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
Functional AnalysisProbabilityStatistics·Captain: mikedeng1

Optimal Rates for the Regularized Least-Squares Algorithm I: With λ Tuned to the Effective Dimension, Regularized Least Squares Attains the Rate ℓ^(−bc/(bc+1)) Uniformly over P(b, c) (Theorem 1)Research Paper

Regularized least squares (RLS, also called kernel ridge regression or Tikhonov regularization) is the simplest learning algorithm built on a reproducing kernel Hilbert space. Given ℓ\ellℓ examples (xi,yi)(x_i,y_i)(xi​,yi​) drawn independently from an unknown distribution ρ\rhoρ, it returns the function in a hypothesis space H\mathcal HH that minimizes the empirical squared…

9 thms1 active userReviewed
🏆Completed
Captain: Minghui

DARE the Extreme: Output Concentration under Delta-Parameter PruningResearch Paper

A fine-tuned model can be stored as a pretrained model together with its parameter changes. Pruning these delta parameters reduces the amount of task-specific information to store. The DARE procedure independently deletes each change with probability ppp and multiplies every surviving change by 1/(1−p)1/(1-p)1/(1−p). This preserves the expected linear-layer output, but a…

6 thms1 active userReviewed
🏆Completed
Linear algebraProbability·Captain: Minghui

Fine-Tuning Can Distort Pretrained Features: Perfect-Feature LP-FT SeparationResearch Paper

Transfer learning starts with a representation learned on an earlier task and adapts it to a new one. Two common choices are linear probing, which changes only the final linear predictor, and fine-tuning, which changes the representation as well. These procedures optimize related training objectives, but their behavior away from the training data can…

9 thms1 active userReviewed
🏆Completed
Analysis·Captain: Minghui

Sharp Minima Can Generalize: ReLU Rescaling and Hessian SharpnessResearch Paper

A trained neural network is used through its predictions, while its parameters are the coordinates in which training takes place. Distinct parameter vectors can describe exactly the same prediction function. A proposed explanation of generalization based on the shape of the parameter-space loss therefore needs to account for these equivalences. This mission…

4 thms1 active userReviewed
🏆Completed
Probability·Captain: Minghui

Neural Tangent Kernel: The Infinite-Width Initialization LimitResearch Paper

A neural network is nonlinear in its parameters, but a small change in those parameters changes its predictions through a Jacobian. The neural tangent kernel is the Gram kernel of that Jacobian: it records which changes in predictions can be produced by common parameter updates. An initialization limit identifies a deterministic object behind this random…

4 thms1 active userReviewed
🏆Completed
OptimizationProbability·Captain: Minghui

Optimization Methods for Large-Scale Machine Learning: Stochastic Gradient ConvergenceResearch Paper

Training a machine-learning model often means choosing a vector of parameters to minimize an average loss. Evaluating the full gradient can require processing an entire dataset. A stochastic-gradient method instead updates the parameters using a random direction obtained from a smaller amount of information. Its computational appeal raises a mathematical…

6 thms1 active userReviewed
🏆Completed
OptimizationProbability·Captain: Minghui

SCAFFOLD: Convergence with Client SamplingResearch Paper

Federated optimization trains one model using objectives held by many clients. Performing several local updates between communication rounds saves communication, but clients with different objectives can move in different directions. SCAFFOLD maintains a correction for each client to address this disagreement, including when only some clients participate.…

6 thms1 active userReviewed
🏆Completed
Convex OptimizationProbability·Captain: Minghui

A Field Guide to Federated Optimization: Convex FedAvg ConvergenceResearch Paper

Federated optimization studies learning when data and computation are spread across clients. Communicating after every stochastic gradient step can be costly, so clients often take several steps before averaging their models. The difficulty is that different clients can optimize different objective functions. Their models then move apart between…

5 thms1 active userReviewed
🏆Completed
Harmonic AnalysisProbability·Captain: Elsie66

ClockRoPE: Random Fourier RotationsResearch Paper

Transformer sequence models modulate attention scores by a function of the relative position between a query and a key: the attention logit between token mmm and token nnn is scaled by a fixed profile f(pm−pn)f(p_m - p_n)f(pm​−pn​). Realizing this modulation the naive way means evaluating fff once per pair (m,n)(m,n)(m,n) and materializing an L×LL\times LL×L adjustment over the whole sequence —…

5 thms1 active userReviewed
🏆Completed
Number Theory·Captain: raver1975

The Alethean CatalogResearch Paper

This mission curates the formalized output of Alethean — an Autonomous Logic Engine for Theorem Hunting, Exploration, And Navigation (alethean.org). Alethean autonomously generates research directions, develops them into research papers, and formalizes their results in Lean 4 — an "ever-expanding registry of absolute mathematical truths," built with the Aris…

12 thms1 active userReviewed
🏆Completed
ProbabilityStatistics·Captain: willma

Don't Label Twice: Game, Set, MatchOpen Problem

(a) In a tennis match, you are the favorite, and win each point independently with probability q∈(1/2,1)q\in(1/2,1)q∈(1/2,1). Let n,mn,mn,m be odd positive integers greater than 111. You have the choice between playing a best-of-nmnmnm (i.e., you play nmnmnm points and whoever wins the majority of points wins the match), or a best-of-nnn of best-of-mmm's (i.e., the match is won by winning the…

39 thms1 active userReviewed
PreviousPage 36 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