Theoretical Analysis of Explicit Averaging and Novel Sign Averaging in Comparison-Based Search

no code implementations • 25 Jan 2024 • Daiki Morinaga, Youhei Akimoto

Explicit averaging takes the sample average of noisy objective function values and is widely used as a simple and versatile noise-handling technique.

Convergence rate of the (1+1)-evolution strategy on locally strongly convex functions with lipschitz continuous gradient and their monotonic transformations

no code implementations • 26 Sep 2022 • Daiki Morinaga, Kazuto Fukuchi, Jun Sakuma, Youhei Akimoto

Evolution strategy (ES) is one of promising classes of algorithms for black-box continuous optimization.

Convergence Rate of the (1+1)-Evolution Strategy with Success-Based Step-Size Adaptation on Convex Quadratic Functions

no code implementations • 2 Mar 2021 • Daiki Morinaga, Kazuto Fukuchi, Jun Sakuma, Youhei Akimoto

The convergence rate, that is, the decrease rate of the distance from a search point $m_t$ to the optimal solution $x^*$, is proven to be in $O(\exp( - L / \mathrm{Tr}(H) ))$, where $L$ is the smallest eigenvalue of $H$ and $\mathrm{Tr}(H)$ is the trace of $H$.