activity
20192026
most citedAdaptive Stochastic Natural Gradient Method for One-Shot Neural Architecture Search

50 citations · 53 across the 5 of their papers we have counts for

collaborators

5 papers

cs.CL2026

BBOWP-Bench: Evaluating LLMs on Black-Box Optimization Word Problems

Yutaro Yamada, Kei Hiroshima, Nozomu Yoshinari +2

Formulating an optimization problem strongly affects the quality of the final solution, yet good formulations usually require substantial expertise. Recent studies have therefore e…

cs.LG2025

Surrogate Benchmarks for Model Merging Optimization

Rio Akizuki, Yuya Kudo, Nozomu Yoshinari +4

Model merging techniques aim to integrate the abilities of multiple models into a single model. Most model merging techniques have hyperparameters, and their setting affects the pe…

cs.AI2025

Bandit-Based Prompt Design Strategy Selection Improves Prompt Optimizers

Rin Ashizawa, Yoichi Hirose, Nozomu Yoshinari +2

Prompt optimization aims to search for effective prompts that enhance the performance of large language models (LLMs). Although existing prompt optimization methods have discovered…

cs.LG2021★ 3 cited

NAS-HPO-Bench-II: A Benchmark Dataset on Joint Optimization of Convolutional Neural Network Architecture and Training Hyperparameters

Yoichi Hirose, Nozomu Yoshinari, Shinichi Shirakawa

The benchmark datasets for neural architecture search (NAS) have been developed to alleviate the computationally expensive evaluation process and ensure a fair comparison. Recent N…

cs.LG2019★ 50 cited

Adaptive Stochastic Natural Gradient Method for One-Shot Neural Architecture Search

Youhei Akimoto, Shinichi Shirakawa, Nozomu Yoshinari +3

High sensitivity of neural architecture search (NAS) methods against their input such as step-size (i.e., learning rate) and search space prevents practitioners from applying them…