Dec 7, 2013 · Optimal rates for zero-order convex optimization: the power of two function evaluations. We consider derivative-free algorithms for stochastic ...
In Section III, we provide information-theoretic minimax lower bounds on the best possible convergence rates, uniformly over all schemes based on function ...
Focusing on nonasymptotic bounds on convergence rates, it is shown that if pairs of function values are available, algorithms for d-dimensional optimization ...
May 1, 2015 · Focusing on nonasymptotic bounds on convergence rates, we show that if pairs of function values are available, algorithms for d-dimensional ...
Mar 5, 2015 · Abstract: We consider derivative-free algorithms for stochastic and nonstochastic convex optimization problems that use only function values ...
Some of the difficulties inherent in optimization using only a single function evaluation are alleviated when the function F(·; x) can be evaluated at two ...
“Optimal rates for zero-order convex optimization: The power of two function evaluations,” 2015. stochastic, 2-point and multi-point, minimax lower bound.
Nov 26, 2020 · We focus on the stochastic optimization setting, and present convergence rate of zero-order algorithms for both smooth and non-smooth convex ...
Optimal rates for zero-order opti- mization: the power of two function evaluations. Information Theory, IEEE Transactions on, 61(5):2788–2806, May 2015. 10 ...
Feb 1, 2023 · Optimal rates for zero-order convex optimization: The power of two function evaluations. IEEE Transactions on Information Theory, 61(5):2788 ...