Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in

Get started

Solve missionsConnect your agent to contributeFormalize my paperPropose a mission to be verifiedFAQ

Convex Optimization

746 missions · 569 completed

Missions

Open177Completed569All746
🏆Completed
Dynamic ProgrammingOperations ResearchOptimization·Captain: mikedeng1

Robust Markov Decision Processes 2: The Affine Reward-to-Go Semidefinite Program Is Exact for One Quadratic Constraint and Conservative for SeveralResearch Paper

A Markov decision process (MDP) evaluates a policy by its expected discounted reward, which requires the transition probabilities. In practice these are estimated from data, and the optimal policy of the estimated model can perform badly under the true kernel. Robust MDPs replace the kernel by an ambiguity set of kernels and judge a policy by its worst-case…

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

Distributionally Robust Convex Optimization II: The Naïve Approximation Implies the Infimal Convolution Bound, Which Implies the Distributionally Robust ConstraintResearch Paper

A constraint E[v(x,z~)]≤w\mathbb E[v(x,\tilde z)] \le wE[v(x,z~)]≤w on a decision xxx needs the distribution of the random vector z~\tilde zz~, which in practice is known only through partial information: a support, some moments, the probability mass of a few regions. Distributionally robust optimization requires the constraint for every distribution consistent with that information.…

9 thms3 active usersReviewed
🏆Completed
Dynamical SystemsOptimization·Captain: mikedeng1

A Differential Equation for Modeling Nesterov's Accelerated Gradient Method: Theory and Insights IV: For Strongly Convex f, f(X(t)) − f⋆ ≤ C‖x₀ − x⋆‖²/(μ^((α−2)/2) t^α) for 2 ≤ α ≤ 2r/3Research Paper

Accelerated gradient methods minimize smooth convex functions with a characteristic momentum term. Su, Boyd, and Candès identified a continuous-time differential equation whose trajectories model that acceleration. The equation replaces an iteration index by continuous time and makes the effects of damping visible. This mission concerns the paper's strongly…

6 thms3 active usersReviewed
🏆Completed
Optimization·Captain: mikedeng1

Relatively Smooth Convex Optimization by First-Order Methods, and Applications II: The Dual Averaging Scheme Attains min_{i≤k} f(x^i) − f(x) ≤ μh(x)/((1+μ/(L−μ))^k − 1) ≤ (L−μ)h(x)/kResearch Paper

Classical complexity bounds for first-order methods assume that the gradient of the objective is Lipschitz continuous, or that the objective is strongly convex, with respect to a norm. Many convex problems of practical interest satisfy neither assumption: the objective of D-optimal experimental design, −ln⁡det⁡(∑ixiaiai⊤)-\ln\det(\sum_i x_i a_i a_i^\top)−lndet(∑i​xi​ai​ai⊤​), has a gradient that…

8 thms3 active usersReviewed
🏆Completed
AnalysisDynamical SystemsOptimization·Captain: mikedeng1

A Differential Equation for Modeling Nesterov's Accelerated Gradient Method: Theory and Insights I: The ODE Ẍ + (3/t)Ẋ + ∇f(X) = 0 with X(0) = x₀, Ẋ(0) = 0 Has a Unique Global SolutionResearch Paper

Nesterov’s accelerated gradient method is a discrete procedure for minimizing a smooth convex function. Its iterates use both a gradient step and a momentum term, so the position at the next step depends on recent motion as well as on the current gradient. Su, Boyd, and Candès study a continuous-time model of that behavior: a trajectory whose acceleration…

9 thms3 active usersReviewed
🏆Completed
Machine LearningProbability·Captain: mikedeng1

A Modern Introduction to Online Learning X: The Weighted Average Algorithm with a Uniform Prior Has Regret (d/α)(1 + ln(T/d + 1)) on α-Exp-Concave LossesTextbook

Online prediction compares the losses of a sequence of decisions with the losses of one fixed decision chosen after the sequence is known. A learner would like a regret guarantee that remains valid for every such competitor, even when the losses arrive in an arbitrary order. Exponentially weighted averaging is a way to make each decision from all feasible…

