Bookmark Saya

Semantic Scholar Open Access 2021 5 sitasi

Improved Complexity Of Trust-Region Optimization For Zeroth-Order Stochastic Oracles with Adaptive Sampling

Yunsoo Ha S. Shashaani Quoc Tran-Dinh
Lihat Sumber DOI

Abstrak

We present an enhanced stochastic trust-region optimization with adaptive sampling (ASTRO-DF) in which optimizing an iteratively constructed local model on estimates of objective values with stochastic sample size guides the search. The noticeable feature is that the underdetermined quadratic model with a diagonal Hessian requires fewer function evaluations, which is particularly useful at high dimensions. This paper describes the enhanced algorithm in detail. It gives several theoretical results, including iteration complexity, and renders almost sure convergence guarantees. We report in our numerical experience the finite-time superiority of the enhanced ASTRO-DF over state-of-the-art using the SimOpt library.

Topik & Kata Kunci

Computer Science

Penulis (3)

Y

Yunsoo Ha

S

S. Shashaani

Q

Quoc Tran-Dinh

Format Sitasi

APA MLA BibTeX
Ha, Y., Shashaani, S., Tran-Dinh, Q. (2021). Improved Complexity Of Trust-Region Optimization For Zeroth-Order Stochastic Oracles with Adaptive Sampling. https://doi.org/10.1109/WSC52266.2021.9715529

Akses Cepat

PDF tidak tersedia langsung

Cek di sumber asli →
Lihat di Sumber doi.org/10.1109/WSC52266.2021.9715529
Informasi Jurnal
Tahun Terbit
2021
Bahasa
en
Total Sitasi
5×
Sumber Database
Semantic Scholar
DOI
10.1109/WSC52266.2021.9715529
Akses
Open Access ✓