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
Algorithmic Game TheoryMechanism DesignOperations Research·Captain: iris

Liquid Welfare Guarantees for No-Regret Learning in Sequential Budgeted Auctions: γ-Competitive Buyers in First-Price Auctions Get Liquid Welfare ≥ (LW* − O(n)(Reg+1))/(γ + 1/2 + O(1/γ))Research Paper

Most online advertising is sold through sequential auctions: one impression at a time, millions of times a day, and since 2019 increasingly by first-price rules (Won21). The advertisers who bid are budget-constrained, and they do not compute equilibria; their bids are set by learning algorithms that adjust a shading or pacing multiplier from round to round.…

27 thms2 active usersReviewed
Operations ResearchProbability·Captain: iris

The Nonstationary Newsvendor with (and without) Predictions: The Prediction-Error-Robust Policy Achieves Regret Õ(T^min{(3+v)/4, a}) Without Knowing the Prediction AccuracyResearch Paper

Retailers, hospitals and data-center operators repeatedly decide how much to stock before demand is seen, and in practice the demand distribution drifts over time while external predictions of its mean (human judgement, forecasting software, machine-learned models) are available but of unknown quality. The newsvendor problem is the classical model of a…

26 thms2 active usersReviewed
Algorithmic Game TheoryOperations ResearchOptimization+1·Captain: iris

Multi-Agent Online Learning in Time-Varying Games: Mirror Descent Converges Almost Surely to the Nash Equilibrium of a Strictly Monotone Limit GameResearch Paper

Many systems in which several agents repeatedly make continuous decisions are modelled as games whose rules drift over time: bidders in repeated Kelly auctions whose valuations change with traffic, wireless users whose channel gains fluctuate, firms in Cournot markets with shifting demand. In such settings agents rarely know the game they are playing; they…

17 thms2 active usersReviewed
Operations ResearchReinforcement LearningStatistics·Captain: iris

Fast Rates for the Regret of Offline Reinforcement Learning: Under the Margin Condition, the Greedy Policy of a Q*-Estimate with Uniform Sub-Gaussian Error at Rate aₙ Has Regret O(aₙ^(1+α))Research Paper

Offline reinforcement learning asks for a good policy in a Markov decision process using only logged transitions, without further interaction. A common family of methods (fitted QQQ-iteration, Bellman residual minimization) first estimates the optimal action-value function Q∗Q^*Q∗ by some f^\hat ff^​ and then acts greedily with respect to f^\hat ff^​. Standard analyses…

11 thms2 active usersReviewed
OptimizationStatistics·Captain: iris

Distributionally Robust Losses for Latent Covariate Mixtures: The Marginal DRO Estimator Nearly Minimizes the LpL^pLp Bound on Worst-Case Subpopulation RiskResearch Paper

A model trained to minimize average loss can perform badly on a subpopulation: a minority group in a language corpus, or a demographic underrepresented in a medical or vision dataset. Marginal distributionally robust optimization asks for good performance on every sufficiently large subpopulation of the covariates, without knowing which subpopulations…

27 thms2 active usersReviewed
Numerical AnalysisOptimization·Captain: iris

Recursive Importance Sketching for Rank Constrained Least Squares: Algorithms and High-Order Convergence: RISRO Converges Quadratic-Linearly to a Rank-rrr Stationary Point under 2r2r2r-RIPResearch Paper

Many estimation problems ask for a low-rank matrix that fits linear measurements: matrix sensing, matrix completion, phase retrieval, blind deconvolution, and system identification among them. The common core is rank constrained least squares, a non-convex problem that also underlies low-rank recovery theory (Recht, Fazel and Parrilo, 2010). The problem is…

30 thms2 active usersReviewed
Convex OptimizationOperations ResearchOptimization·Captain: iris

On the Efficient Implementation of the Matrix Exponentiated Gradient Algorithm for Low-Rank Matrix Optimization: Low-Rank MEG Converges at Rate O(1/T) from a Warm Start under Strict ComplementarityResearch Paper