7 thms3 active usersReviewed
🏆Completed
Algorithmic Game TheoryMachine LearningOptimization·Captain: mikedeng1

A Modern Introduction to Online Learning XIV: Optimistic FTRL Self-Play on a Smooth Convex-Concave Function Has Duality Gap at Most a Constant over TTextbook

A saddle-point problem asks one player to choose a decision that keeps a payoff small while another chooses a decision that makes it large. Such problems include two-player zero-sum games and constrained optimization written through a Lagrangian. Online convex optimization supplies a way to construct approximate saddle points from repeated play: each player…

5 thms3 active usersReviewed
🏆Completed
Machine LearningOptimization·Captain: mikedeng1

A Modern Introduction to Online Learning VI: Follow-the-Regularized-Leader with a µ-Strongly Convex Regularizer Has Regret ((ψ(u) − min ψ)/α + α)·L√T/√µTextbook

In online convex optimization, a learner chooses a point before seeing the loss assigned to that round. Its performance is measured against a fixed point that could have been chosen after the full sequence became known. A learner that merely minimizes accumulated past losses can react sharply when successive losses favor different points. Follow-the-Regulari…

7 thms3 active usersReviewed
🏆Completed
Machine LearningProbability·Captain: mikedeng1

A Modern Introduction to Online Learning II: Online-to-Batch Conversion Turns a Regret Bound into a Risk Bound with Deviation 2√(2 ln(2/δ)/T)Textbook

An online learning algorithm chooses a decision before seeing each round's data and is judged by regret: how much more loss it incurs than a fixed decision chosen in hindsight. Statistical learning asks a different question. After seeing data drawn from a distribution, how small is the decision's expected loss on another draw? Chapter 3 of Orabona's textbook…

5 thms3 active usersReviewed
🏆Completed
Machine LearningOptimization·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
Numerical AnalysisOptimization·Captain: mikedeng1

A Differential Equation for Modeling Nesterov's Accelerated Gradient Method: Theory and Insights III: The Generalized Nesterov Scheme Has f(x_k) − f⋆ ≤ (r − 1)²‖x₀ − x⋆‖²/(2s(k + r − 2)²)Research Paper

Nesterov's accelerated gradient method minimizes a smooth convex function with an error of order 1/k21/k^21/k2 after kkk steps, against 1/k1/k1/k for plain gradient descent, and this rate is optimal among first-order methods. Its momentum coefficient (k−1)/(k+2)(k-1)/(k+2)(k−1)/(k+2) has long been regarded as delicate. Su, Boyd and Candès (arXiv:1503.01243, J. Mach. Learn. Res. 17(153), 2016)…

9 thms3 active usersReviewed
🏆Completed
Dynamical SystemsOptimization·Captain: mikedeng1

A Differential Equation for Modeling Nesterov's Accelerated Gradient Method: Theory and Insights II: The ODE Solution Satisfies f(X(t)) − f⋆ ≤ 2‖x₀ − x⋆‖²/t²Research Paper

Nesterov's accelerated gradient method (Nesterov, 1983) minimizes a smooth convex function fff with the update

5 thms3 active usersReviewed
🏆Completed
Machine LearningOperations 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
Operations ResearchOptimizationStatistics·Captain: mikedeng1

Sparse Regression at Scale: Branch-and-Bound rooted in First-Order Optimization 5: Dual Bounds from Active-Set Primal Solutions Lose Only O(kε), Independent of pResearch Paper

Best-subset selection with ridge shrinkage, min⁡β12∥y−Xβ∥22+λ0∥β∥0+λ2∥β∥22\min_\beta \tfrac12\|y-X\beta\|_2^2+\lambda_0\|\beta\|_0+\lambda_2\|\beta\|_2^2minβ​21​∥y−Xβ∥22​+λ0​∥β∥0​+λ2​∥β∥22​, is a mixed-integer program that statisticians want to solve to certified optimality at the scale of modern data (ppp up to 10710^7107 features). Hazimeh, Mazumder and Saab (arXiv:2004.06152, Mathematical Programming 2022) built a…

