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
🏆Completed
CombinatoricsProbabilityStatistics·Captain: naimengye

An Introduction to Computational Learning Theory V: Classification Noise and Statistical QueriesTextbook

Chapter 5 of Kearns and Vazirani, An Introduction to Computational Learning Theory (MIT Press, 1994, doi:10.7551/mitpress/3897.001.0001), asks what happens to PAC learning when the labels are unreliable. In the classification noise model of Angluin and Laird, each label returned by the oracle is flipped independently with a fixed probability η<1/2\eta < 1/2η<1/2. The…

7 thms3 active usersReviewed
🏆Completed
CombinatoricsProbabilityStatistics·Captain: naimengye

An Introduction to Computational Learning Theory IV: Weak and Strong Learning, Boosting and Chernoff BoundsTextbook

Chapter 4 of Kearns and Vazirani, An Introduction to Computational Learning Theory (MIT Press, 1994, doi:10.7551/mitpress/3897.001.0001), asks whether the PAC model's demand for arbitrarily small error and confidence is essential. A weak learning algorithm need only, with some fixed positive probability, output a hypothesis that beats random guessing by a…

7 thms3 active usersReviewed
🏆Completed
Algorithmic Game TheoryBandit AlgorithmsOperations Research+1·Captain: naimengye

Introduction to Multi-Armed Bandits XI: Bandits and Agents, Incentivized Exploration via Hidden ExplorationTextbook

A recommendation system learns from the users it serves: the diner who tries a restaurant produces the review the next diner reads. Each user would rather exploit what is already known than explore for the benefit of those who come later, so a population of self-interested agents under-explores, and an alternative that looks bad on sparse early evidence may…

10 thms3 active usersReviewed
🏆Completed
Operations ResearchProbabilityStatistics+1·Captain: mikedeng1

Foundations of Machine Learning XIV: Finite Markov Decision Processes and Bellman's EquationsTextbook

Reinforcement learning formalizes a scenario supervised learning cannot: an agent that actively interacts with an environment, choosing actions that change both the state it observes next and the reward it receives, rather than passively receiving an i.i.d. labeled sample. Every practical treatment of this scenario — from classical dynamic programming to…

13 thms3 active usersReviewed
🏆Completed
Convex OptimizationOperations ResearchOptimization·Captain: mikedeng1

First-Order and Stochastic Optimization Methods for Machine Learning I: The Separation Theorem, Strong Duality and the KKT ConditionsTextbook

Every convex optimization algorithm in machine learning — from projected gradient descent to support vector machines to the mirror-descent methods of later chapters of this book — is justified by a small set of optimality certificates: a checkable condition on a candidate solution that guarantees it actually solves the problem, without searching the whole…

11 thms3 active users
🏆Completed
ProbabilityRandom Matrix TheoryStatistics·Captain: mikedeng1

High-Dimensional Probability XI: Dvoretzky-Milman's TheoremTextbook

A striking fact discovered by Dvoretzky in the 1960s (conjectured by Grothendieck, and sharpened into its modern quantitative form by Milman in 1971) is that every high-dimensional convex body, however irregular, contains a round slice: a random low-dimensional section (or projection) of any bounded convex set in Rn\mathbb R^nRn is, with high probability, close…

9 thms3 active usersReviewed
🏆Completed
ProbabilityStatistics·Captain: mikedeng1

Support Vector Machines V: Bernstein's Inequality for Independent Hilbert-Space-Valued Random VariablesTextbook

Every statistical guarantee for a learning algorithm ultimately rests on a concentration inequality: a bound on how far an empirical average can stray from its expectation. For real-valued averages, Bernstein's inequality (1924, refined through the 20th century) is the classical tool — sharper than Hoeffding's inequality whenever the summands' variance is…

5 thms3 active usersReviewed
Convex OptimizationOptimization·Captain: mikedeng1

Introduction to Online Convex Optimization VI: Bandit Convex Optimization via Gradient EstimationTextbook

Every algorithm in Chapters I–V observes the full cost function ftf_tft​ after playing xtx_txt​. Many applications only reveal the scalar cost ft(xt)f_t(x_t)ft​(xt​) incurred — routing a network and observing total latency, or placing an ad and observing the click-through revenue, without ever seeing the cost of a path or bid not taken. This is the bandit feedback model, and…

10 thms3 active users
🏆Completed
Convex OptimizationOptimization·Captain: mikedeng1

