Optimal Transport Under Marginal Martingale Constraints 5: For c = ϕ(x)ψ(y), ψ Strictly Convex, ϕ Strictly Decreasing, the Left-Curtain Coupling Is the Unique OptimizerResearch Paper

Martingale optimal transport asks for the cheapest way to couple two given laws μ\muμ and ν\nuν on R\mathbb RR by a one-step martingale: a pair (X,Y)(X,Y)(X,Y) with X∼μX\sim\muX∼μ, Y∼νY\sim\nuY∼ν and E[Y∣X]=XE[Y\mid X]=XE[Y∣X]=X. The problem arises in mathematical finance, where μ\muμ and ν\nuν are the risk-neutral laws of an asset at two maturities, implied by quoted vanilla option prices, and the…

11 thms2 active usersReviewed
Algorithmic Game TheoryControl Theory·Captain: mikedeng1

A Probabilistic Weak Formulation of Mean Field Games and Applications 1: When the Hamiltonian's Maximizer Sets Are Convex, the Mean Field Game in Weak Formulation Has a SolutionResearch Paper

Mean field games (MFGs) describe Nash equilibria of stochastic differential games with a very large number of symmetric players, each of whom interacts with the others only through the empirical distribution of their states (and, in this paper, of their controls). They were introduced independently by Lasry and Lions and by Huang, Malhamé and Caines around…

16 thms2 active usersReviewed
PreviousPage 33 of 48Next

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