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 LearningProbability·Captain: mikedeng1

Online Learning and Online Convex Optimization 5: Online-to-Batch Conversion Bounds the Excess Risk by the Expected Average RegretResearch Paper

Online learning and stochastic learning ask different questions. An online learner faces an arbitrary sequence of loss functions and is judged by its regret: the excess of its cumulative loss over that of the best fixed hypothesis in hindsight. A stochastic learner receives independent samples from an unknown distribution and is judged by the risk of a…

6 thms2 active usersReviewed
🏆Completed
Information TheoryTheoretical Computer Science·Captain: wurtle

Posterior replicas and conditional information in Gaussian regressionResearch Paper

Suppose an unknown unit vector s∈Sd−1s \in S^{d-1}s∈Sd−1 is observed through exact linear measurements Yj=⟨Xj,s⟩Y_j = \langle X_j, s\rangleYj​=⟨Xj​,s⟩ with independent Gaussian rows Xj∼N(0,Id)X_j \sim N(0, I_d)Xj​∼N(0,Id​). If every pair is kept, ddd rows determine sss. A learner that can keep only a bounded number of bits between measurements must compress each exact real label into a state update, and the…

20 thms2 active usersReviewed
🏆Completed
Machine LearningTheoretical Computer Science·Captain: wurtle

Memory and precision in noiseless Gaussian regressionResearch Paper

A single exact linear equation y=⟨x,s⟩y = \langle x, s\rangley=⟨x,s⟩ about an unknown unit vector s∈Rds \in \mathbb{R}^ds∈Rd carries arbitrarily fine information: ddd independent Gaussian equations determine sss almost surely, provided all of them can be kept. A learner that reads the equations once, in order, and keeps only a bounded number of bits between them faces a different…

18 thms2 active usersReviewed
🏆Completed
Graph TheoryOptimization·Captain: mikedeng1

Random Graphs with a Given Degree Sequence 1: The Fixed-Point Iteration x ↦ φ(x) Converges Geometrically to the Unique β-Model MLE, and Diverges When No MLE ExistsResearch Paper

The β\betaβ-model is the simplest exponential random graph model in which every vertex has its own parameter. It was studied by Holland and Leinhardt (1981) in the directed case and by Park and Newman (2004) and Blitzstein and Diaconis (2011) in the undirected case, and it is a close relative of the Bradley–Terry model for paired comparisons. Its sufficient…

9 thms2 active usersReviewed
🏆Completed
Machine LearningOptimization·Captain: mikedeng1

Robust Regression and Lasso 3: Robust Regression Has a Solution Supported on I if Some Allowable Perturbation of the Features Outside I Makes Them IrrelevantResearch Paper

The Lasso fits a linear model by least-norm regression with an ℓ1\ell^1ℓ1 penalty, and its most used property is that it returns sparse coefficient vectors: many features receive weight exactly zero. Most sparsity guarantees for the Lasso are statistical. They assume a generative model and an incoherence or irrepresentability condition on the design, and…

7 thms2 active usersReviewed
🏆Completed
Machine LearningOptimization·Captain: mikedeng1

Robust Regression and Lasso 1: Under Feature-Wise Norm-Bounded Column Disturbances, Worst-Case Least-Norm Regression Is Exactly ℓ1-Regularized Regression ‖b − Ax‖₂ + Σ cᵢ|xᵢ|Research Paper

The Lasso (Tibshirani 1996; Chen, Donoho and Saunders 1998) fits a linear model b≈Axb \approx Axb≈Ax by penalizing the ℓ¹ norm of the coefficients. It is one of the standard tools of high-dimensional statistics and signal processing, and its usual justification is statistical or geometric: the ℓ¹ penalty is a convex surrogate for sparsity, or the negative…

5 thms2 active usersReviewed
🏆Completed
Experimental DesignOperations ResearchProbability+1·Captain: mikedeng1

Stochastic Kriging for Simulation Metamodeling II: The MSE of the Optimal Stochastic Kriging Predictor Exceeds the Kriging MSE by a Positive Definite FormResearch Paper

A simulation metamodel is a cheap surrogate for an expensive stochastic simulation: after running the simulation at a few design settings, one predicts the mean response at settings never simulated. Kriging, the interpolation method of geostatistics and of the design and analysis of computer experiments (DACE; Sacks, Welch, Mitchell and Wynn 1989; Santner,…

4 thms2 active usersReviewed
🏆Completed
Experimental DesignOperations ResearchProbability+1·Captain: mikedeng1

Stochastic Kriging for Simulation Metamodeling I: The Plug-In Stochastic Kriging Predictor Is UnbiasedResearch Paper

Stochastic simulation models of queues, supply chains and manufacturing systems are often too slow to run at every input setting of interest. A metamodel fitted to a moderate number of simulation runs then stands in for the simulation, for instance inside an optimization or a sensitivity analysis. Kriging, developed in geostatistics and in the design and…

