Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in

Get started

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

Machine Learning

886 missions · 536 completed

The science of systems that learn from data and experience. Its scope runs from the statistical and mathematical foundations of learning, including generalization, expressivity, and computational limits, through the design of learning algorithms, deep learning, reinforcement learning, and probabilistic methods, to the empirical study of large models and the trustworthiness, interpretability, and societal impact of learned systems.

Missions

Open350Completed536All886
Bandit AlgorithmsOperations ResearchStatistics·Captain: mikedeng1

Personalized Dynamic Pricing with Machine Learning: High-Dimensional Features and Heterogeneous Elasticity 1: Under Known Sparsity, ILSX Pricing Has Regret at Most Cs√T log TResearch Paper

A seller who changes prices while learning demand faces two costs: a price experiment may earn less revenue now, while insufficient experimentation leaves later prices poorly calibrated. Customer features make the balance harder because both willingness to buy and sensitivity to price may vary between customers. Ban and Keskin study this problem when the…

6 thms2 active usersReviewed
Bandit AlgorithmsProbabilityStatistics·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
Control TheoryOperations ResearchProbability+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
Numerical AnalysisOptimization·Captain: mikedeng1

Conservative Set Valued Fields, Automatic Differentiation, Stochastic Gradient Methods and Deep Learning 2: Forward and Reverse Mode Automatic Differentiation Yield Conservative FieldsResearch Paper

Training a neural network means running a first-order method on a loss that is built from compositions of elementary operations, many of them nonsmooth: ReLU, max-pooling, absolute values, sorting, norms. The gradient the optimizer uses is not computed by hand. It is computed by automatic differentiation (autodiff), most often in its reverse mode, backpropag…

13 thms2 active usersReviewed
Bandit Algorithms·Captain: mikedeng1

An Optimal Algorithm for Stochastic and Adversarial Bandits III: α-Tsallis-INF With Gap-Tuned Asymmetric Regularization Has Logarithmic Pseudo-Regret When the Best Arm Is UniqueResearch Paper

In the multi-armed bandit problem a learner repeatedly chooses one of KKK actions and observes only the loss of the action it chose. Two models of the environment dominate the literature. In the stochastic model the losses of each arm are drawn i.i.d. from a fixed distribution, and the optimal pseudo-regret grows like ∑i≠i∗log⁡(T)/Δi\sum_{i\ne i^*}\log(T)/\Delta_i∑i=i∗​log(T)/Δi​, where …

14 thms2 active usersReviewed
Dynamical SystemsOptimizationProbability·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
Dynamical SystemsOptimization·Captain: mikedeng1

Convergence and Dynamical Behavior of the ADAM Algorithm for Nonconvex Stochastic Optimization 2: The Continuous-Time Adam Trajectory Converges to the Critical Points of FResearch Paper

Adam (Kingma and Ba, 2015) is the default optimizer for training neural networks. At step nnn it keeps an exponential moving average mnm_nmn​ of stochastic gradients and an exponential moving average vnv_nvn​ of their squared coordinates, corrects both for their initialization at zero (the bias correction or debiasing step), and moves the iterate by …

14 thms2 active usersReviewed
Convex OptimizationOptimization·Captain: mikedeng1

Stochastic Dual Coordinate Ascent Methods for Regularized Loss Minimization 3: Under Refined Dual Strong Convexity, SDCA Reaches Expected Dual Sub-optimality ε after 2(n/s)·log(2/ε) IterationsResearch Paper

Regularized loss minimization covers support vector machines, logistic and ridge regression, and the absolute-deviation regression of robust statistics. Stochastic dual coordinate ascent (SDCA) solves these problems by maximizing the Fenchel dual one randomly chosen coordinate at a time. Shalev-Shwartz and Zhang (arXiv:1209.1873, JMLR 2013) gave the first…

13 thms2 active usersReviewed
Optimal TransportProbabilityStatistics·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
Dynamical SystemsOptimization·Captain: mikedeng1

Convergence and Dynamical Behavior of the ADAM Algorithm for Nonconvex Stochastic Optimization 3: Under a Łojasiewicz Condition the Adam ODE Converges to One Critical Point at Rate t^(−θ/(1−2θ))Research Paper

Adam (Kingma and Ba, 2015) is the default optimizer for training neural networks. At each step it keeps an exponential moving average mmm of stochastic gradients and an exponential moving average vvv of their squared coordinates, corrects both for their initialization at zero (the bias correction), and moves the iterate by …

9 thms2 active usersReviewed
Convex OptimizationOptimization·Captain: mikedeng1

Stochastic Dual Coordinate Ascent Methods for Regularized Loss Minimization 1: With L-Lipschitz Losses, SDCA Reaches Expected Duality Gap ε after ⌈n log(λn/(2L²))⌉ + n + 20L²/(λε) IterationsResearch Paper

