Convex optimization: algorithms and complexity

zbMATH Open1365.90196arXiv1405.4980MaRDI QIDQ2809807FDOQ2809807

Authors: Sébastien Bubeck 

Publication date: 30 May 2016

Published in: Foundations and Trends in Machine Learning (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1405.4980

Recommendations

• Lectures on convex optimization
• Large-scale convex optimization. Algorithms \& analyses via monotone operators
• Introductory lectures on convex optimization. A basic course.
• Algorithms for convex optimization
• Lectures on modern convex optimization. Analysis, algorithms, and engineering applications

zbMATH Keywords

convex optimizationstochastic optimizationnumerical methodsblack-box model

Mathematics Subject Classification ID

Convex programming (90C25) Analysis of algorithms and problem complexity (68Q25) Abstract computational complexity for mathematical programming problems (90C60)

Cited In (only showing first 100 items - show all)

• Random Batch Methods for Classical and Quantum Interacting Particle Systems and Statistical Samplings
• Nudging the particle filter
• Graph-dependent implicit regularisation for distributed stochastic subgradient descent
• Alternating direction method of multipliers for machine learning
• Adaptive Catalyst for Smooth Convex Optimization
• Accelerated proximal envelopes: application to componentwise methods
• On the computational efficiency of catalyst accelerated coordinate descent
• Efficient online linear optimization with approximation algorithms
• Convergence of distributed gradient-tracking-based optimization algorithms with random graphs
• Variable demand and multi-commodity flow in Markovian network equilibrium
• Fit without fear: remarkable mathematical phenomena of deep learning through the prism of interpolation
• New Hadamard-type inequalities for \(E\)-convex functions involving generalized fractional integrals
• Data-Driven Mirror Descent with Input-Convex Neural Networks
• Non-smooth setting of stochastic decentralized convex optimization problem over time-varying graphs
• Numerical methods for the resource allocation problem in a computer network
• Intuitionistic-fuzzy goals in zero-sum multi criteria matrix games
• Accelerated methods for weakly-quasi-convex optimization problems
• On the random batch method for second order interacting particle systems
• Title not available (Why is that?)
• The entropic barrier: exponential families, log-concave geometry, and self-concordance
• Mass-spring-damper networks for distributed optimization in non-Euclidean spaces
• Stochastic saddle-point optimization for the Wasserstein barycenter problem
• Accelerated gradient methods with absolute and relative noise in the gradient
• Large-scale convex optimization. Algorithms \& analyses via monotone operators
• Divergences on symmetric cones and medians
• Nonconvex Low-Rank Tensor Completion from Noisy Data
• A dual approach for optimal algorithms in distributed optimization over networks
• How can we identify the sparsity structure pattern of high-dimensional data: an elementary statistical analysis to interpretable machine learning
• Vaidya's method for convex stochastic optimization problems in small dimension
• The computational asymptotics of Gaussian variational inference and the Laplace approximation
• Efficient numerical methods to solve sparse linear equations with application to PageRank
• Convergence of the random batch method for interacting particles with disparate species and weights
• Optimization based methods for partially observed chaotic systems
• Behavior of accelerated gradient methods near critical points of nonconvex functions
• Convergence guarantees for a class of non-convex and non-smooth optimization problems
• Accelerated methods for saddle-point problem
• Differentially private inference via noisy optimization
• First-order and stochastic optimization methods for machine learning
• Average stability is invariant to data preconditioning. Implications to exp-concave empirical risk minimization
• Heteroskedastic PCA: algorithm, optimality, and applications
• Convergence results of a nested decentralized gradient method for non-strongly convex problems
• Generalized Nesterov's accelerated proximal gradient algorithms with convergence rate of order \(o(1/k^2)\)
• A multiplicative weight updates algorithm for packing and covering semi-infinite linear programs
• The common-directions method for regularized empirical risk minimization
• Title not available (Why is that?)
• Approximate inference for constructing astronomical catalogs from images
• A finite time analysis of temporal difference learning with linear function approximation
• Exploiting problem structure in optimization under uncertainty via online convex optimization
• Fast Core Pricing for Rich Advertising Auctions
• Efficient, certifiably optimal clustering with applications to latent variable graphical models
• Elliptic quasi-variational inequalities under a smallness assumption: uniqueness, differential stability and optimal control
• Scale-free online learning
• Persuasion in networks: public signals and cores
• Accelerating incremental gradient optimization with curvature information
• Convex optimization with an interpolation-based projection and its application to deep learning
• Replicator dynamics: old and new
• Random batch methods (RBM) for interacting particle systems
• Bregman three-operator splitting methods
• Smoothed Variable Sample-Size Accelerated Proximal Methods for Nonsmooth Stochastic Convex Programs
• A multiplicative weights update algorithm for packing and covering semi-infinite linear programs
• Metamodel construction for sensitivity analysis
• Complexity analysis for optimization methods
• Stochastic matrix-free equilibration
• Title not available (Why is that?)
• First-order methods for convex optimization
• Asymptotic theory in network models with covariates and a growing number of node parameters
• Robust and sparse regression in generalized linear model by stochastic optimization
• Implicit regularization in nonconvex statistical estimation: gradient descent converges linearly for phase retrieval, matrix completion, and blind deconvolution
• A consensus-based global optimization method for high dimensional machine learning problems
• Polynomial-time algorithms for submodular Laplacian systems
• Convergence rates for optimised adaptive importance samplers
• Regularisation of neural networks by enforcing Lipschitz continuity
• Stochastic mirror descent method for linear ill-posed problems in Banach spaces
• A distributed flexible delay-tolerant proximal gradient algorithm
• A regularization interpretation of the proximal point method for weakly convex functions
• A new look at the Hardy-Littlewood-Pólya inequality of majorization
• Asynchronous schemes for stochastic and misspecified potential games and nonconvex optimization
• Accelerated gradient boosting
• Min-Max-Min Optimization with Smooth and Strongly Convex Objectives
• Convergence rates for deterministic and stochastic subgradient methods without Lipschitz continuity
• Inverse reinforcement learning in contextual MDPs
• A stochastic gradient algorithm with momentum terms for optimal control problems governed by a convection-diffusion equation with random diffusivity
• Natural gradient for combined loss using wavelets
• Bounds for the tracking error of first-order online optimization methods
• A fully polynomial time approximation scheme for the smallest diameter of imprecise points
• Linear convergence of first order methods for non-strongly convex optimization
• Mirror descent algorithms for minimizing interacting free energy
• Proximal gradient methods with adaptive subspace sampling
• Inexact primal-dual gradient projection methods for nonlinear optimization on convex set
• Strong convexity of sandwiched entropies and related optimization problems
• Efficient numerical methods for entropy-linear programming problems
• Bandit online optimization over the permutahedron
• Bias of homotopic gradient descent for the hinge loss
• Log-concave sampling: Metropolis-Hastings algorithms are fast
• A Newton-CG algorithm with complexity guarantees for smooth unconstrained optimization
• Perturbed iterate analysis for asynchronous stochastic optimization
• From inexact optimization to learning via gradient concentration
• A stochastic subgradient method for distributionally robust non-convex and non-smooth learning
• Robust statistical learning with Lipschitz and convex loss functions
• Exact worst-case convergence rates of the proximal gradient method for composite convex minimization

This page was built for publication: Convex optimization: algorithms and complexity

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2809807)