Katyusha: the first direct acceleration of stochastic gradient methods
From MaRDI portal
Recommendations
- Katyusha: the first direct acceleration of stochastic gradient methods
- Accelerated stochastic variance reduction for a class of convex optimization problems
- Accelerating variance-reduced stochastic gradient methods
- Momentum and stochastic momentum for stochastic gradient, Newton, proximal point and subspace descent methods
- Catalyst acceleration for first-order convex optimization: from theory to practice
Cites work
- A proximal stochastic gradient method with progressive variance reduction
- Accelerated methods for nonconvex optimization
- Accelerated proximal stochastic dual coordinate ascent for regularized loss minimization
- An accelerated randomized proximal coordinate gradient method and its application to regularized empirical risk minimization
- An optimal method for stochastic composite optimization
- Beyond the regret minimization barrier: optimal algorithms for stochastic strongly-convex optimization
- Efficiency of coordinate descent methods on huge-scale optimization problems
- Finding approximate local minima faster than gradient descent
- scientific article; zbMATH DE number 3850830 (Why is no real title available?)
- Incremental majorization-minimization optimization with application to large-scale machine learning
- Introductory lectures on convex optimization. A basic course.
- Linear coupling: an ultimate unification of gradient and mirror descent
- Nearly-linear time positive LP solver with faster convergence rate
- On the complexity analysis of randomized block-coordinate descent methods
- Optimization algorithms for faster computational geometry
- Prediction by Categorical Features: Generalization Properties and Application to Feature Ranking
- Smooth minimization of non-smooth functions
- Stochastic dual coordinate ascent methods for regularized loss minimization
- Stochastic primal-dual coordinate method for regularized empirical risk minimization
- Using optimization to break the epsilon barrier: a faster and simpler width-independent algorithm for solving positive linear programs in parallel
- Using optimization to obtain a width-independent, parallel, simpler, and faster positive SDP solver
Cited in
(46)- Momentum and stochastic momentum for stochastic gradient, Newton, proximal point and subspace descent methods
- Accelerating variance-reduced stochastic gradient methods
- Oracle complexity separation in convex optimization
- Laplacian smoothing gradient descent
- Optimization for deep learning: an overview
- Accelerated directional search with non-Euclidean prox-structure
- Accelerated stochastic variance reduction for a class of convex optimization problems
- Catalyst acceleration for first-order convex optimization: from theory to practice
- On the complexity analysis of the primal solutions for the accelerated randomized dual coordinate ascent
- Katyusha: the first direct acceleration of stochastic gradient methods
- L-SVRG and L-Katyusha with arbitrary sampling
- scientific article; zbMATH DE number 7625177 (Why is no real title available?)
- Scheduled restart momentum for accelerated stochastic gradient descent
- An adaptive gradient method with energy and momentum
- An aggressive reduction on the complexity of optimization for non-strongly convex objectives
- Nonconvex optimization with inertial proximal stochastic variance reduction gradient
- Block mirror stochastic gradient method for stochastic optimization
- Adaptive proximal SGD based on new estimating sequences for sparser ERM
- SGEM: stochastic gradient with energy and momentum
- An accelerated stochastic mirror descent method
- Optimal gradient tracking for decentralized optimization
- Iterative learning control based on random variance reduction gradient method
- Efficient first order method for saddle point problems with higher order smoothness
- Complementary composite minimization, small gradients in general norms, and applications
- Accelerated minimax algorithms flock together
- SketchySGD: reliable stochastic optimization via randomized curvature estimates
- Accelerated methods with compression for horizontal and vertical federated learning
- Fine-grained analysis and faster algorithms for iteratively solving linear systems
- Practical operator sketching framework for accelerating iterative data-driven solutions in linear inverse problems
- Stochastic primal-dual three operator splitting algorithm with extension to equivariant regularization-by-denoising
- Convergence analysis of a proximal stochastic denoising regularization algorithm
- On the fast convergence of minibatch heavy ball momentum
- On the improvement of the Barzilai-Borwein step size in variance reduction methods
- A guide to stochastic optimisation for large-scale inverse problems
- Accelerated stochastic extragradient: mixing Hessian and gradient similarity to reduce communication in distributed and federated learning
- Nonconvex stochastic Bregman proximal gradient method with application to deep learning
- New penalized stochastic gradient methods for linearly constrained strongly convex optimization
- Variance-reduced conservative policy iteration
- AEGD: adaptive gradient descent with energy
- Global Riemannian acceleration in hyperbolic and spherical spaces
- A novel stochastic conjugate gradient algorithm based on a stochastic differential equation perspective
- Stochastic ADMM with variance-reduced recursive momentum and its accelerated variant for nonconvex nonsmooth optimization
- Stochastic limited memory BFGS algorithms for solving nonconvex support vector machine problems and nonconvex risk minimization program
- Stochastic Polyak stepsize for SGD with variance reduction and momentum
- Second-order information promotes mini-batch robustness in variance-reduced gradients
- Equivariant denoisers for plug-and-play image restoration
This page was built for publication: Katyusha: the first direct acceleration of stochastic gradient methods
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4558559)
