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
🏆Completed
Machine LearningOperations ResearchOptimization·Captain: Shuze Chen

Matrix Completion has No Spurious Local MinimumResearch Paper

Matrix completion — recovering a low-rank matrix M=ZZ⊤M = ZZ^\topM=ZZ⊤ from a small random subset of its entries — powers recommender systems and collaborative filtering. In practice it is solved by running (stochastic) gradient descent on the non-convex objective

14 thms4 active users
🏆Completed
Linear algebraOperations ResearchProbability·Captain: mikedeng1

Low-Rank Denoising for Predict-then-OptimizeResearch Paper

A predict-then-optimize pipeline estimates unknown costs and passes the estimate to an optimizer. In shortest-path problems, edge costs can come from noisy measurements or simulation replications. Averaging more replications reduces noise, but costs across different instances may also share structure: several edges can vary together. A projection estimator k…

6 thms3 active usersReviewed
🏆Completed
Machine LearningProbability·Captain: mikedeng1

Is Randomness Necessary for Adaptive Data Analysis?Research Paper

A dataset is often reused to answer questions chosen after seeing earlier answers. Each answer can influence the next question, so the usual guarantee for one question fixed in advance does not automatically extend to the resulting interaction. Adaptive data analysis asks what a mechanism can reliably reveal about a population from a single finite sample in…

14 thms3 active usersReviewed
🏆Completed
Machine Learning·Captain: iris

Omniprediction for All Mixable Proper Losses and BeyondResearch Paper

A forecaster that outputs probabilities is usually trained against one loss function, yet its forecasts are often consumed by several downstream decision makers, each with its own loss, some of them unknown at training time. Omniprediction, introduced in the batch setting by Gopalan, Kalai, Reingold, Sharan and Wieder (arXiv:2109.05389) and in the online…

49 thms3 active usersReviewed
🏆Completed
Operations ResearchOptimizationProbability·Captain: iris

Learning-based Robust Optimization: Procedures and Statistical Guarantees: with n₂ ≥ log δ/log(1 − ϵ), the data-split order-statistic set covers 1 − ϵ of P with confidence 1 − δResearch Paper

A chance-constrained program (CCP) asks for a decision xxx minimizing a cost f(x)f(x)f(x) subject to P(g(x;ξ)∈A)≥1−ϵP(g(x;\xi)\in A)\ge 1-\epsilonP(g(x;ξ)∈A)≥1−ϵ, where ξ\xiξ is a random parameter with law PPP and ϵ\epsilonϵ is a tolerance level. Chance constraints model reliability requirements in operations, finance and engineering, but they are hard to solve: the feasible set is usually nonconvex,…

10 thms3 active usersReviewed
🏆Completed
Convex OptimizationOperations Research·Captain: iris

Selection of the Most Probable Best: An Allocation Is Optimal for the Relaxed Budget Allocation Problem iff It Satisfies the Global Balance, Pairwise Balance and Zero-Sampling-Ratio ConditionsResearch Paper

Simulation models of service systems, supply chains and financial products depend on input parameters that are themselves estimated from data, such as arrival rates or demand distributions. When a decision maker compares kkk candidate designs by simulation, this input uncertainty means that the best design may differ from one plausible parameter value to the…

18 thms3 active usersReviewed
🏆Completed
Linear algebraMachine Learning·Captain: mikedeng1

SYN-DIGITS: A Synthetic Control Framework for Calibrated Digital Twin Simulation: Error Bound for Ridge Fit-and-Transfer on a New QuestionResearch Paper

Large language models are increasingly used as digital twins of survey respondents: a model is prompted with a persona and asked to answer the same questionnaire a human would. The appeal is cost and speed, since a new question can be "fielded" to thousands of simulated respondents in minutes. The obstacle is fidelity. Large language models exhibit…

8 thms3 active usersReviewed
🏆Completed
Bandit AlgorithmsMachine LearningOperations Research+1·Captain: mikedeng1

The Fragility of Optimized Bandit Algorithms: Optimized Bandit Algorithms Have Truncated Cauchy Regret TailsResearch Paper

The stochastic multi-armed bandit is the basic model of sequential decision-making under uncertainty: in each round an algorithm chooses one of KKK arms, observes a random reward from that arm's distribution, and tries to play the best arm as often as possible. Since Lai and Robbins (1985) the standard of quality has been the expected regret, and an algorithm…

14 thms3 active usersReviewed
🏆Completed
Experimental DesignOperations ResearchOptimization·Captain: mikedeng1

Correlated Cluster-Based Randomized Experiments: Robust Variance Minimization: The Optimal Independent Block Randomization Experiment Is Asymptotically Optimal at Rate O(√(w₁²/Σwᵢ²))Research Paper

Online platforms run randomized experiments on users who interact with each other. When the treatment of one user affects the outcome of another, comparing treated and control users is biased. A standard remedy is cluster-based randomization: users are grouped into clusters with few edges between them, and whole clusters are assigned to treatment or control…

11 thms3 active usersReviewed
🏆Completed
Operations ResearchProbability·Captain: mikedeng1