6 thms2 active usersReviewed
🏆Completed
Probability·Captain: mikedeng1

On Tail Probabilities for Martingales 2: For |X_n| ≤ 1 and E{X_n | ℱ_{n−1}} = 0, the Conditional Variance W_a Used to Cross a Satisfies E exp[−f(λ)W_a] ≥ exp[−λ(a+1)]Research Paper

Exponential tail bounds for sums of bounded martingale differences (Bernstein, Bennett, Hoeffding, Freedman) are the workhorses of probability, statistics and learning theory. They bound how far a martingale can travel in a given amount of conditional variance. The converse question is just as basic: how much conditional variance does a martingale need…

10 thms2 active usersReviewed
🏆Completed
Operations ResearchProbability·Captain: mikedeng1

Residual Life Time at Great Age 6: For 0 < ξ < α, Residual Life Attraction to Γ_α Is Equivalent to a Finite ξ-th Moment and E((X/t)^ξ | X > t) → (1 − ξ/α)^{−1}Research Paper

Actuaries, reliability engineers and demographers ask how much longer an item or a person will live given that it has already survived to a great age ttt. For a lifetime XXX with distribution function FFF, this is the law of the residual life time X−tX - tX−t given X>tX > tX>t, and the question is what this law looks like as t→∞t \to \inftyt→∞. Balkema and de Haan (Ann. Probab. 2…

8 thms2 active usersReviewed
🏆Completed
Operations ResearchProbability·Captain: mikedeng1

Residual Life Time at Great Age 2: The Domain of Residual Life Time Attraction of the Exponential Law Is D(Λ) ∩ D₀Research Paper

A lifetime observed only after it has survived to a high age is described by its residual life: the additional time until failure, conditional on survival so far. Reliability analysis asks whether these conditional distributions settle into a stable shape after scaling and shifting. Extreme-value theory asks a related question about the largest observation…

11 thms2 active usersReviewed
🏆Completed
Operations ResearchProbability·Captain: mikedeng1

Residual Life Time at Great Age 3: F Is in the Domain of Residual Life Time Attraction of Π_{p,c} iff It Is Tail Equivalent to a Discrete Law with Gap Ratios → e^{pc} and Tail Ratios → e^{−p}Research Paper

A component that has survived to age ttt has a residual life time X−tX - tX−t, and in reliability, actuarial work and the analysis of excesses over high thresholds the question is what its conditional law looks like when ttt is large. Balkema and de Haan (Ann. Probab. 2 (1974), 792–804) answered this in full generality: after an affine normalization, the only…

9 thms2 active usersReviewed
🏆Completed
Operations ResearchProbability·Captain: mikedeng1

Simulation Output Analysis Using Standardized Time Series 2: Every STS Interval Has liminf n^{1/2} E Lₙ ≥ 2σΦ⁻¹(1 − δ/2)Research Paper

A simulation run often estimates a steady-state mean without producing independent observations. A confidence interval must account for dependence in the output, and the relevant variance constant may be unknown. Standardized time series (STS) methods use the shape of an integrated output path to cancel that constant rather than estimating it separately.…

11 thms2 active usersReviewed
🏆Completed
Operations Research·Captain: mikedeng1

Some Theoretical Aspects of Road Traffic Research I: Time-Mean Speed Equals Space-Mean Speed plus σₛ²/v̄ₛ, so v̄ₜ ≥ v̄ₛ with Equality Only Without Speed VariationResearch Paper

A speed recorded as a vehicle passes a fixed point and a speed recorded among vehicles occupying a road segment answer different questions. Fast vehicles pass a detector more often per unit time; slow vehicles remain visible along the segment for longer. Traffic studies therefore need to identify which distribution a measurement samples before comparing…

5 thms2 active usersReviewed
🏆Completed
AnalysisProbability·Captain: mikedeng1

Estimating Variance From High, Low and Closing Prices II: Under the Overshoot Law (9), E(Z ∨ Z′) = aσ√h and E(Z ∨ Z′)² = bσ²hResearch Paper

Volatility estimates from daily high, low and closing prices have been used since Parkinson (1980) and Garman and Klass (1980): the range of a day's log-price carries much more information about the volatility σ\sigmaσ than the close alone. Rogers and Satchell (1991) propose an estimator, S1(S1−X1)+I1(I1−X1)S_1(S_1-X_1)+I_1(I_1-X_1)S1​(S1​−X1​)+I1​(I1​−X1​), that is unbiased for σ2\sigma^2σ2 whatever the…

8 thms2 active usersReviewed
🏆Completed
Operations ResearchProbability·Captain: mikedeng1

Some Aspects of the Sequential Design of Experiments III: Optional Stopping — P(Sₙ > αn^½ for Some n₁ ≤ n ≤ n₂) < (1 − Φ(α))/(1 − Φ(α(λ^½ − 1)/(λ − 1)^½))Research Paper