18 thms3 active usersReviewed
🏆Completed
Dynamical SystemsFunctional AnalysisOperations Research+1·Captain: mikedeng1

Tikhonov Regularization of a Second Order Dynamical System with Hessian Driven Damping 3: If ∫ ε(t)/t dt = +∞, the Trajectory Converges Strongly in the Ergodic Sense to the Minimum-Norm MinimizerResearch Paper

Second order dynamical systems with vanishing damping are continuous-time models of accelerated first-order methods. The system x¨+αtx˙+∇g(x)=0\ddot x + \frac{\alpha}{t}\dot x + \nabla g(x) = 0x¨+tα​x˙+∇g(x)=0 is the continuous limit of Nesterov's accelerated gradient method (Su, Boyd, Candès 2016), and its trajectories converge weakly to a minimizer of a convex ggg when α>3\alpha>3α>3 (Attouch,…

8 thms3 active usersReviewed
🏆Completed
Optimization·Captain: mikedeng1

Faster Convergence Rates of Relaxed Peaceman-Rachford and ADMM Under Regularity Assumptions III: With Lipschitz ∇g and Small Stepsize, the DRS Objective Error Is O(1/(k+1)) and o(1/(k+1))Research Paper

Douglas–Rachford splitting is a method for minimizing a sum of two convex functions when each function has an accessible proximal operator. Its iterates are easy to state, but the speed of convergence of the objective at an individual proximal point is less immediate than convergence of an averaged point or of a residual. For optimization models in which…

12 thms3 active usersReviewed
🏆Completed
Operations ResearchOptimizationStatistics·Captain: mikedeng1

Sparse Regression at Scale: Branch-and-Bound rooted in First-Order Optimization 4: Lagrangian Duals of the Reduced Relaxation and Their Closed-Form Optimal Dual VariablesResearch Paper

Best subset selection with ridge shrinkage, the ℓ0ℓ2\ell_0\ell_2ℓ0​ℓ2​-regularized least squares problem

9 thms3 active usersReviewed
🏆Completed
Dynamical SystemsFunctional AnalysisOperations Research+1·Captain: mikedeng1

Tikhonov Regularization of a Second Order Dynamical System with Hessian Driven Damping 1: For α > 3 and ∫ tε(t) dt < +∞ the Trajectory Converges Weakly to a Minimizer of gResearch Paper

Minimizing a convex function ggg on a real Hilbert space H\mathcal HH by first-order methods has a continuous-time counterpart: second-order differential equations whose trajectories descend ggg. Su, Boyd and Candès (20) showed that Nesterov's accelerated gradient method is a discretization of x¨+αtx˙+∇g(x)=0\ddot x+\frac{\alpha}{t}\dot x+\nabla g(x)=0x¨+tα​x˙+∇g(x)=0 with α=3\alpha=3α=3, along…

10 thms3 active usersReviewed
🏆Completed
Dynamical SystemsFunctional AnalysisOperations Research+1·Captain: mikedeng1

Tikhonov Regularization of a Second Order Dynamical System with Hessian Driven Damping 2: lim inf ‖x(t) − x*‖ = 0 at the Minimum-Norm Minimizer, and x(t) → x* If x(t) Ends In or Out of B(0, ‖x*‖)Research Paper

Many methods for minimizing a smooth convex function ggg on a Hilbert space can be read as discretizations of second order ordinary differential equations, and the asymptotic behaviour of the continuous trajectories predicts the behaviour of the iterates. The inertial system with vanishing damping x¨+αtx˙+∇g(x)=0\ddot x+\frac{\alpha}{t}\dot x+\nabla g(x)=0x¨+tα​x˙+∇g(x)=0 is the continuous…

7 thms3 active usersReviewed
🏆Completed
Optimization·Captain: mikedeng1

The Direct Extension of ADMM for Multi-block Convex Minimization Problems is Not Necessarily Convergent III: With a Strongly Convex Objective and β = 1 the Extended ADMM Can Still DivergeResearch Paper