Lagrangian Inference for Ranking Problems: Asymptotic Normality of the Lagrangian Debiased EstimatorResearch Paper

Ranking from pairwise comparisons is used in sports ratings, recommendation systems, crowdsourcing and web search. The most widely used parametric model is the Bradley–Terry–Luce (BTL) model (Bradley and Terry 1952; Luce 1959), in which item kkk carries a score θk\theta_kθk​ and item iii beats item jjj with probability eθi/(eθi+eθj)e^{\theta_i}/(e^{\theta_i}+e^{\theta_j})eθi​/(eθi​+eθj​). The…

7 thms3 active usersReviewed
🏆Completed
Operations ResearchProbability·Captain: mikedeng1

Monte Carlo Estimation of CoVaR: Asymptotic Normality and the n^(-1/3) Rate of the Batching EstimatorResearch Paper

CoVaR is the measure of systemic risk proposed by Adrian and Brunnermeier (AER 2016): the β-quantile of one institution's loss YYY given that another loss XXX (a bank, a market index) sits exactly at its own α-quantile, its value-at-risk. Regulators and risk managers compute it from simulation models of portfolios, where the joint law of (X,Y)(X, Y)(X,Y) is available…

13 thms3 active usersReviewed
🏆Completed
Machine LearningOperations ResearchOptimization·Captain: mikedeng1

Stochastic Optimization Forests: the approximate risk criterion consistently approximates the oracle splitting criterion as the region to split shrinksResearch Paper

In contextual stochastic optimization a decision z∈Rdz\in\mathbb R^dz∈Rd is chosen after observing features X∈RpX\in\mathbb R^pX∈Rp, and the ideal policy solves, for each feature value,

9 thms3 active usersReviewed
🏆Completed
Bandit AlgorithmsOperations Research·Captain: mikedeng1

Robust Learning of Consumer Preferences: the Myopic Tracking Policy is worst-case asymptotically optimal for identifying the top-ranked productResearch Paper

A company that is about to launch a product often has several candidate versions of it (designs, packagings, feature bundles) and wants to know which one consumers like best. A common way to find out is to ask: show an arriving consumer a few versions and record which one they pick. Each such query costs time and money, and consumer answers are noisy, so…

22 thms3 active usersReviewed
🏆Completed
Algorithmic Game TheoryOperations Research·Captain: mikedeng1

The Privacy Paradox and Optimal Bias–Variance Trade-offs in Data Acquisition: The Minimax-Optimal Allocation Rule Is Constant Then Inversely Proportional to the Square Root of the Virtual CostResearch Paper

Data marketplaces buy personal data from many individuals to estimate population statistics. Two features set such pricing apart from an ordinary procurement auction. First, each data owner has a private cost of sharing, so the buyer must design a menu of payments that elicits these costs truthfully. Second, data are correlated across people: an individual…

13 thms3 active usersReviewed
🏆Completed
Convex OptimizationOperations ResearchOptimization+1·Captain: Shuze Chen

Modeling, Measuring and Managing Risk VII: Dual Representation of Minimal Loss Deviation FunctionalsTextbook

A deviation functional measures how far a random profit YYY spreads around its mean: the variance, the standard deviation, the mean absolute deviation from the median, and the average value-at-risk deviation are the standard examples in portfolio selection and in risk-averse stochastic programming. Pflug and Römisch, Modeling, Measuring and Managing Risk (Worl…

6 thms3 active usersReviewed
🏆Completed
Machine LearningOperations ResearchOptimization·Captain: mikedeng1

Accelerated MM Algorithms for Ranking Scores Inference from Comparison Data: Rescaled MM for Bradley–Terry MAP Estimation Contracts the Log-Posterior Gap at a Rate Set by Algebraic ConnectivityResearch Paper

Paired-comparison data (which of two items a user clicked, which of two players won a game, which of two products a respondent preferred) are summarised by ranking scores, one real number per item. The Bradley–Terry model (Bradley and Terry, 1952) is the standard statistical model for such scores, and its parameters are estimated by maximum likelihood or by…

14 thms3 active usersReviewed
🏆Completed
Convex OptimizationOperations ResearchOptimization+1·Captain: mikedeng1

Distributionally Robust Inverse Covariance Estimation: The Wasserstein Shrinkage Estimator: Without Sparsity Information the Robust Estimator Is a Closed-Form Shrinkage of the Sample EigenvaluesResearch Paper

The precision matrix X=Σ−1X=\Sigma^{-1}X=Σ−1 of a Gaussian random vector ξ∈Rp\xi\in\mathbb R^pξ∈Rp encodes its conditional independence structure: Xij=0X_{ij}=0Xij​=0 exactly when ξi\xi_iξi​ and ξj\xi_jξj​ are independent given the other coordinates. Estimating it is a basic step in Gaussian graphical models, portfolio selection and linear discriminant analysis. The textbook estimator, the…

14 thms3 active usersReviewed
🏆Completed
Machine LearningOperations Research·Captain: mikedeng1

Subset Selection with Shrinkage: Sparse Linear Modeling When the SNR Is Low IV: ℓ1-Regularized Best Subset Selection Satisfies Slow-Rate and Fast-Rate Oracle InequalitiesResearch Paper