Section 4 of Herbert Robbins's 1952 address Some aspects of the sequential design of experiments (Bull. Amer. Math. Soc. 58, 527–535, doi:10.1090/S0002-9904-1952-09620-8) isolates a problem that every user of significance tests meets: if the sample size is not fixed in advance, an experimenter can keep sampling until the test rejects. Robbins shows that a…

4 thms2 active usersReviewed
🏆Completed
Probability·Captain: mikedeng1

The Tight Constant in the Dvoretzky–Kiefer–Wolfowitz Inequality II: Binomial Tail Bound P(S − np > nε) ≤ exp(−nε²/(2(p + ε/3)(q − ε/3))) for 0 < ε ≤ qResearch Paper

Exponential bounds for the tails of the binomial distribution are among the most frequently used tools in probability, statistics and the analysis of algorithms: they control the number of successes in independent trials, the deviation of an empirical frequency from its mean, and, through counting arguments, the empirical distribution function itself. The…

5 thms2 active usersReviewed
🏆Completed
Convex OptimizationMachine Learning·Captain: mikedeng1

Distributed Optimization and Statistical Learning via the Alternating Direction Method of Multipliers VI: The Group-Lasso Block Update Is Zero iff ‖Aᵢᵀv‖₂ ≤ λ/ρ, Otherwise Ridge with ν‖xᵢ‖₂ = λ/ρTextbook

Fitting a statistical model usually means solving a convex problem of the form

10 thms2 active usersReviewed
🏆Completed
Convex OptimizationLinear algebra·Captain: mikedeng1

Distributed Optimization and Statistical Learning via the Alternating Direction Method of Multipliers IV: The Covariance-Selection X-Update Is Q·diag((λᵢ + √(λᵢ² + 4ρ))/(2ρ))·QᵀTextbook

Many estimation problems in statistics, machine learning and signal processing minimize a smooth loss plus a nonsmooth ℓ1-type regularizer: the lasso, basis pursuit, least absolute deviations, Huber fitting, the group lasso, and ℓ1-penalized maximum likelihood for Gaussian graphical models. Chapter 6 of Boyd, Parikh, Chu, Peleato and Eckstein, Distributed…

13 thms2 active usersReviewed
🏆Completed
Operations ResearchProbability·Captain: mikedeng1

Residual Life Time at Great Age 4: α₁ ≤ tF′(t)/(1 − F(t)) ≤ α₂ for t ≥ t₀ Sandwiches P{(X − t)/t ≤ x | X > t} Between Γ_{α₁}(x) and Γ_{α₂}(x)Research Paper

The residual life time of a lifetime XXX at age ttt is the remaining life X−tX - tX−t given survival past ttt. Its distribution at great age is a basic object in reliability, insurance and the statistics of extremes: excess-of-loss reinsurance prices the part of a claim above a retention level, and peaks-over-threshold methods fit a model to the observations exceeding…

4 thms2 active usersReviewed
🏆Completed
Linear OptimizationOperations Research·Captain: mikedeng1

Optimal Estimation of Executive Compensation by Linear Programming I: Least Absolute Deviations under Ranking Constraints Equal a Linear ProgramResearch Paper

A firm may know salary bounds and the ranking of positions without having a reliable sample of individual salaries suitable for least-squares estimation. Charnes, Cooper and Ferguson used that kind of partial information to estimate a salary formula from ratings assigned to job factors. Their 1955 paper gives a model in which weights respect the job…

5 thms2 active usersReviewed
🏆Completed
Bandit AlgorithmsMachine LearningProbability·Captain: mikedeng1

Kullback–Leibler Upper Confidence Bounds for Optimal Sequential Allocation II: Empirical KL-UCB Draws a Suboptimal Arm log(T)/K_inf(ν_a, μ*) + O((log T)^{4/5} log log T) TimesResearch Paper

In a stochastic multi-armed bandit a player repeatedly chooses one of KKK arms and receives a random reward drawn from that arm's unknown distribution; the aim is to pull suboptimal arms as rarely as possible. Lai and Robbins (1985) and, for general models, Burnetas and Katehakis (1996) showed that any reasonable strategy must pull a suboptimal arm aaa at least …

13 thms2 active usersReviewed
🏆Completed
Machine LearningOptimal TransportProbability·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 LearningOptimal TransportOptimization·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
Bandit AlgorithmsOperations ResearchProbability·Captain: mikedeng1

Dynamic Pricing Without Knowing the Demand Function: Risk Bounds and Near-Optimal Algorithms II: The Parametric Learn-then-Price Policy Has Regret at Most C(log n)^{1/2}/n^{1/3}Research Paper

A seller with a fixed inventory must choose prices before knowing how customers respond to them. A price that earns a high margin can sell too slowly; a price that sells quickly can exhaust stock before the selling season ends. Learning demand uses time and inventory, so the seller must account for the cost of its own experiments. This mission formalizes…

13 thms2 active usersReviewed
PreviousPage 12 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