The ``black-box optimization problem: zero-order accelerated stochastic method via kernel approximation
From MaRDI portal
(Redirected from Publication:6655796)
The ``black-box'' optimization problem: zero-order accelerated stochastic method via kernel approximation
The ``black-box'' optimization problem: zero-order accelerated stochastic method via kernel approximation
Recommendations
- Accelerated zero-order SGD method for solving the black box optimization problem under ``overparametrization condition
- Stochastic adversarial noise in the ``black box optimization problem
- Black-box reductions for zeroth-order gradient algorithms to achieve lower query complexity
- Zeroth-order regularized optimization (ZORO): approximately sparse gradients and adaptive sampling
Cites work
- A theoretical and empirical comparison of gradient approximations in derivative-free optimization
- Accelerated gradient methods with absolute and relative noise in the gradient
- Accelerated zero-order SGD method for solving the black box optimization problem under ``overparametrization condition
- An accelerated method for derivative-free smooth stochastic convex optimization
- Decentralized and parallel primal and dual accelerated methods for stochastic convex programming problems
- Derivative-free optimization: a review of algorithms and comparison of software implementations
- Differential evolution -- a simple and efficient heuristic for global optimization over continuous spaces
- Distributed Randomized Gradient-Free Mirror Descent Algorithm for Constrained Optimization
- Efficiency of coordinate descent methods on huge-scale optimization problems
- Efficient unconstrained black box optimization
- Finite Difference Gradient Approximation: To Randomize or Not?
- scientific article; zbMATH DE number 1321699 (Why is no real title available?)
- Hyperband: a novel bandit-based approach to hyperparameter optimization
- Introduction to Derivative-Free Optimization
- Lectures on convex optimization
- Mathematical analysis II. Translated from the 4th and 6th Russian editions by Roger Cooke and Octavio T. Paniagua
- Minimization of unsmooth functionals
- Noisy zeroth-order optimization for non-smooth saddle point problems
- Non-smooth setting of stochastic decentralized convex optimization problem over time-varying graphs
- Optimal order of accuracy of search algorithms in stochastic optimization
- Robust Stochastic Approximation Approach to Stochastic Programming
- Stochastic Estimation of the Maximum of a Regression Function
Cited in
(6)- Minimax efficient finite-difference stochastic gradient estimators using black-box function evaluations
- Black-box reductions for zeroth-order gradient algorithms to achieve lower query complexity
- A Zeroth-Order Proximal Stochastic Gradient Method for Weakly Convex Stochastic Optimization
- Stochastic adversarial noise in the ``black box optimization problem
- Accelerated zero-order SGD method for solving the black box optimization problem under ``overparametrization condition
- Accelerated zero-order SGD under high-order smoothness and overparameterized regime
This page was built for publication: The ``black-box optimization problem: zero-order accelerated stochastic method via kernel approximation
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6655796)