Many low-rank recovery problems in machine learning and statistics, among them matrix completion, robust PCA and phase retrieval, are relaxed to convex optimization over the spectrahedron, the set of positive semidefinite matrices of unit trace. On this set Matrix Exponentiated Gradient (MEG), the mirror descent method for the von Neumann entropy, has the…

39 thms2 active usersReviewed
Operations ResearchProbabilityReinforcement Learning·Captain: iris

Self-guided Approximate Linear Programs: With Probability ≥ 1 − δ, H Further Random Bases Give a FALP-Feasible VFA Within E(N,H) of V* in Sup-Norm and E(N,H)-Feasible for Guiding ConstraintsResearch Paper

Approximate linear programming computes a value function approximation (VFA) for a discounted-cost Markov decision process by maximizing a weighted average of the VFA subject to the Bellman inequalities (De Farias and Van Roy, 2003). The method needs a set of basis functions, and the choice of those functions is a recurring difficulty in operations research…

40 thms2 active usersReviewed
Algorithmic Game TheoryOperations ResearchProbability·Captain: iris

Policy Learning with Competing Agents: The Finite-Agent Stochastic Threshold Iteration Reaches a λ-Neighborhood of the Mean-Field Equilibrium Threshold with Probability at Least 1 − δResearch Paper

A decision maker with limited capacity (a college admitting students, a lender approving loans) treats only the 1−q1-q1−q fraction of applicants with the highest score βTX\beta^TXβTX. The applicants know the rule and invest effort to change their covariates XXX, so the score distribution, and hence the admission threshold, depends on the rule itself. When the rule is…

20 thms2 active usersReviewed
Bandit AlgorithmsOperations ResearchStatistics·Captain: iris

A Simple and Optimal Policy Design with Safety Against Heavy-Tailed Risk for Stochastic Bandits: SE and UCB Have O(KTln⁡T)O(\sqrt{KT\ln T})O(KTlnT​) Regret and an e−Ω(x/KT)e^{-\Omega(x/\sqrt{KT})}e−Ω(x/KT​) Regret TailResearch Paper

Stochastic multi-armed bandit policies are judged almost always by their expected regret. In operations settings such as dynamic pricing, assortment testing or clinical allocation, a decision maker also cares about the probability of a bad outcome: a policy whose regret is small on average can still incur regret linear in the horizon TTT with non-negligible…

21 thms2 active usersReviewed
Bandit AlgorithmsOperations Research·Captain: iris

Shrinking the Upper Confidence Bound: A Dynamic Product Selection Problem for Urban Warehouses: ConsUCB Has Regret at Most K + αK + 10α√(dKT log(KT)) with Probability at Least 1 − δResearch Paper

An online retailer choosing which low-demand products to display, and to stock in its urban warehouses, faces an unusual learning problem. Thousands of products must be chosen at once, the selection can change only a few times per season, and sales data arrive only for the products that were offered. Jin, Simchi-Levi, Wang, Wang and Yang (arXiv:1903.07844v2)…

19 thms2 active usersReviewed
Mechanism DesignOperations Research·Captain: iris

Stateful Posted Pricing with Vanishing Regret via Dynamic Deterministic Markov Decision Processes: Some Posted Price Mechanism Has Regret O(T^{(1+CW/(CW+1))/2}·√log|Γ|) on Every DRACC InstanceResearch Paper

A seller who allocates resources that appear and expire over time (machine slots in a cloud, rooms on given nights, edges of a matching market that change from round to round) often cannot run an auction for every user. A posted price mechanism announces prices before the user arrives and lets the user buy her preferred bundle; it is truthful for myopic…

20 thms2 active usersReviewed
Bandit AlgorithmsGraph TheoryProbability·Captain: iris

Small-Loss Bounds for Online Learning with Partial Information: Double-Threshold Freezing has ϵ\epsilonϵ-approximate regret ≤300α(A(d,T)+3log⁡d+2δ)/ϵ2\le 300\alpha(A(d,T)+3\log\frac{d+2}{\delta})/\epsilon^2≤300α(A(d,T)+3logδd+2​)/ϵ2 w.p. 1−δ1-\delta1−δResearch Paper

