Scalability of optimization algorithms is a major challenge in coping with the ever-growing
size of optimization problems in a wide range of application areas from high-dimensional …

Reinforcement learning (RL) is a machine learning approach that trains agents to maximize
cumulative rewards through interactions with environments. The integration of RL with deep …

Computationally efficient algorithms for large-scale black-box optimization have become
increasingly important in recent years due to the growing complexity of engineering and …

The deep learning revolution has greatly been accelerated by the'hardware lottery': Recent
advances in modern hardware accelerators, compilers and the availability of open-source …

High-dimensional problems are ubiquitous in many fields, yet still remain challenging to be
solved. To tackle such problems with high effectiveness and efficiency, this article proposes …

Evolution Strategies (ES) have recently been demonstrated to be a viable alternative to
reinforcement learning (RL) algorithms on a set of challenging deep RL problems, including …

Hyperparameter Optimization in Black-box Image Processing using Differentiable Proxies
Page 1 Hyperparameter Optimization in Black-box Image Processing using Differentiable …

Evolution strategies are a class of evolutionary algorithms for black-box optimization and
achieve state-of-the-art performance on many benchmarks and real-world applications …

We consider the zeroth-order optimization problem in the huge-scale setting, where the
dimension of the problem is so large that performing even basic vector operations on the …

Proximal Policy Optimization (PPO) is a highly popular model-free reinforcement learning
(RL) approach. However, we observe that in a continuous action space, PPO can …