Introduction to Online Convex Optimization V: RFTL and the Regret Bound of Follow-the-Regularized-LeaderTextbook

Online convex optimization (OCO) asks a learner to repeatedly pick a point in a convex set KKK, pay a cost that an adversary reveals only after the choice is made, and be judged against the best fixed point in hindsight. Chapter III of this series formalized the simplest general-purpose answer, online gradient descent (OGD): take a gradient step, project back…

6 thms3 active users
Reinforcement LearningStatistics·Captain: mikedeng1

Foundations of Reinforcement Learning V: General Decision Making and the Decision-Estimation Coefficient Lower BoundTextbook

Online decision-making problems — multi-armed bandits, contextual bandits, structured bandits, and episodic reinforcement learning — look superficially different but share a common shape: a learner repeatedly acts, observes feedback, and is scored by regret against the best action in hindsight. Foster, Kakade, Qian and Rakhlin's Foundations of Reinforcement…

20 thms3 active users
🏆Completed
Bandit AlgorithmsOperations Research·Captain: Shuze Chen

Bandit Algorithms I: Concentration of MeasureTextbook

How quickly does the empirical mean of independent random variables concentrate around the true mean? This question is the analytic engine of the entire theory of stochastic bandits: every optimistic algorithm (Explore-Then-Commit, UCB and its relatives) is calibrated by a tail bound on the sample mean. This mission formalizes the subgaussian framework of…

2 thms3 active usersReviewed
🏆Completed
Combinatorics·Captain: mikedeng1

The Optimal Sample Complexity of Multiclass and List LearningResearch Paper

In multiclass classification, a prediction rule assigns one label to each data point, and the set of possible labels may be infinite. Learning theory asks how much labeled data suffices to predict accurately on new points. The number of labels alone does not describe the difficulty of a hypothesis class. A useful complexity parameter must also distinguish…

12 thms2 active usersReviewed
Complexity TheoryInformation Theory·Captain: mikedeng1

Autoregressive Distribution Learning and Universal CompressionResearch Paper

Large language models are autoregressive: they predict the next symbol of a string given the previous ones. A good next-symbol predictor yields a good compressor by arithmetic coding, and it is folklore that "prediction is compression". Hirahara and Nanashima (STOC 2027 submission #793, October 2026) turn this into an exact complexity-theoretic equivalence.…

22 thms2 active usersReviewed
🏆Completed
ProbabilityStatistics·Captain: Shuze Chen

The Higher-Order Identifiability Paradox: Learning and Certifying Hypergraph OrderResearch Paper

Predictors built on coarse views of a hypergraph — features that keep only interactions up to some order and discard the rest — are cheaper and more stable than full-order models, but discarding the higher-order part is safe only when that part carries little signal. Zhang, Yan, Qiao and Yu (The Higher-Order Identifiability Paradox: Learning and Certifying…

15 thms2 active usersReviewed
Complexity TheoryComputational Complexity·Captain: Shuze Chen

The Complexity of ReLU Network Synthesis from a Parameter MultisetResearch Paper

Training a neural network usually means fixing an architecture and searching a continuous space of weights. A different question separates the numbers from the architecture: the parameter values are supplied in advance, as a finite multiset, and one asks whether some ReLU network with a bounded number of neurons can be wired up and have those numbers placed…

19 thms2 active usersReviewed
ProbabilityStatisticsTheoretical Computer Science·Captain: Shuze Chen

Understanding Model Misspecification in Low-Rank Distributions: Tolerant Testing and Agnostic LearningResearch Paper

Sequence models such as hidden Markov models, tensor trains and autoregressive language models define laws on strings of length TTT over a finite alphabet. A common measure of their complexity is the distribution rank: the largest rank of the matrices that pair every history with every future. Low-rank laws can be learned efficiently from conditional samples…

20 thms2 active usersReviewed
CombinatoricsProbabilityTheoretical Computer Science·Captain: Shuze Chen

The Margin Complexity of Maxima of Linear FunctionalsResearch Paper

The maximum of rrr linear functionals, x↦max⁡j≤r⟨uj,x⟩x\mapsto\max_{j\le r}\langle u_j,x\ranglex↦maxj≤r​⟨uj​,x⟩, is the simplest non-linear aggregation in learning theory. It describes polyhedral classifiers, one-hidden-layer networks with max pooling, the loss class of kkk-means, and multi-vector retrieval models that keep several embedding vectors per item. Its statistical complexity at a…

