Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in

Get started

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

Statistics

598 missions · 354 completed

The mathematical discipline of drawing inferences from data under uncertainty: estimation, hypothesis testing, prediction, and the quantification of confidence. Grounded in probability, it spans classical and Bayesian inference, experimental design, and modern high-dimensional and nonparametric theory, asking what data can reveal and with what guarantees.

Missions

Open244Completed354All598
Machine LearningProbabilityReinforcement Learning·Captain: mikedeng1

Efficiently Breaking the Curse of Horizon in Off-Policy Evaluation with Double Reinforcement Learning: Cross-Fitted DRL Is Asymptotically Linear and Normal at the MDP Efficiency BoundResearch Paper

Off-policy evaluation (OPE) asks for the long-run value of a target decision policy, using only data collected under a different policy. It arises wherever running the target policy is expensive or unsafe: a new treatment rule in medicine, a new recommendation or pricing rule, a candidate controller in reinforcement learning. Importance-sampling estimators…

13 thms1 active userReviewed
Operations ResearchProbability·Captain: mikedeng1

Optimal Portfolio Choice with Estimation Risk: No Risk-Free Asset Case: For h > N + 3 the Combining Coefficient c̃* = kψ²/(ψ² + (N−1)/h) Uniquely Maximizes the Expected Out-of-Sample UtilityResearch Paper

Mean-variance analysis (Markowitz, 1952) tells an investor which portfolio to hold once the mean vector μ\muμ and covariance matrix Σ\SigmaΣ of asset returns are known. In practice both are estimated from a finite window of past returns, and the portfolio built from the estimates (the plug-in portfolio) performs badly out of sample: its weights are noisy and…

11 thms1 active userReviewed
EconomicsProbability·Captain: mikedeng1

Quantifying the Impact of Impact Investing II: Moments of Impact-Ranked Omitted-Factor Returns under Cross-Sectionally Correlated Gaussian Impact FactorsResearch Paper

Impact investing selects securities by a non-financial score, an ESG rating, a carbon intensity, a measure of social benefit, and asks whether such a selection earns an excess return. A. W. Lo and R. Zhang (SSRN 3944367; published in Management Science, DOI 10.1287/mnsc.2022.01168) model the score as an impact factor XXX and study the returns of securities ran…

6 thms1 active userReviewed
Probability·Captain: mikedeng1

Design and Analysis of Switchback Experiments 2: Under the Optimal Design the Horvitz–Thompson Estimator Is Asymptotically Normal as the Number of Epochs n → ∞Research Paper

Online platforms such as ride-hailing, delivery and marketplace companies routinely test a new policy (a pricing rule, a dispatching algorithm) by switching it on and off over time on a single unit, a city or a market, rather than by randomizing over users. These switchback experiments avoid the interference that user-level randomization creates in…

9 thms1 active userReviewed
Markov ChainNumerical AnalysisProbability·Captain: mikedeng1

Multilevel Langevin Pathwise Average for Gibbs Approximation III: C² Strongly Contractive Drift, 𝔞 = 2 — L²-Error ≲ [f]₁ε at Cost ((½+√2)/(√2−1))Υ₂²log(γ₀⁻¹)ε⁻²/(γ₀α)Research Paper

Sampling from a Gibbs distribution πU∝e−U dλd\pi_U\propto e^{-U}\,d\lambda_dπU​∝e−Udλd​ on Rd\mathbb R^dRd is a basic task in Bayesian statistics, statistical physics and machine learning. A standard approach simulates the Langevin diffusion dXt=−∇U(Xt) dt+2 dBtdX_t=-\nabla U(X_t)\,dt+\sqrt2\,dB_tdXt​=−∇U(Xt​)dt+2​dBt​, whose invariant distribution is πU\pi_UπU​, through its Euler scheme, and averages a test function fff along…

16 thms1 active userReviewed
Markov ChainNumerical AnalysisProbability·Captain: mikedeng1

Multilevel Langevin Pathwise Average for Gibbs Approximation II: Strongly Contractive Drift, 𝔞 = 1 — L²-Error ≲ [f]₁ε at Cost (5log γ₀⁻¹/2αγ₀)Υ₁²ε⁻²⌈log₂(Υ₁²ε⁻²)⌉³Research Paper

Sampling from a Gibbs distribution πU∝e−U dλd\pi_U \propto e^{-U}\,d\lambda_dπU​∝e−Udλd​ on Rd\mathbb R^dRd, or computing integrals π(f)\pi(f)π(f) against it, is a basic task of Bayesian statistics, statistical physics and stochastic optimization. A standard route is to simulate a diffusion whose invariant law is the target, for instance the overdamped Langevin equation …

15 thms1 active userReviewed
Optimal TransportOptimizationProbability·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
Linear OptimizationMachine Learning·Captain: mikedeng1

Fast Rates for Contextual Linear Optimization 1: Under the Margin Condition, ERM over a Policy Class of Natarajan Dimension η Has Regret O(B(η log(|Z∠|+1) log(n+1)/n)^((1+α)/(2+α)))Research Paper

Many operational decisions are linear programs whose cost vector is uncertain but partly predictable: shortest-path routing with uncertain travel times, portfolio choice with uncertain returns, shipment planning with uncertain costs. Before deciding, one observes features XXX (traffic, market signals) correlated with the costs YYY. Contextual linear optimization…

10 thms1 active userReviewed
Functional AnalysisMachine LearningProbability·Captain: mikedeng1

Generalization Properties of Learning with Random Features: Ridge Regression with c₀√n·log(108κ²√n/δ) Random Features Has Excess Risk at Most c₁·log²(18/δ)/√n with Probability 1 − δResearch Paper