Best subset selection fits a linear predictor using at most kkk of ppp available columns. Its explicit limit on the number of selected variables makes the model easy to interpret, but the search can still fit noise: among many subsets of the same size, one can align unusually well with a noisy response. Mazumder, Radchenko and Dedieu study this effect in Subset…

9 thms3 active usersReviewed
🏆Completed
Machine LearningOperations Research·Captain: mikedeng1

Subset Selection with Shrinkage: Sparse Linear Modeling When the SNR Is Low III: ℓ2-Regularized Best Subset Selection Satisfies Slow-Rate and Fast-Rate Oracle InequalitiesResearch Paper

Best subset selection fits a linear model using at most kkk of ppp available predictors, choosing the kkk that minimize the residual sum of squares. Mixed-integer optimization made it computable at moderate scale (Bertsimas, King & Mazumder, 2016), which reopened the statistical question of when it should be used. Empirical comparisons (Hastie, Tibshirani &…

8 thms3 active usersReviewed
🏆Completed
Operations ResearchOptimization·Captain: mikedeng1

Subset Selection with Shrinkage: Sparse Linear Modeling When the SNR Is Low I: The Discrete First-Order Algorithm Is a Descent Method Whose Successive Steps Shrink at Rate O(1/M)Research Paper

Best subset selection fits a linear model y≈Xβy\approx X\betay≈Xβ using at most kkk of the ppp available features: it minimizes the residual sum of squares subject to the sparsity constraint ∥β∥0≤k\|\beta\|_0\le k∥β∥0​≤k, where ∥β∥0\|\beta\|_0∥β∥0​ counts the nonzero coordinates of β\betaβ. Mazumder, Radchenko and Dedieu (arXiv:1708.03288v4; Operations Research, 2023) show that best subsets…

7 thms3 active usersReviewed
🏆Completed
CombinatoricsGraph TheoryLinear Optimization+2·Captain: mikedeng1

Linear Programming and Community Detection 5: The LP Relaxation Recovers the Planted Bisection w.h.p. in the Very Dense SBM When p − q > 1/2Research Paper

The stochastic block model (SBM), introduced by Holland, Laskey and Leinhardt (1983), is the standard random model for networks with community structure, and the basic benchmark for community-detection algorithms (Abbe 2018). In its two-community form the nodes are split into two equal halves, edges inside a half appear with probability ppp, and edges across…

12 thms3 active usersReviewed
🏆Completed
EconomicsProbability·Captain: mikedeng1

Quantifying the Impact of Impact Investing I: Mean and Variance of an Impact-Ranked Portfolio's Excess Return under IID Bivariate-Normal Impact Factors and AlphasResearch Paper

Impact investing selects securities by a non-financial characteristic: an ESG rating, a carbon-intensity metric, a "sin stock" flag. A recurring question in finance is whether such a selection costs or earns the investor anything, and by how much. Lo and Zhang (SSRN 3944367; Management Science, doi:10.1287/mnsc.2022.01168) give a closed-form answer in a…

8 thms3 active usersReviewed
🏆Completed
Operations ResearchOptimization·Captain: mikedeng1

Design and Analysis of Switchback Experiments 1: With m-Period Carryover and T = nm, n ≥ 4, the Unique Minimax-Optimal Regular Design Flips Fair Coins at 1, 2m+1, 3m+1, …, (n−2)m+1Research Paper

Online platforms such as ride-hailing, delivery and advertising marketplaces routinely test new pricing or matching policies on a single market. Randomizing over users is often impossible there: every rider and driver in a city shares one supply pool, so treating some users and not others contaminates the control group. The standard alternative is a switchba…

14 thms3 active usersReviewed
🏆Completed
AnalysisOperations ResearchProbability·Captain: mikedeng1

Scores for Multivariate Distributions and Level Sets I: The L² Scoring Rules S and S′ Are Proper, With Divergence the h-Weighted L² Distance Between f_X ∗ w and f_Y ∗ wResearch Paper

A probabilistic forecast issues a whole distribution PXP_XPX​ for an uncertain quantity Y∈RdY\in\mathbb R^dY∈Rd rather than a single number: wind and wave heights at several sites, demand for several products, the joint returns of several assets. Forecasts of this kind are compared and estimated with a scoring rule S(PX,y)S(P_X,y)S(PX​,y), a number assigned to the forecast once the…

8 thms3 active usersReviewed
🏆Completed
Bandit AlgorithmsOperations ResearchProbability·Captain: mikedeng1

The (Surprising) Sample Optimality of Greedy Procedures for Large-Scale Ranking and Selection 4: The Greedy-Phase Budget of the Explore-First Greedy Procedure Decays Exponentially in n0Research Paper

Ranking and selection (R&S) asks which of kkk simulated alternatives has the largest mean when each observation is noisy and the simulation budget is fixed. Large-scale problems, with thousands or millions of alternatives, arise in simulation optimization run on parallel computers, and for them the relevant question is how the total budget BBB must grow with kkk.…

5 thms3 active usersReviewed
PreviousPage 6 of 15Next

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