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
OptimizationProbability·Captain: mikedeng1

Linear Convergence of Gradient and Proximal-Gradient Methods Under the Polyak-Łojasiewicz Condition III: Randomized Coordinate Descent Has Expected Rate (1 − μ/(dL))^kResearch Paper

Coordinate descent changes one component of a parameter vector at a time. This matters when evaluating or updating a single component is cheaper than handling the full vector, for example in problems with sparse features. The coordinate chosen at each step can be random or selected from the current gradient. Karimi, Nutini, and Schmidt study these choices…

7 thms3 active usersReviewed
🏆Completed
Convex OptimizationOptimization·Captain: mikedeng1

Linear Convergence of Gradient and Proximal-Gradient Methods Under the Polyak-Łojasiewicz Condition II: SC → ESC → WSC → RSI → EB ≡ PL → QG, and RSI ≡ EB ≡ PL ≡ QG for Convex fResearch Paper

Gradient descent on a smooth function f:Rd→Rf:\mathbb R^d\to\mathbb Rf:Rd→R converges at a linear rate (the optimality gap shrinks by a constant factor each step) under strong convexity. Many problems in machine learning and statistics are not strongly convex: least squares with a rank-deficient design, logistic regression on separable or degenerate data, and some…

12 thms3 active usersReviewed
🏆Completed
Optimization·Captain: mikedeng1

Linear Convergence of Gradient and Proximal-Gradient Methods Under the Polyak-Łojasiewicz Condition I: Gradient Descent with Step 1/L Satisfies f(x_k) − f* ≤ (1 − μ/L)^k (f(x_0) − f*)Research Paper

Gradient descent is often introduced with strong convexity as the condition that gives a geometric reduction in objective error. That condition excludes useful smooth objectives whose minimizer is not unique and some nonconvex objectives. Karimi, Nutini, and Schmidt place the Polyak–Łojasiewicz inequality at the center of a more general account: it controls…

5 thms3 active usersReviewed
🏆Completed
OptimizationProbability·Captain: mikedeng1

Linear Convergence of Gradient and Proximal-Gradient Methods Under the Polyak-Łojasiewicz Condition IV: Stochastic Gradient Rates LC²/(2kμ²) and (1 − 2μα)^k [f(x_0) − f*] + LC²α/(4μ)Research Paper

Stochastic gradient (SG) methods are the default algorithms for training machine-learning models: when an objective is an average over a very large number of training examples, computing its full gradient even a few times is infeasible, while the gradient of a single randomly chosen example is cheap. The classical convergence theory of SG rates its expected…

7 thms3 active usersReviewed
🏆Completed
Bandit AlgorithmsReinforcement Learning·Captain: mikedeng1

The Statistical Complexity of Interactive Decision Making VII: Policy-Cover Inverse Gap Weighting Certifies dec_γ ≤ 95H³SA/γ for Tabular Reinforcement LearningResearch Paper

In episodic reinforcement learning, an agent learns the rewards and dynamics of a system while choosing actions that determine which states it observes. A bound on the number of states and actions alone does not prescribe how to explore: a policy can be valuable because it earns reward, because it visits an uncertain state-action pair, or both. Foster,…

16 thms3 active usersReviewed
🏆Completed
Bandit AlgorithmsReinforcement Learning·Captain: mikedeng1

The Statistical Complexity of Interactive Decision Making VI: Posterior Sampling Bounds the Dual DEC of Tabular Reinforcement Learning by 26H²SA/γResearch Paper

In episodic reinforcement learning, an agent acts repeatedly in an unknown system and must learn which policy earns the largest expected reward. Even when states and actions are finite, the agent's choices change which data it observes. Foster, Kakade, Qian, and Rakhlin use the decision-estimation coefficient (DEC) to connect this information constraint to…

12 thms3 active usersReviewed
🏆Completed
Reinforcement LearningStatistics·Captain: mikedeng1