In adversarial online learning a learner chooses one of ddd actions (arms) in each of TTT rounds and suffers a loss in [0,1][0,1][0,1]. Classical regret bounds grow with the horizon, O(Tlog⁡d)O(\sqrt{T\log d})O(Tlogd​). A small-loss bound replaces TTT by the loss L⋆L^\starL⋆ of the best arm, which matters whenever good actions exist: routing traffic, choosing treatments, recommending items.…

12 thms2 active usersReviewed
Algorithmic Game TheoryMechanism DesignOperations Research·Captain: iris

Learning to Persuade on the Fly: Robustness Against Ignorance: The Rai Algorithm Has O(√(T log T)) Regret with High ProbabilityResearch Paper

In Bayesian persuasion a sender who observes a random state commits to a rule that maps states to recommendations, and a receiver who knows the state distribution follows a recommendation only when it is optimal given what it reveals (Kamenica and Gentzkow 2011; Bergemann and Morris 2019). When the distribution is known, the sender's best rule solves a…

33 thms2 active usersReviewed
Bandit AlgorithmsInformation Theory·Captain: iris

Satisficing in Time-Sensitive Bandit Learning: Every Policy's Discounted Satisficing Regret Is at Most Γ(A~,ψ) I(A~;θ)/(1−α2)\sqrt{\Gamma(\tilde A,\psi)\,I(\tilde A;\theta)/(1-\alpha^2)}Γ(A~,ψ)I(A~;θ)/(1−α2)​Research Paper

Bayesian bandit algorithms such as Thompson sampling are analyzed through the information ratio: the squared expected shortfall of a period divided by the information the period's observation reveals about the optimal action A∗A^*A∗ (Russo & Van Roy 2016). That analysis bounds regret by Γ H(A∗) T\sqrt{\Gamma\, H(A^*)\, T}ΓH(A∗)T​, where H(A∗)H(A^*)H(A∗) is the entropy of the optimal…

18 thms2 active usersReviewed
StatisticsTheoretical Computer Science·Captain: iris

Statistical Query Algorithms for Mean Vector Estimation and Stochastic Convex Optimization: ℓ_q Mean Estimation for 1 < q < 2 to Error ε with 2d log d Queries to VSTAT((16 log d/ε)^p)Research Paper

The statistical query (SQ) model describes algorithms that never see individual samples of a distribution DDD; they only ask for approximate expectations Ew∼D[ϕ(w)]\mathbf E_{w\sim D}[\phi(w)]Ew∼D​[ϕ(w)] of functions ϕ\phiϕ of their choice. It was introduced by Kearns for noise-tolerant learning (Kearns 1998), and it has since become the standard abstraction for algorithms that can…

24 thms2 active usersReviewed
Operations ResearchOptimizationProbability+1·Captain: iris

Scalable Reinforcement Learning for Multi-Agent Networked Systems: High-Probability Stationarity Bound for Scalable Actor Critic with κ\kappaκ-Hop Truncated Q-FunctionsResearch Paper

Many control problems are posed on networks of agents that each see only a local state and take a local action: traffic signals at intersections, wireless transmitters sharing a channel, nodes of an epidemic or a power grid. Treated as one Markov decision process, such a system has a state space whose size is exponential in the number of agents nnn, so…

22 thms2 active usersReviewed
Dynamic ProgrammingReinforcement Learning·Captain: iris

Foundations of Reinforcement Learning XVII: LSVI-UCB Has Regret ≲Hd3Tlog⁡(HT/δ)log⁡(1+T/d)\lesssim H\sqrt{d^3 T\log(HT/\delta)\log(1+T/d)}≲Hd3Tlog(HT/δ)log(1+T/d)​ in Low-Rank MDPsTextbook

In episodic reinforcement learning a learner interacts with an unknown Markov decision process for TTT episodes of HHH steps and is measured by its regret: the total shortfall of the value of the policies it plays against the value of an optimal policy. For tabular problems, where states and actions are few, optimism-based algorithms such as UCB-VI reach regret…

