First-order and stochastic optimization methods for machine learning

DOI10.1007/978-3-030-39568-1zbMath1442.68003OpenAlexW3025638325MaRDI QIDQ2307433

Guanghui Lan

Publication date: 27 March 2020

Published in: Springer Series in the Data Sciences (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/978-3-030-39568-1

Mathematics Subject Classification ID

Convex programming (90C25) Nonconvex programming, global optimization (90C26) Learning and adaptive systems in artificial intelligence (68T05) Stochastic programming (90C15) Research exposition (monographs, survey articles) pertaining to computer science (68-02) Randomized algorithms (68W20) Distributed algorithms (68W15) Online algorithms; streaming algorithms (68W27)

Related Items

Frank--Wolfe Methods with an Unbounded Feasible Region and Applications to Structured Learning ⋮ Solving Stochastic Optimization with Expectation Constraints Efficiently by a Stochastic Augmented Lagrangian-Type Algorithm ⋮ Spatiotemporal-textual point processes for crime linkage detection ⋮ A stochastic primal-dual method for a class of nonconvex constrained optimization ⋮ Differentially Private Accelerated Optimization Algorithms ⋮ Simple and Optimal Methods for Stochastic Variational Inequalities, II: Markovian Noise and Policy Evaluation in Reinforcement Learning ⋮ Simple and Optimal Methods for Stochastic Variational Inequalities, I: Operator Extrapolation ⋮ Subgradient ellipsoid method for nonsmooth convex problems ⋮ Convergence analysis of a subsampled Levenberg-Marquardt algorithm ⋮ A dual-based stochastic inexact algorithm for a class of stochastic nonsmooth convex composite problems ⋮ Universal Conditional Gradient Sliding for Convex Optimization ⋮ Accelerated gradient methods with absolute and relative noise in the gradient ⋮ Finite-time convergence rates of distributed local stochastic approximation ⋮ A unified analysis of stochastic gradient‐free Frank–Wolfe methods ⋮ Optimistic optimisation of composite objective with exponentiated update ⋮ A distributed proximal gradient method with time-varying delays for solving additive convex optimizations ⋮ A unified single-loop alternating gradient projection algorithm for nonconvex-concave and convex-nonconcave minimax problems ⋮ Hyperfast second-order local solvers for efficient statistically preconditioned distributed optimization ⋮ Accelerated variance-reduced methods for saddle-point problems ⋮ Optimal Methods for Convex Risk-Averse Distributed Optimization ⋮ Graph Topology Invariant Gradient and Sampling Complexity for Decentralized and Stochastic Optimization ⋮ No-regret dynamics in the Fenchel game: a unified framework for algorithmic convex optimization ⋮ Randomized Douglas–Rachford Methods for Linear Systems: Improved Accuracy and Efficiency ⋮ Variable sample-size operator extrapolation algorithm for stochastic mixed variational inequalities ⋮ Optimal Algorithms for Stochastic Complementary Composite Minimization ⋮ Decentralized saddle-point problems with different constants of strong convexity and strong concavity ⋮ Stochastic regularized Newton methods for nonlinear equations ⋮ Block mirror stochastic gradient method for stochastic optimization ⋮ Policy mirror descent for reinforcement learning: linear convergence, new sampling complexity, and generalized problem classes ⋮ Accelerated doubly stochastic gradient descent for tensor CP decomposition ⋮ Hessian averaging in stochastic Newton methods achieves superlinear convergence ⋮ Accelerating stochastic sequential quadratic programming for equality constrained optimization using predictive variance reduction ⋮ First-order methods for convex optimization ⋮ Stochastic variable metric proximal gradient with variance reduction for non-convex composite optimization ⋮ Sample average approximations of strongly convex stochastic programs in Hilbert spaces ⋮ Statistical Analysis of Fixed Mini-Batch Gradient Descent Estimator ⋮ An oracle-based framework for robust combinatorial optimization ⋮ Stochastic first-order methods for convex and nonconvex functional constrained optimization ⋮ Sample Size Estimates for Risk-Neutral Semilinear PDE-Constrained Optimization ⋮ Unnamed Item ⋮ Accelerated methods for saddle-point problem ⋮ Recent theoretical advances in decentralized distributed convex optimization ⋮ Recent Theoretical Advances in Non-Convex Optimization ⋮ Frank-Wolfe and friends: a journey into projection-free first-order optimization methods ⋮ Conditional Gradient Methods for Convex Optimization with General Affine and Nonlinear Constraints ⋮ Solving convex min-min problems with smoothness and strong convexity in one group of variables and low dimension in the other ⋮ A new restricted memory level bundle method for constrained convex nonsmooth optimization ⋮ Dualize, split, randomize: toward fast nonsmooth optimization algorithms ⋮ Stochastic relaxed inertial forward-backward-forward splitting for monotone inclusions in Hilbert spaces ⋮ Dimension independent excess risk by stochastic gradient descent ⋮ Efficient Algorithms for Distributionally Robust Stochastic Optimization with Discrete Scenario Support ⋮ Learning over No-Preferred and Preferred Sequence of Items for Robust Recommendation ⋮ Finite-Time Analysis and Restarting Scheme for Linear Two-Time-Scale Stochastic Approximation ⋮ Constructing unbiased gradient estimators with finite variance for conditional stochastic optimization ⋮ Finite-sample analysis of nonlinear stochastic approximation with applications in reinforcement learning ⋮ Decentralized convex optimization under affine constraints for power systems control ⋮ Network manipulation algorithm based on inexact alternating minimization ⋮ Distributionally robust optimization with moment ambiguity sets ⋮ Inertial accelerated SGD algorithms for solving large-scale lower-rank tensor CP decomposition problems ⋮ Complexity of stochastic dual dynamic programming

This page was built for publication: First-order and stochastic optimization methods for machine learning