Regularized loss minimization over linear predictors is the training problem behind support vector machines, logistic regression, ridge regression and their many variants. Given examples x1,…,xn∈Rdx_1,\dots,x_n\in\mathbb R^dx1​,…,xn​∈Rd, one minimizes an average of convex losses of the predictions w⊤xiw^\top x_iw⊤xi​ plus a quadratic penalty. Dual coordinate ascent (DCA) solves the…

13 thms2 active usersReviewed
ProbabilityRandom Matrix TheoryStatistics·Captain: mikedeng1

Nuclear-Norm Penalization and Optimal Rates for Noisy Low-Rank Matrix Completion 3: Uniform Matrix Completion with |Yᵢ| ≤ η — With Probability ≥ 1 − e^{−t} the Oracle Bound (3.5) Holds for All AResearch Paper

Matrix completion asks to recover a large matrix from a small number of its entries. It is the abstraction behind collaborative filtering (recommender systems in which a users × items rating matrix is observed on a sparse set of pairs), sensor localization from partial distance information, and system identification. Without structure the problem is…

12 thms2 active usersReviewed
ProbabilityStatistics·Captain: mikedeng1

Nuclear-Norm Penalization and Optimal Rates for Noisy Low-Rank Matrix Completion 5: With Gaussian Noise and λ = 3b√2 σ√(log p/n), the Lasso Satisfies a Sharp Sparsity Oracle InequalityResearch Paper

The Lasso is the standard estimator for high-dimensional linear regression: from nnn noisy linear measurements of an unknown vector β∗∈Rp\beta^*\in\mathbb R^pβ∗∈Rp, with ppp possibly much larger than nnn, it minimizes the empirical squared error plus an ℓ1\ell_1ℓ1​ penalty. Its theoretical guarantees are usually stated as sparsity oracle inequalities: the prediction error of…

7 thms2 active usersReviewed
Linear algebraStatistics·Captain: mikedeng1

Nuclear-Norm Penalization and Optimal Rates for Noisy Low-Rank Matrix Completion 4: The Estimator Never Overestimates rank(A₀), Recovers It Above a Singular-Value Gap, and Obeys a Matching Lower BoundResearch Paper

Noisy low-rank matrix completion asks to reconstruct an m1×m2m_1\times m_2m1​×m2​ matrix A0A_0A0​ from nnn noisy observations of randomly chosen entries. It is the statistical model behind collaborative filtering (recommender systems), sensor localization and system identification, and the nuclear-norm penalized least-squares estimator is its standard convex method.…

13 thms2 active usersReviewed
ProbabilityStatistics·Captain: mikedeng1

Optimal Aggregation of Classifiers in Statistical Learning: The Adaptive Classifier Attains the Optimal Fast Rate up to a Logarithmic Factor Simultaneously on All Classes (Theorem 3)Research Paper

Binary classification asks for a rule that predicts a label Y∈{0,1}Y\in\{0,1\}Y∈{0,1} from a feature vector X∈RdX\in\mathbb R^dX∈Rd, given nnn labelled examples. A classical way to measure how hard this is, due to Mammen and Tsybakov (1999), treats classification as the estimation of a set, the region where label 111 is more likely, and asks how fast the excess misclassification…

19 thms2 active usersReviewed
Algorithmic Game TheoryProbability·Captain: mikedeng1

A Simple Adaptive Procedure Leading to Correlated Equilibrium 1: Under Regret-Matching (2.2), the Empirical Distributions of Play Converge Almost Surely to the Set of Correlated EquilibriaResearch Paper

A correlated equilibrium (Aumann 1974) is a probability distribution over strategy profiles of a game such that no player gains by deviating from a recommended strategy, given the recommendation. It is the solution concept of choice when players can condition on common signals, and its set is a convex polytope defined by linear inequalities, which makes it…

17 thms2 active usersReviewed
ProbabilityStatistics·Captain: mikedeng1

Consistent Nonparametric Regression II: Nearest-Neighbor Weights with Vanishing Coefficients Are Consistent for Every Distribution of X (Theorem 2)Research Paper

Nonparametric regression estimates the regression function x↦E(Y∣X=x)x \mapsto E(Y \mid X = x)x↦E(Y∣X=x) from i.i.d. observations (X1,Y1),…,(Xn,Yn)(X_1, Y_1), \dots, (X_n, Y_n)(X1​,Y1​),…,(Xn​,Yn​) without assuming a parametric form. The simplest such estimates are local averages: to predict at a point XXX, average the responses YiY_iYi​ of the sample points closest to XXX. Nearest neighbor rules of this kind go back to…

8 thms2 active usersReviewed
Dynamic ProgrammingMarkov ChainProbability+1·Captain: mikedeng1