The Statistical Complexity of Interactive Decision Making IV: Log-Loss Regret Controls Hellinger Estimation Error, Est_H ≤ Reg_KL + 2 log(1/δ) with Probability 1−δResearch Paper

Interactive decision methods often need an estimate of an unknown outcome law after each round. A learner can be good at decisions only if its model of the observations is accurate where future decisions will sample. Foster, Kakade, Qian and Rakhlin measure this accuracy by a cumulative squared Hellinger distance and use it in their regret bounds for…

12 thms3 active users
🏆Completed
OptimizationProbability·Captain: mikedeng1

Certifying Some Distributional Robustness with Principled Adversarial Training 1: SGD on the Wasserstein Penalty Surrogate Finds an Approximate Stationary Point at Rate 4σ√(L_φΔ_F/T)Research Paper

Neural networks trained by empirical risk minimization are sensitive to small, deliberately chosen perturbations of their inputs ("adversarial examples"). A standard defence is adversarial training: at each step, perturb the training example to increase the loss, then take a gradient step at the perturbed point. Sinha, Namkoong, Volpi and Duchi (arXiv:1710.1…

10 thms3 active usersReviewed
🏆Completed
Bandit AlgorithmsInformation TheoryOperations Research·Captain: mikedeng1

Regret in Online Combinatorial Optimization II: Under Bandit Feedback Every Strategy Has Minimax Regret at Least 0.02 m√(dn) on Some Set of Actions with m OnesResearch Paper

An online player repeatedly chooses a subset of coordinates and pays the sum of their losses. In many applications the player sees only that sum, not the losses of the selected coordinates. This bandit feedback makes it harder to identify which coordinate within each chosen subset is responsible for a favorable or unfavorable outcome. Audibert, Bubeck and…

13 thms3 active usersReviewed
🏆Completed
Operations ResearchOptimizationProbability·Captain: mikedeng1

Stochastic First- and Zeroth-Order Methods for Nonconvex Stochastic Programming 1: The Randomized Stochastic Gradient Method Has (1/L)E‖∇f(x_R)‖² ≤ (D_f² + σ²Σγ_k²)/Σ(2γ_k − Lγ_k²)Research Paper

Stochastic gradient methods are the standard tool for minimizing an objective that can only be accessed through noisy gradient samples. Training a machine-learning model on sampled data, simulation-based optimization, and stochastic programs with endogenous uncertainty are all of this kind. In many of these applications the objective is nonconvex: the loss…

13 thms3 active usersReviewed
🏆Completed
Operations ResearchOptimal TransportOptimization·Captain: mikedeng1

Wasserstein Distributionally Robust Optimization and Variation Regularization II: The ∞-Wasserstein Regularizer Equals ρ Times the Mean Local Slope up to ρ²‖H‖ Plus a Boundary TermResearch Paper

In distributionally robust optimization, a decision is judged against probability laws near a nominal law rather than against the nominal law alone. The nominal law is often the empirical distribution of observed data. For a loss function, this produces a worst-case expected loss that depends on the size and geometry of the permitted changes to the data.…

10 thms3 active usersReviewed
🏆Completed
Algebraic TopologyComputational GeometryProbability·Captain: mikedeng1

Persistence-Based Clustering in Riemannian Manifolds: With High Probability the Algorithm Returns as Many Clusters as the Density Has d₂-Prominent PeaksResearch Paper

Mode-seeking clustering groups data points by the peak of an underlying probability density that they "flow up" to. Methods of this kind (mean-shift, graph-based hill climbing) are widely used, but their output depends heavily on noise: a density estimated from finitely many samples has many spurious local maxima, and each of them becomes a cluster. Chazal,…

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

Incremental Proximal Methods for Large Scale Convex Optimization I: With a Cyclic Order and a Diminishing Stepsize, Incremental Subgradient-Proximal Methods Converge to an Optimal SolutionResearch Paper

Many optimization problems in machine learning, signal processing and distributed computation have an objective that is a sum of a large number mmm of component functions: one per data point, per sensor, or per processor. Evaluating the whole sum, or a subgradient of it, at every iteration is expensive when mmm is large. Incremental methods process one…