25 thms2 active usersReviewed
🏆Completed
ProbabilityStatistics·Captain: mikedeng1

Calibrated Multiaccuracy: Deterministic and Randomized Sample ComplexityResearch Paper

Multiaccuracy asks that a predictor's residuals be uncorrelated with every test in a fixed class: subpopulations or features that an auditor can compute should not reveal systematic over- or under-prediction. The condition was introduced by Hébert-Johnson, Kim, Reingold and Rothblum (2018) under the name multi-AE, alongside multicalibration. Calibration asks…

25 thms2 active usersReviewed
ProbabilityTheoretical Computer Science·Captain: mikedeng1

New Lower Bounds for Private PAC LearningResearch Paper

A learner trained on sensitive examples must control what its output reveals about any one record. Differential privacy imposes that control by comparing output probabilities when a single record changes. The resulting sample requirement can exceed the requirement for ordinary classification. A useful lower bound should explain which independent learning…

35 thms2 active usersReviewed
ProbabilityStatisticsTheoretical Computer Science·Captain: Shuze Chen

Sublinear Sample Size Suffices for Learning Mixtures of Gaussians up to IsometryResearch Paper

Learning a mixture of Gaussians from samples is a central problem of statistics and learning theory. For mixtures of kkk spherical Gaussians in Rd\mathbb R^dRd, proper density estimation in total variation needs Θ~(kd/ε2)\tilde\Theta(kd/\varepsilon^2)Θ~(kd/ε2) samples (Ashtiani, Ben-David, Harvey, Liaw, Mehrabian, Plan, J. ACM 2020), and the linear dependence on ddd cannot be…

21 thms2 active usersReviewed
Quantum InformationStatisticsTheoretical Computer Science·Captain: iris

Agnostic Product Mixed State Tomography via Robust StatisticsResearch Paper

Quantum state tomography asks for a classical description of an unknown state ρ\rhoρ from measurements on copies of it. Learning a general nnn-qubit state needs exponentially many copies, so one asks instead for the best approximation within a simple class. The agnostic version makes no assumption on ρ\rhoρ: the learner must compete with opt\mathrm{opt}opt, the…

32 thms2 active usersReviewed
Quantum InformationStatistics·Captain: iris

Finding Gaussian Structure in Bosonic StatesResearch Paper

Bosonic systems (optical modes, microwave cavities, motional modes of trapped ions) are described by states on Fock space, and the Gaussian states are the ones that standard optical hardware prepares most easily: squeezed, coherent and thermal states. They are fully described by a mean vector and a covariance matrix, and they can be learned from…

42 thms2 active usersReviewed
ProbabilityStatisticsTheoretical Computer Science·Captain: Shuze Chen

Achieving the Optimal Abstention Rate for Learning with Distribution ShiftResearch Paper

A classifier trained on one distribution is often deployed on data drawn from another. When nothing is assumed about the shift, no guarantee is possible on every test point, but a learner may abstain: it predicts on some test points and declines the rest. The question is then how few points it must decline while keeping its error low on the points it…

24 thms2 active usersReviewed
Harmonic AnalysisProbabilityTheoretical Computer Science·Captain: Shuze Chen

Efficient Non-Adaptive Sparse Fourier Learning on the Boolean Cube and Finite Abelian GroupsResearch Paper

Learning a real function on the Boolean cube from a few of its values is a basic task in computational learning theory, property testing and signal processing on {0,1}d\{0,1\}^d{0,1}d. Many functions in these areas are close to a combination of a few parities. When such a function is sampled only at chosen points, the natural goal is to find a short Fourier expansion…

15 thms2 active usersReviewed
ProbabilityStatisticsTheoretical Computer Science·Captain: Shuze Chen

Data-Dependent Probability Estimation via Sample AmplificationResearch Paper

A statistician observes nnn independent draws S=(X1,…,Xn)S=(X_1,\dots,X_n)S=(X1​,…,Xn​) from an unknown distribution DDD on a finite domain [d]={1,…,d}[d]=\{1,\dots,d\}[d]={1,…,d}, and is then asked about an event, or more generally a [0,1][0,1][0,1]-valued query, chosen by looking at the same sample. Such data-dependent questions arise whenever a dataset is explored before it is analysed: adaptive data analysis,…

22 thms2 active usersReviewed
PreviousPage 21 of 36Next

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