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
OptimizationStatistics·Captain: mikedeng1

Additive Logistic Regression: A Statistical View of Boosting 3: Population LogitBoost Takes Newton Steps on the Binomial Log-LikelihoodResearch Paper

Boosting combines many weak classifiers into a strong one by refitting, round after round, to a reweighted version of the training data. Freund and Schapire's AdaBoost was introduced as a procedure, with guarantees on the training error, and for several years it was not clear what statistical model it fitted. Friedman, Hastie and Tibshirani (Ann. Statist.…

8 thms3 active usersReviewed
Markov ChainProbabilityReinforcement Learning·Captain: mikedeng1

An Analysis of Temporal-Difference Learning with Function Approximation 2: For Every Sampling Distribution q and 5/6 < α < 1, Off-Line q-Sampled TD(0) Can Diverge in ExpectationResearch Paper

Temporal-difference learning estimates the future cost of a system from observed transitions. In a Markov model, a state has a distribution of possible successors and each transition carries a cost. An agent may approximate the future cost with a small number of basis functions rather than store one number per state. This is useful when the state set is…

9 thms3 active usersReviewed
🏆Completed
ProbabilityStatistics·Captain: mikedeng1

Consistent Nonparametric Regression III: Consistent Probability Weights Give Consistent Estimators of Conditional Quantiles (Theorem 3)Research Paper

Many prediction tasks ask not for the mean of a response YYY given covariates XXX but for a quantile of its conditional distribution: a median that is robust to outliers, a high quantile that sets a safety stock or a value at risk, or a pair of quantiles that forms a prediction interval. Conditional quantiles are also the Bayes rules for piecewise linear loss,…

8 thms3 active usersReviewed
🏆Completed
Operations ResearchTheoretical Computer Science·Captain: mikedeng1

The Weighted Majority Algorithm 4: The Continuous Master WMC Has Total Absolute Loss at Most ln(w_init/w_fin)/(1−β)Research Paper

In sequential prediction, several forecasters can issue different answers for the same instance. A master algorithm must combine their advice before the true label is known. Littlestone and Warmuth's Weighted Majority framework gives worst-case guarantees for this setting: the instances and labels need not come from a probability distribution. The paper…

6 thms3 active usersReviewed
ProbabilityStatistics·Captain: mikedeng1

Fast Rates for Support Vector Machines Using Gaussian Kernels 1: Under Tsybakov and Geometric Noise, Gaussian-Kernel SVMs Reach Excess Risk Cx²n^{−β+ε} with Probability 1 − e^{−x}Research Paper

Support vector machines classify observations by choosing a real-valued function from a reproducing kernel Hilbert space and using its sign as the predicted label. The Gaussian kernel is widely used because it gives a flexible class of functions, but that flexibility alone does not explain how quickly classification error approaches the best possible error…

11 thms3 active usersReviewed
🏆Completed
ProbabilityStatistics·Captain: mikedeng1

Fast Rates for Support Vector Machines Using Gaussian Kernels 2: An Envelope of Order γ and Tsybakov Noise Exponent q Give Geometric Noise Exponent (q+1)γ/dResearch Paper

A binary classifier is learned from a sample of a distribution PPP on X×{−1,1}X \times \{-1, 1\}X×{−1,1}, and its quality is measured by its excess classification risk over the Bayes classifier. Without assumptions on PPP no learning method converges at a uniform rate, so every rate theorem rests on a condition that describes how hard PPP is. Two such conditions are standard: Tsy…

9 thms3 active usersReviewed
🏆Completed
Operations ResearchOptimization·Captain: mikedeng1

Smart "Predict, then Optimize": Under a Continuous, Centrally Symmetric Cost Law Every Minimizer of the SPO+ Risk Equals E[c|x] and Minimizes the SPO RiskResearch Paper

Many decisions are made before their objective coefficients are known. A planner may know the feasible decisions and the form of a linear optimization problem, but must predict its cost vector from available features. Squared prediction error measures how close a forecast is to the eventual coefficients; it need not measure the quality of the decision…

10 thms3 active usersReviewed
OptimizationProbabilityStatistics·Captain: mikedeng1

Learning Models with Uniform Performance via Distributionally Robust Optimization 1: The Plug-In Cressie–Read Robust Risk Concentrates at Rate n^(−1/(k*∨2))·√(t + log n) (Theorem 2)Research Paper

A model trained to minimize its average loss EP0[ℓ(θ;X)]\mathbb E_{P_0}[\ell(\theta;X)]EP0​​[ℓ(θ;X)] can perform poorly on subpopulations that are rare under the training distribution P0P_0P0​. Distributionally robust optimization replaces the average loss by its worst case over all distributions QQQ close to P0P_0P0​ in an fff-divergence, which upweights the tail of the loss and controls…

12 thms3 active usersReviewed
🏆Completed
OptimizationReinforcement Learning·Captain: mikedeng1

On the Theory of Policy Gradient Methods: Optimality, Approximation, and Distribution Shift 4: Log-Barrier-Regularized Softmax Policy Gradient Is ε-Optimal After 320|S|²|A|²D∞²/((1−γ)⁶ε²) StepsResearch Paper