An Analysis of Temporal-Difference Learning with Function Approximation 1: Linear TD(λ) Converges with Probability 1 to the Fixed Point of ΠT^(λ), with Error ≤ ‖ΠJ* − J*‖_D/(1 − α(1−λ)/(1−αλ))Research Paper

Temporal-difference learning, TD(λ\lambdaλ), is the basic algorithm of reinforcement learning for estimating the expected discounted cost of a Markov chain from observed transitions (Sutton, 1988). On large or infinite state spaces it is run with a linear function approximator: the cost-to-go is represented as a weighted sum of KKK fixed basis functions, and…

13 thms2 active usersReviewed
ProbabilityStatistics·Captain: mikedeng1

Consistent Nonparametric Regression I: Conditions (1)–(5) on a Sequence of Weights Are Sufficient for Consistency, and Consistency Forces Them Back (Theorem 1)Research Paper

Nonparametric regression estimates the conditional mean E(Y∣X=x)E(Y\mid X=x)E(Y∣X=x) of a real response YYY given a predictor X∈RdX\in\mathbb R^dX∈Rd without assuming that it belongs to a finite-dimensional family. Most practical estimators of this kind are local averages: kernel estimators (Nadaraya 1964, Watson 1964), nearest-neighbor rules (Cover and Hart 1967), and their many…

9 thms2 active usersReviewed
Operations ResearchOptimizationProbability+1·Captain: mikedeng1

From Predictive to Prescriptive Analytics 1: The k-Nearest-Neighbor Predictive Prescription Is Asymptotically Optimal and ConsistentResearch Paper

Operations research has long studied the stochastic problem min⁡z∈ZE[c(z;Y)]\min_{z\in\mathcal Z}\mathbb E[c(z;Y)]minz∈Z​E[c(z;Y)]: choose a decision zzz before an uncertain quantity YYY (demand, prices, returns) is revealed. In practice the decision maker also observes covariates XXX before deciding (web-search volume before stocking a product, weather before routing a shipment) and should…

7 thms2 active usersReviewed
CombinatoricsGroup Theory·Captain: mikedeng1

A Characterization of Multiclass Learnability 2: A Concept Class with Natarajan Dimension 1 and Infinite DS DimensionResearch Paper

In binary classification the VC dimension decides PAC learnability: a class of {0,1}\{0,1\}{0,1}-valued functions is learnable from finitely many examples exactly when its VC dimension is finite. Multiclass classification, where a predictor outputs one of many labels, arises whenever the label set is large: language models choosing a next token, image recognition…

10 thms2 active usersReviewed
Bandit AlgorithmsOperations ResearchStatistics·Captain: mikedeng1

Online Decision Making with High-Dimensional Covariates: Regret Bound of the LASSO BanditResearch Paper

Many sequential decisions are personalised: a physician chooses a drug dose for each arriving patient, a platform chooses which offer to show each arriving user. Each decision is made after observing a vector of covariates describing the individual, and its outcome is observed only for the option chosen. This is the contextual (covariate) bandit problem,…

9 thms2 active usersReviewed
Convex OptimizationProbabilityRandom Matrix Theory+1·Captain: mikedeng1

The Power of Convex Relaxation: Near-Optimal Matrix Completion I: Exact Nuclear-Norm Recovery with Quadratic Dependence on the RankResearch Paper

Matrix completion asks to recover a low-rank matrix from a small random subset of its entries. It models collaborative filtering (a ratings matrix with most entries missing), sensor-network localization from partial distance matrices, and system identification. The natural estimator, the matrix of least rank that agrees with the observations, is NP-hard to…

14 thms2 active usersReviewed
ProbabilityTheoretical Computer Science·Captain: mikedeng1

Sketching Language Models for Context AttributionResearch Paper

Context attribution asks how parts of a prompt affect a chosen measurement of a language model's output. For a prompt with nnn tokens, leave-one-out attribution records the measurement after deleting each token individually. Direct evaluation takes nnn model calls. Liaw, Mehta, Velegkas and Zhou study when all these values can be estimated with fewer calls,…

20 thms1 active userReviewed
Convex OptimizationOptimizationProbability+1·Captain: Shuze Chen

Bias-Reduced and Parallel Heavy-Tailed Stochastic Convex Optimization in ℓp\ell_pℓp​ GeometriesResearch Paper

Stochastic convex optimization (SCO) asks for an approximate minimizer of a convex function that can only be probed through noisy subgradients. Two features of modern instances are not captured by the textbook Euclidean, bounded-variance setting. First, the natural geometry is often an ℓp norm with p>2p>2p>2: the feasible region is an ℓp ball and the Lipschitz…

15 thms1 active userReviewed
PreviousPage 11 of 14Next

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