A kernel-based accelerated zero-order SGD method is introduced for convex stochastic optimization under higher-order smoothness and overparameterization, with convergence guarantees under deterministic and stochastic adversarial noise.
An Optimal Algorithm for Bandit and Zero-Order Convex Optimization with Two-Point Feedback
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
We consider the closely related problems of bandit convex optimization with two-point feedback, and zero-order stochastic convex optimization with two function evaluations per round. We provide a simple algorithm and analysis which is optimal for convex Lipschitz functions. This improves on \cite{dujww13}, which only provides an optimal result for smooth functions; Moreover, the algorithm and analysis are simpler, and readily extend to non-Euclidean problems. The algorithm is based on a small but surprisingly powerful modification of the gradient estimator.
fields
math.OC 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Accelerated zero-order SGD under high-order smoothness and overparameterized regime
A kernel-based accelerated zero-order SGD method is introduced for convex stochastic optimization under higher-order smoothness and overparameterization, with convergence guarantees under deterministic and stochastic adversarial noise.