Policy gradient methods search directly over parameterized policies of a Markov decision process (MDP) by gradient ascent on the expected discounted reward. They are among the most widely used methods in reinforcement learning, yet the value Vπθ(ρ)V^{\pi_\theta}(\rho)Vπθ​(ρ) is a nonconcave function of the parameters, and until recently little was known about whether,…

20 thms3 active usersReviewed
🏆Completed
Bandit AlgorithmsOperations ResearchProbability·Captain: mikedeng1

MNL-Bandit: A Dynamic Learning Approach to Assortment Selection II: Under a K-Cardinality Constraint Every Policy Has Regret at Least C√(NT/K)Research Paper

A retailer with a large catalogue but a limited display (a web page, a shelf, a search result) must decide which assortment of products to show each arriving customer. Customers choose among the displayed products or leave without buying, and the retailer does not know their preferences in advance; it learns them only from the purchases it observes. This is…

12 thms3 active usersReviewed
🏆Completed
Dynamic ProgrammingProbabilityReinforcement Learning·Captain: mikedeng1

Technical Note: Q-Learning: With Bounded Rewards and Learning Rates with Σα = ∞, Σα² < ∞ at Every State–Action Pair, Tabular Q-Learning Converges to Q* with Probability 1Research Paper

Q-learning is the basic model-free algorithm of reinforcement learning: an agent that does not know the transition probabilities or the reward structure of a controlled Markov process learns the optimal action values from experience alone, by a one-line update applied after every observed transition. It was introduced in C. J. C. H. Watkins' 1989 thesis,…

8 thms3 active usersReviewed
🏆Completed
Operations ResearchTheoretical Computer Science·Captain: mikedeng1

The Weighted Majority Algorithm 2: On Any Partition into Segments, WML Makes at Most Σ min(l_i, (log(n/(βγ)) + m_i log(1/β))/log(1/u)) MistakesResearch Paper

Prediction with expert advice asks a master algorithm to combine the binary predictions of a pool of nnn prediction algorithms, trial after trial, so that it makes few more mistakes than the best member of the pool, without any probabilistic assumption on the data. Littlestone and Warmuth's Weighted Majority Algorithm WM (Littlestone and Warmuth 1994) keeps a…

4 thms3 active usersReviewed
🏆Completed
Linear algebraMarkov ChainReinforcement Learning·Captain: mikedeng1

Learning to Predict by the Methods of Temporal Differences: Linear TD(0) Converges in Expected Value to the Ideal Predictions on Absorbing Markov ChainsResearch Paper

Temporal-difference (TD) methods learn to predict an eventual outcome from the differences between successive predictions rather than from the difference between each prediction and the final outcome. Sutton's 1988 paper Learning to predict by the methods of temporal differences introduced the TD(λ\lambdaλ) family and gave the first convergence proof for a TD…

24 thms3 active usersReviewed
🏆Completed
OptimizationReinforcement Learning·Captain: mikedeng1

On the Theory of Policy Gradient Methods: Optimality, Approximation, and Distribution Shift 6: Agnostic Q-NPG for Log-Linear Policies, Bounded by Transfer Error, Excess Risk and Condition NumberResearch Paper

Policy gradient methods optimize a decision rule by changing the parameters that determine its action probabilities. In reinforcement learning, the objective is the expected total reward collected over time. Once a policy is restricted to a feature-based class, the best policy may be less effective than the unrestricted optimum. A useful guarantee must…

16 thms3 active usersReviewed
🏆Completed
OptimizationReinforcement Learning·Captain: mikedeng1

On the Theory of Policy Gradient Methods: Optimality, Approximation, and Distribution Shift 2: On a Chain MDP All Low-Order Derivatives of the Value Are Exponentially Small at Suboptimal PoliciesResearch Paper

Policy gradient methods adjust a policy by following derivatives of its expected reward. A common expectation is that a small gradient indicates a policy close to optimal. For discounted Markov decision processes, that interpretation can fail when a policy rarely reaches the states where reward is available. Agarwal, Kakade, Lee, and Mahajan study this…

12 thms3 active usersReviewed
🏆Completed
Linear algebraOptimization·Captain: mikedeng1

Distributed Optimization and Statistical Learning via the Alternating Direction Method of Multipliers VII: Factor Model Fitting — the ADMM X-Update in Closed Form, Entry by EntryTextbook

Alternating direction methods are used when one part of an optimization problem is easy to minimize and another part has a simple projection. Chapter 9 of Boyd, Parikh, Chu, Peleato and Eckstein (2011) examines this idea with nonconvex constraints. Its examples include sparse vectors, Boolean vectors and low-rank matrices. The chapter says explicitly that…

7 thms3 active usersReviewed
🏆Completed
Operations ResearchProbabilityStatistics·Captain: mikedeng1

From Predictive to Prescriptive Analytics 2: For Costs in [0, c̄] That Are L-Lipschitz, w.p. ≥ 1 − δ Every Decision Rule in F Costs ≤ Its Empirical Cost + c̄√(log(1/δ)/2N) + L·ℜ_N(F)Research Paper