10 thms3 active usersReviewed
🏆Completed
Bandit Algorithms·Captain: mikedeng1

An Optimal Algorithm for Stochastic and Adversarial Bandits II: α-Tsallis-INF With Symmetric Regularization Has Anytime Adversarial Pseudo-Regret 2√(min{1/(α−α²), log K/α, log T/(1−α)}·KT) + 1Research Paper

In the adversarial multi-armed bandit problem a learner repeatedly picks one of KKK arms and observes only the loss of the arm it picked, while an adversary chooses the losses, possibly reacting to the learner's past choices. The minimax pseudo-regret of this problem is of order KT\sqrt{KT}KT​ after TTT rounds, and the classical algorithm Exp3 achieves only …

9 thms3 active usersReviewed
🏆Completed
Optimal TransportOptimization·Captain: mikedeng1

Computational Optimal Transport XII: The Entropic Barycenter Scalings Are (e^{f_s/ε}, e^{g_s/ε}) for the Solutions of a Dual Program with Σ_s λ_s f_s = 0Textbook

A barycenter summarizes several objects by minimizing a weighted sum of distances to them. For probability histograms, ordinary coordinatewise averages depend strongly on how the bins are labeled. Optimal transport instead lets mass move between bins and charges for those moves through a cost matrix. The resulting Wasserstein barycenter can reflect the…

6 thms3 active usersReviewed
🏆Completed
Information TheoryOptimal TransportOptimization·Captain: mikedeng1

Computational Optimal Transport IX: The Entropic Cost L^ε_C(a, b) Equals max ⟨f, a⟩ + ⟨g, b⟩ − ε⟨e^{f/ε}, K e^{g/ε}⟩, with Optimal Scalings (e^{f/ε}, e^{g/ε})Textbook

Optimal transport compares two distributions by finding the least expensive way to move mass between them. For finite histograms, the resulting linear program is precise but its optimal coupling can be sparse. In applications where the coupling represents traffic, matching, or a differentiable loss, a sparse plan may be undesirable or expensive to compute…

9 thms3 active users
🏆Completed
Information TheoryOptimal TransportOptimization·Captain: mikedeng1

Computational Optimal Transport VII: The Entropic Optimal Coupling P_ε Tends to the Maximum-Entropy Optimal Plan as ε → 0 and to a ⊗ b as ε → ∞Textbook

The discrete optimal transport problem of Kantorovich asks for the cheapest way to move a probability histogram a\mathbf aa onto a histogram b\mathbf bb when moving a unit of mass from iii to jjj costs Ci,j\mathbf C_{i,j}Ci,j​. Its optimal couplings are vertices of a polytope and are typically sparse: they rely on a few routes. Two communities have reasons to blur them. In…

7 thms3 active usersReviewed
🏆Completed
Bandit Algorithms·Captain: mikedeng1

An Optimal Algorithm for Stochastic and Adversarial Bandits I: Tsallis-INF Has Square-Root Adversarial Pseudo-Regret and Logarithmic Pseudo-Regret Under a Self-Bounding ConstraintResearch Paper

A multi-armed bandit learner repeatedly chooses one of several actions, observes only the loss of the chosen action, and tries to perform nearly as well as a single fixed action selected in hindsight. Two common loss models make different demands on the learner. In a stochastic model, each arm has a stable mean loss and the learner can gradually distinguish…

10 thms3 active usersReviewed
🏆Completed
Bandit AlgorithmsInformation TheoryProbability·Captain: mikedeng1

A Tutorial on Thompson Sampling I: Any Algorithm Whose Information Ratio Is at Most Γ̄ Has Expected Regret at Most √(Γ̄·H(x*)·T)Research Paper

Thompson sampling (TS) chooses each action with the posterior probability that it is optimal. Its practical success in online advertising, recommendation and experimentation raised the question of why it works and when it does not. The tutorial of Russo, Van Roy, Kazerouni, Osband and Wen (Found. Trends Mach. Learn. 11(1), 2018) answers part of that…

