Neural Architecture Search (NAS) has shown excellent results in designing
architectures for computer vision problems. NAS alleviates the need for
human-defined settings by automating architecture design and engineering.
However, NAS methods tend to be slow, as they require large amounts of GPU
computation. This bottleneck is mainly due to the performance estimation
strategy, which requires the evaluation of the generated architectures, mainly
by training them, to update the sampler method. In this paper, we propose
EPE-NAS, an efficient performance estimation strategy, that mitigates the
problem of evaluating networks, by scoring untrained networks and creating a
correlation with their trained performance. We perform this process by looking
at intra and inter-class correlations of an untrained network. We show that
EPE-NAS can produce a robust correlation and that by incorporating it into a
simple random sampling strategy, we are able to search for competitive
networks, without requiring any training, in a matter of seconds using a single
GPU. Moreover, EPE-NAS is agnostic to the search method, since it focuses on
the evaluation of untrained networks, making it easy to integrate into almost
any NAS method.

本文提出了一种高效的性能评估策略 - EPE-NAS，通过评分未训练的神经网络并与其训练后的表现建立相关性，旨在解决神经架构搜索中耗时的性能估计问题，进而能够在几秒钟内使用单个 GPU 进行搜索。此方法仅需使用简单的随机取样策略，可支持几乎所有 NAS 方法的集成。

EPE-NAS: 用于神经架构搜索的高效性能估计方法

EPE-NAS: Efficient Performance Estimation Without Training for Neural  Architecture Search

For extended periods of time, sequence generation models rely on beam search
algorithm to generate output sequence. However, the correctness of beam search
degrades when the a model is over-confident about a suboptimal prediction. In
this paper, we propose to perform minimum Bayes-risk (MBR) decoding for some
extra steps at a later stage. In order to speed up MBR decoding, we compute the
Bayes risks on GPU in batch mode. In our experiments, we found that MBR
reranking works with a large beam size. Later-stage MBR decoding is shown to
outperform simple MBR reranking in machine translation tasks.

本研究提出使用最小贝叶斯风险编解码技术 (MBR) 来消除基于 beam search 算法的模型自信度导致的输出错误，并使用 GPU 批量计算贝叶斯风险值以加速解码，并在机器翻译中验证后期 MBR 解码的优越性。