Many operations decisions are made after observing side information: an inventory manager sees weather, search trends and calendar effects before ordering; a supply-chain planner sees market signals before shipping. Bertsimas and Kallus, in From Predictive to Prescriptive Analytics (arXiv:1402.5481v4, Management Science 2020), study how to turn such data…

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

Convex Optimization: Algorithms and Complexity XVI: Random Coordinate Descent RCD(γ) on a Strongly Convex Coordinate-Smooth Function Has Rate (1 − 1/κ_γ)^tTextbook

When a problem has millions of variables, even one full gradient can be too expensive to compute, while a single partial derivative ∂f/∂xi\partial f/\partial x_i∂f/∂xi​ is often cheap: in regularized regression, support vector machines and many structured problems, updating one coordinate costs a small fraction of a full gradient step. Coordinate descent methods exploit…

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

Convex Optimization: Algorithms and Complexity XIV: Stochastic Mirror Descent on a β-Smooth Function with Noise σ Has Rate Rσ√(2/t) + βR²/tTextbook

Many optimization problems in statistics and machine learning ask to minimize an expected loss f(x)=Eξ ℓ(x,ξ)f(x)=\mathbb E_\xi\,\ell(x,\xi)f(x)=Eξ​ℓ(x,ξ), or an average f(x)=1m∑i=1mfi(x)f(x)=\frac1m\sum_{i=1}^m f_i(x)f(x)=m1​∑i=1m​fi​(x) over a large data set. Exact gradients of such an fff are unavailable or too expensive, but unbiased random estimates are cheap: the gradient of the loss at one sample, or of one randomly…

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

Convex Optimization: Algorithms and Complexity XII: Mirror Prox on a Convex β-Smooth Function Has Rate βR²/(ρt)Textbook

First-order methods for constrained convex optimization are usually analysed in the Euclidean norm, where gradient descent and its projected and accelerated variants have well-understood rates. Many constraint sets of practical interest, such as the probability simplex, the ℓ1\ell_1ℓ1​ ball and the spectrahedron, are poorly adapted to the Euclidean geometry: the…

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

Convex Optimization: Algorithms and Complexity XI: Mirror Descent with a ρ-Strongly Convex Mirror Map Has Rate RL√(2/(ρt))Textbook

The projected subgradient method of Chapter 3 measures distances in the Euclidean norm, and its rate RL/tRL/\sqrt tRL/t​ depends on the geometry only through a Euclidean radius RRR and a Euclidean bound LLL on the subgradients. For many constraint sets that occur in practice this is the wrong geometry. On the probability simplex Δn\Delta_nΔn​ with subgradients bounded in …

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

Convex Optimization: Algorithms and Complexity X: Nesterov's Accelerated Gradient Descent on a β-Smooth α-Strongly Convex Function Has Rate ((α + β)/2)‖x₁ − x*‖² exp(−(t − 1)/√κ)Textbook

First-order methods, which query only function values and gradients, are the workhorse of large-scale optimization in machine learning, signal processing and operations research, because each step costs little more than one gradient evaluation. For a function that is both strongly convex and smooth, plain gradient descent converges geometrically, but the…

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

Convex Optimization: Algorithms and Complexity IX: Nesterov's Accelerated Gradient Descent on a Convex β-Smooth Function Has Rate 2β‖x₁ − x*‖²/t²Textbook

Minimizing a convex function f:Rn→Rf:\mathbb R^n\to\mathbb Rf:Rn→R whose gradient is Lipschitz is the basic problem of first-order optimization, and it is the regime in which most large-scale methods of machine learning, signal processing and operations research are analysed. The natural method, gradient descent, reaches accuracy ε\varepsilonε after O(1/ε)O(1/\varepsilon)O(1/ε) gradi…

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

Convex Optimization: Algorithms and Complexity VIII: No Black-Box Method Beats 3β‖x₁ − x*‖²/(32(t + 1)²) on β-Smooth Convex FunctionsTextbook

Upper bounds for an optimization method say how fast it converges; oracle complexity lower bounds say how fast any method of a given kind can possibly converge. Chapter 3 of S. Bubeck, Convex Optimization: Algorithms and Complexity (Foundations and Trends in Machine Learning 8(3–4), 2015, arXiv:1405.4980) proves upper bounds for subgradient descent on…

8 thms3 active usersReviewed
🏆Completed
ProbabilityStatistics·Captain: mikedeng1

Rademacher and Gaussian Complexities: Risk Bounds and Structural Results 6: The Expected Maximum Discrepancy Lies Between R_n(F)/2 − 2√(2/n) and R_n(F) + 4√(2/n)Research Paper

Data-dependent risk bounds in statistical learning theory control the gap between the expected loss of a learned function and its empirical loss by a complexity penalty that is computed from the training data. The first such penalties were the maximum discrepancy of a function class (Bartlett, Boucheron and Lugosi, Model selection and error estimation,…

10 thms3 active usersReviewed
PreviousPage 18 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