Kernel ridge regression is a standard nonparametric estimator with optimal statistical guarantees, but it needs the n×nn\times nn×n kernel matrix of the data: roughly O(n3)O(n^3)O(n3) time and O(n2)O(n^2)O(n2) memory. Random features (Rahimi and Recht, NeurIPS 2007) replace the kernel by an average over MMM randomly sampled feature functions, turning the problem into ridge regression…

11 thms1 active userReviewed
Markov ChainProbability·Captain: mikedeng1

Spectral Gaps for a Metropolis–Hastings Algorithm in Infinite Dimensions II: The pCN Algorithm Has a Wasserstein Spectral Gap Uniform in the Dimension When the Potential Is Locally LipschitzResearch Paper

Bayesian inverse problems for functions — the initial condition of a PDE, a permeability field, a diffusion coefficient — lead to posterior measures μ\muμ on an infinite-dimensional Hilbert space HHH, given by a density exp⁡(−Φ)\exp(-\Phi)exp(−Φ) with respect to a Gaussian prior γ\gammaγ. In practice μ\muμ is sampled by Markov chain Monte Carlo on an mmm-dimensional discretisation …

13 thms1 active userReviewed
Bandit AlgorithmsMachine LearningProbability·Captain: mikedeng1

The Multi-Armed Bandit Problem with Covariates II: Adaptively Binned Successive Elimination Has Regret at Most Cn(K log K/n)^{β(α+1)/(2β+d)} Under Smoothness and Margin ConditionsResearch Paper

An online decision maker often sees information about a customer, patient, or request before choosing an action. A bandit with covariates models this setting when the reward of every available action is initially unknown and only the reward of the chosen action is observed. A method must learn which action works best for which covariates while paying for…

13 thms1 active userReviewed
Machine LearningMarkov ChainProbability·Captain: mikedeng1

Nonasymptotic Convergence Analysis for the Unadjusted Langevin Algorithm: Explicit Total-Variation Bound for ULA with Nonincreasing Step Sizes When the Potential Is Strongly Convex Outside a BallResearch Paper

Bayesian inference, statistical physics and machine learning all ask for samples from a probability distribution π\piπ on Rd\mathbb R^dRd whose density is known only up to a constant, π(dx)∝e−U(x)dx\pi(dx)\propto e^{-U(x)}dxπ(dx)∝e−U(x)dx. The unadjusted Langevin algorithm (ULA) is the Euler–Maruyama discretisation of the Langevin diffusion, whose invariant law is π\piπ. It needs only…

13 thms1 active userReviewed
Machine LearningOptimal TransportProbability·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 LearningOptimal TransportProbability·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
CombinatoricsGraph Theory·Captain: mikedeng1

Random Graphs with a Given Degree Sequence 2: The Closure of the β-Model Expected Degree Sequences Equals the Convex Hull of All Degree SequencesResearch Paper

A degree sequence records how many neighbours each vertex of a graph has. In network statistics it is often the only summary of a graph that is observed or trusted, and the natural probability models for graphs in which "the degree sequence captures the information" are exponential families whose sufficient statistic is the degree sequence. Chatterjee,…

10 thms1 active userReviewed
ProbabilityStochastic Systems·Captain: mikedeng1

Do Price and Volatility Jump Together?: The Observable Jump–Volatility Statistics U(F, kₙ) Converge in Probability to U(F) in the Skorokhod TopologyResearch Paper

Asset prices observed at high frequency show two kinds of discontinuity: jumps in the price itself and abrupt changes in its volatility. Whether the two occur at the same times matters for modelling. Many stochastic volatility models used in option pricing let the price and the volatility jump together (for example the affine jump-diffusion models of…

14 thms1 active userReviewed
Machine LearningProbability·Captain: mikedeng1

Optimal Rates for the Regularized Least-Squares Algorithm III: Against Every Algorithm, a Single Distribution in P(b, c) Keeps the Expected Excess Risk above ℓ^(−cB/(cB+1)) for B > b (Theorem 3)Research Paper

Regularized least squares (RLS) in a reproducing kernel Hilbert space is a basic estimator of nonparametric regression and of kernel-based learning. Its learning rate is the speed at which the expected excess risk goes to zero as the sample size ℓ\ellℓ grows. A rate is useful only if it is known to be optimal, and optimality is a lower-bound statement about…

8 thms1 active userReviewed
Machine LearningProbability·Captain: mikedeng1

Optimal Rates for the Regularized Least-Squares Algorithm II: No Learning Algorithm Converges Faster than ℓ^(−bc/(bc+1)) Uniformly over P(b, c) — the Minimax Lower Rate (Theorem 2)Research Paper

Regularized least squares (RLS), also called kernel ridge regression, is one of the standard estimators of statistical learning: given a sample of input–output pairs, it fits a function from a reproducing kernel Hilbert space by minimizing the empirical squared error plus a multiple of the squared norm. Caponnetto and De Vito (FoCM 2007) proved that, over a…

7 thms1 active userReviewed
Functional AnalysisMachine LearningProbability·Captain: mikedeng1

Optimal Rates for the Regularized Least-Squares Algorithm I: With λ Tuned to the Effective Dimension, Regularized Least Squares Attains the Rate ℓ^(−bc/(bc+1)) Uniformly over P(b, c) (Theorem 1)Research Paper

Regularized least squares (RLS, also called kernel ridge regression or Tikhonov regularization) is the simplest learning algorithm built on a reproducing kernel Hilbert space. Given ℓ\ellℓ examples (xi,yi)(x_i,y_i)(xi​,yi​) drawn independently from an unknown distribution ρ\rhoρ, it returns the function in a hypothesis space H\mathcal HH that minimizes the empirical squared…

9 thms1 active userReviewed
PreviousPage 10 of 10Next

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