10 thms2 active usersReviewed
Bandit AlgorithmsReinforcement Learning·Captain: iris

Foundations of Reinforcement Learning XI: Generalized UCB Has Regret Controlled by the Eluder DimensionTextbook

A structured bandit is a repeated decision problem in which a learner picks a decision πt\pi^tπt from a set Π\PiΠ and observes a noisy reward. The set Π\PiΠ can be large or continuous: a dosage, a price vector, a path in a graph. Treating each decision separately costs regret of order ∣Π∣T\sqrt{|\Pi|T}∣Π∣T​, which is useless when Π\PiΠ is large relative to the horizon TTT. The…

22 thms2 active usersReviewed
Bandit AlgorithmsReinforcement LearningStatistics·Captain: iris

Foundations of Reinforcement Learning XV: A Family Embedding the Multi-Armed Bandit Forces the Constrained DEC to Be ≳ αTextbook

In interactive decision making a learner repeatedly picks a decision π\piπ from a decision space Π\PiΠ, receives a reward and an observation drawn from an unknown model M⋆M^\starM⋆, and is judged by its regret against the best decision of M⋆M^\starM⋆. Foster and Rakhlin's lecture notes (arXiv:2312.16730) organize the whole theory around one complexity measure, the Decis…

14 thms2 active usersReviewed
Computational Complexity·Captain: Shuze Chen

Training a 3-node neural network is NP-complete: NP-completeness of exact training on Boolean inputsResearch Paper

Training a classifier asks for parameters that fit observed examples. Even when the data can be classified perfectly, the task of finding suitable parameters can have substantial computational cost. The question here concerns exact training: deciding whether any parameter choice makes zero mistakes on the entire supplied data set. It concerns computation on…

7 thms2 active usersReviewed
ProbabilityStatistics·Captain: Shuze Chen

Towards Optimal Problem Dependent Generalization Error Bounds in Statistical Learning Theory: Variance-dependent generalization for moment penalizationResearch Paper

A learning procedure chooses a hypothesis from observed data, but its quality is determined by performance on future observations. A uniform bound based only on the largest possible loss can obscure a useful feature of a problem: a population-optimal hypothesis may have much smaller loss variance than the worst-case envelope suggests. Variance-dependent…

13 thms2 active usersReviewed
🏆Completed
CombinatoricsGraph TheoryOperations Research·Captain: mikedeng1

Correlation Clustering: Algorithm Cautious Is a Constant-Factor Approximation for Minimizing DisagreementsResearch Paper

In many clustering tasks the data come as pairwise judgements rather than as points in a metric space: a classifier says, for each pair of documents, whether they refer to the same entity or not. Correlation clustering asks for a partition that agrees with as many of these judgements as possible, without fixing the number of clusters in advance. The problem…

12 thms2 active usersReviewed
Bandit AlgorithmsOperations ResearchProbability·Captain: mikedeng1

Robust Dynamic Assortment Optimization in the Presence of Outlier Customers: Active Elimination Has TOTE Regret O(ε̄K²T log T + (K²√ε̄ + √K)√(NT log³T) + K²N log²T) Under ε-ContaminationResearch Paper

A retailer that learns customer preferences online, for example an e-commerce platform choosing which products to display, observes purchases that are not all generated by the population it is trying to learn. Some arrivals are bots, fraudulent accounts or atypical buyers, and their choices can be arbitrary or deliberately misleading. Standard learning…

10 thms2 active usersReviewed
🏆Completed
EconomicsOperations Research·Captain: mikedeng1

Decision Forest: A Nonparametric Approach to Modeling Irrational Choice: Every Customer Choice Model Is a Decision Forest of Depth at Most N + 1Research Paper

Retailers, airlines and platforms decide which products to offer by predicting how customers substitute among them. Such predictions rest on a discrete choice model: for every set of offered products, a probability distribution over what a customer buys. The classical models are built on random utility maximization (RUM): each customer draws utilities and…

7 thms2 active usersReviewed
PreviousPage 24 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