9 thms3 active users
🏆Completed
Operations ResearchOptimal TransportOptimization·Captain: mikedeng1

Regularization via Mass Transportation I: Wasserstein-Robust Linear Classification with Label Flipping Is a Finite Convex ProgramResearch Paper

A classifier trained from finitely many examples can perform well on those examples while responding poorly to changes in the feature distribution or to mislabeled observations. Distributionally robust learning addresses this by choosing a classifier against every probability distribution within a specified distance of the empirical distribution. The…

9 thms3 active usersReviewed
🏆Completed
Convex OptimizationOptimization·Captain: mikedeng1

Revisiting Frank-Wolfe: Projection-Free Sparse Convex Optimization 1: All Four Frank-Wolfe Variants Reach Duality Gap ≤ 2βC_f(1+δ)/(K+2), β = 27/8, Within K IterationsResearch Paper

The Frank–Wolfe method, also called the conditional-gradient method, minimizes a smooth convex objective over a compact convex set while asking only for a minimizer of a linear function over that set. In domains where a linear optimization oracle is easier than a projection, this distinction changes which algorithms are practical. Examples in Jaggi's paper…

5 thms3 active usersReviewed
🏆Completed
Convex OptimizationOptimization·Captain: mikedeng1

Stochastic Dual Coordinate Ascent Methods for Regularized Loss Minimization 2: With (1/γ)-Smooth Losses, SDCA Reaches Expected Duality Gap ε after (n + 1/(λγ))·log((n + 1/(λγ))/ε) IterationsResearch Paper

Regularized loss minimization (training a linear predictor with a convex loss and an ℓ2\ell_2ℓ2​ penalty) covers support vector machines, ridge and logistic regression, and much of classical linear learning. A standard way to solve these problems at scale is dual coordinate ascent: optimize the dual problem one coordinate, i.e. one training example, at a time.…

12 thms3 active usersReviewed
🏆Completed
CombinatoricsProbabilityTheoretical Computer Science·Captain: mikedeng1

A Learning Theory Approach to Non-Interactive Database Privacy 2: An ε-Differentially Private Mechanism Useful on Databases of Size at Most VCDIM(C)/2 Has Error α ≥ Ω(1/(4+16ε))Research Paper

A data curator holds a database of nnn records and wants to publish answers to a large family of statistical questions about it without revealing any individual record. Differential privacy (Dwork, McSherry, Nissim, Smith 2006) makes the requirement precise, and the most basic questions are counting queries: what fraction of the records satisfy a given…

9 thms3 active usersReviewed
🏆Completed
Convex OptimizationOptimization·Captain: mikedeng1

Online Learning and Online Convex Optimization 1: Follow-the-Regularized-Leader with a σ-Strongly-Convex Regularizer Has Regret at Most R(u) − min R + TL²/σResearch Paper

Online convex optimization is a repeated game between a learner and an environment. In each round the learner commits to a vector, the environment then reveals a convex loss function, and the learner pays the loss of its vector. No statistical assumption is made about how the losses are generated; they may be chosen adversarially. Performance is measured…

8 thms3 active usersReviewed
🏆Completed
Convex OptimizationOptimization·Captain: mikedeng1

Making Gradient Descent Optimal for Strongly Convex Stochastic Optimization 2: For F Smooth at the Optimum, SGD's Last and Averaged Iterates Attain 2µG²/(λ²T) and 16µG²/(λ²T)Research Paper

Stochastic gradient descent (SGD) is the standard method for minimizing an expected loss F(w)=Ez[ℓ(w,z)]F(w) = \mathbb E_z[\ell(w, z)]F(w)=Ez​[ℓ(w,z)] when only noisy gradients are available: in machine learning, www is a predictor, zzz a random example, and each step uses the gradient of the loss on one fresh example. When FFF is strongly convex, as for regularized learning problems such as…

9 thms3 active usersReviewed
PreviousPage 11 of 22Next

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