Many evolutionary algorithms (EAs) take advantage of parallel evaluation of
candidates. However, if evaluation times vary significantly, many worker nodes
(i.e.,\ compute clients) are idle much of the time, waiting for the next
generation to be created. Evolutionary neural architecture search (ENAS), a
class of EAs that optimizes the architecture and hyperparameters of deep neural
networks, is particularly vulnerable to this issue. This paper proposes a
generic asynchronous evaluation strategy (AES) that is then adapted to work
with ENAS. AES increases throughput by maintaining a queue of upto $K$
individuals ready to be sent to the workers for evaluation and proceeding to
the next generation as soon as $M<<K$ individuals have been evaluated by the
workers. A suitable value for $M$ is determined experimentally, balancing
diversity and efficiency. To showcase the generality and power of AES, it was
first evaluated in 11-bit multiplexer design (a single-population verifiable
discovery task) and then scaled up to ENAS for image captioning (a
multi-population open-ended-optimization task). In both problems, a multifold
performance improvement was observed, suggesting that AES is a promising method
for parallelizing the evolution of complex systems with long and variable
evaluation times, such as those in ENAS.

该论文提出了一种通用的异步评估策略 (AES)，并将其适应于 Evolutionary neural architecture search (ENAS)，通过维护一个队列，以便在工人进行评估后尽快进入下一代，从而提高了吞吐量，并在多个问题中观察到了多倍性能改善。

深度神经网络架构的异步演化

Asynchronous Evolution of Deep Neural Network Architectures

In many real-world scenarios, decision makers seek to efficiently optimize
multiple competing objectives in a sample-efficient fashion. Multi-objective
Bayesian optimization (BO) is a common approach, but many of the
best-performing acquisition functions do not have known analytic gradients and
suffer from high computational overhead. We leverage recent advances in
programming models and hardware acceleration for multi-objective BO using
Expected Hypervolume Improvement (EHVI)---an algorithm notorious for its high
computational complexity. We derive a novel formulation of q-Expected
Hypervolume Improvement (qEHVI), an acquisition function that extends EHVI to
the parallel, constrained evaluation setting. qEHVI is an exact computation of
the joint EHVI of q new candidate points (up to Monte-Carlo (MC) integration
error). Whereas previous EHVI formulations rely on gradient-free acquisition
optimization or approximated gradients, we compute exact gradients of the MC
estimator via auto-differentiation, thereby enabling efficient and effective
optimization using first-order and quasi-second-order methods. Our empirical
evaluation demonstrates that qEHVI is computationally tractable in many
practical scenarios and outperforms state-of-the-art multi-objective BO
algorithms at a fraction of their wall time.

本文利用编程模型和硬件加速，提出了 q-Expected Hypervolume Improvement (qEHVI) 算法，使得计算多目标贝叶斯优化的探索函数能够适用于平行、受限制的计算情况，并通过自动微分方法，一个精确的求解 MC 积分误差的加速器来计算探索函数的性能和效果进行了实证研究。

针对并行多目标贝叶斯优化的可微分期望超体积改进方法

Differentiable Expected Hypervolume Improvement for Parallel  Multi-Objective Bayesian Optimization

In this paper, we consider the challenge of maximizing an unknown function f
for which evaluations are noisy and are acquired with high cost. An iterative
procedure uses the previous measures to actively select the next estimation of
f which is predicted to be the most useful. We focus on the case where the
function can be evaluated in parallel with batches of fixed size and analyze
the benefit compared to the purely sequential procedure in terms of cumulative
regret. We introduce the Gaussian Process Upper Confidence Bound and Pure
Exploration algorithm (GP-UCB-PE) which combines the UCB strategy and Pure
Exploration in the same batch of evaluations along the parallel iterations. We
prove theoretical upper bounds on the regret with batches of size K for this
procedure which show the improvement of the order of sqrt{K} for fixed
iteration cost over purely sequential versions. Moreover, the multiplicative
constants involved have the property of being dimension-free. We also confirm
empirically the efficiency of GP-UCB-PE on real and synthetic problems compared
to state-of-the-art competitors.

本文提出了一种采用高斯过程、UCB 策略和纯探索相结合的算法（GP-UCB-PE），旨在解决在评估带有噪声的未知函数时最大化其价值的问题，通过并行迭代的方式进行批次评估，并分析了批次评估与纯顺序评估在累积遗憾方面的差异。理论和实证验证表明，在固定迭代成本的情况下，批次大小为 K 的情况下，GP-UCB-PE 算法具有比纯顺序版本更小的遗憾界。