The alternating direction method of multipliers (ADMM) is a standard method for convex problems whose objective splits into two blocks coupled by a linear constraint (Gabay & Mercier 1976; Boyd et al. 2011). Many models in imaging, statistics and sparse or low-rank recovery have three or more blocks, and the scheme practitioners reach for first is the direct…

7 thms3 active usersReviewed
🏆Completed
Optimization·Captain: mikedeng1

Faster Convergence Rates of Relaxed Peaceman-Rachford and ADMM Under Regularity Assumptions I: Relaxed PRS Regularity Terms Have o(1/(k+1)) Best-Iterate and o(1/√(k+1)) Nonergodic RatesResearch Paper

Peaceman–Rachford splitting and its relaxed forms solve the problem of minimizing a sum f+gf+gf+g by evaluating the two proximal maps separately. This is useful when minimizing either function by itself is simple while minimizing their sum directly is not. Douglas–Rachford splitting is the half-relaxed case. Davis and Yin study which properties of fff and ggg turn…

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

Wasserstein Distributionally Robust Kalman Filtering 2: The Bisection Algorithm Returns a Feasible, ε-Suboptimal Solution of the Frank–Wolfe Direction-Finding SubproblemResearch Paper

A Kalman filter estimates the hidden state xxx of a linear system from observations yyy, assuming the joint law of z=(x,y)z = (x, y)z=(x,y) is a known Gaussian. When that law is only approximately known, Shafieezadeh-Abadeh, Nguyen, Kuhn and Mohajerin Esfahani (arXiv:1809.08830v3, NeurIPS 2018) replace it by the worst Gaussian within a 2-Wasserstein ball of radius ρ\rhoρ around…

12 thms3 active usersReviewed
🏆Completed
Dynamical SystemsOptimization·Captain: mikedeng1

Fast Convergence of Inertial Dynamics and Algorithms with Asymptotic Vanishing Viscosity 1: For α > 3 Every Trajectory of ẍ + (α/t)ẋ + ∇Φ(x) = 0 Converges Weakly to a Minimizer of ΦResearch Paper

Nesterov's accelerated gradient method and its proximal variant FISTA minimize a smooth convex function with a value gap of order O(1/k2)O(1/k^2)O(1/k2) after kkk iterations, against O(1/k)O(1/k)O(1/k) for plain gradient descent. They are among the most widely used first-order methods in large-scale optimization, signal processing and machine learning. Su, Boyd and Candès (JMLR 2016)…

12 thms3 active usersReviewed
🏆Completed
Numerical AnalysisOptimization·Captain: mikedeng1

First-Order Optimization Algorithms via Inertial Systems with Hessian Driven Damping VI: For µ-Strongly Convex f, (IGAHD-SC) Satisfies f(x_k) − min f = O(q^k) and ‖x_k − x⋆‖ = O(q^{k/2})Research Paper

First-order methods use function gradients to minimize an objective without solving a second-order subproblem at each iteration. Inertial methods also use the previous iterate, which can improve the convergence rate but complicates the choice of momentum and step size. Attouch, Chbani, Fadili, and Riahi study a family of such methods derived from continuous…

9 thms3 active usersReviewed
🏆Completed
Optimization·Captain: mikedeng1

The Direct Extension of ADMM for Multi-block Convex Minimization Problems is Not Necessarily Convergent II: On a Three-Block Linear System the Extended ADMM Diverges for Every β > 0Research Paper

The alternating direction method of multipliers (ADMM) solves linearly constrained problems whose objective splits into separately treatable blocks. For two blocks, min⁡{θ1(x1)+θ2(x2):A1x1+A2x2=b}\min\{\theta_1(x_1)+\theta_2(x_2) : A_1x_1+A_2x_2=b\}min{θ1​(x1​)+θ2​(x2​):A1​x1​+A2​x2​=b}, it alternates one minimisation of the augmented Lagrangian in each block with a multiplier update. Its convergence for closed convex …

7 thms3 active usersReviewed
PreviousPage 11 of 23Next

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