Bayesian Optimization（BO）是一种优化昂贵对评估黑匣子功能的采样有效的方法。大多数BO方法忽略了评估成本如何在优化域中变化。然而，这些成本可以是高度异质的并且通常提前未知。这发生在许多实际设置中，例如机器学习算法或基于物理的仿真优化的超参数调整。此外，那些确认成本异质性的现有方法并不自然地适应总评估成本的预算限制。这种未知的成本和预算限制的组合引入了勘探开发权衡的新维度，其中关于成本的学习成本本身。现有方法没有原因地理由以原则的方式对此问题的各种权衡，经常导致性能不佳。我们通过证明，每单位成本的预期改进和预期改善，可以使这两个最广泛使用的采购职能在实践中的预期改进和预期的索赔可以是任意劣等的。为了克服现有方法的缺点，我们提出了预算的多步预期改进，是一个非近视收购函数，以概括为异质和未知评估成本的古典预期改进。最后，我们表明我们的采集功能优于各种合成和实际问题的现有方法。
translated by 谷歌翻译
本文探讨了超线性增长趋势的环境影响，从整体角度来看，跨越数据，算法和系统硬件。我们通过在行业规模机器学习用例中检查模型开发周期来表征AI计算的碳足迹，同时考虑系统硬件的生命周期。进一步迈出一步，我们捕获AI计算的操作和制造碳足迹，并为硬件 - 软件设计和尺度优化的结束分析以及如何帮助降低AI的整体碳足迹。根据行业经验和经验教训，我们分享关键挑战，并在AI的许多方面上绘制了重要的发展方向。我们希望本文提出的关键信息和见解能够激发社区以环保的方式推进AI领域。
translated by 谷歌翻译
许多现实世界的科学和工业应用都需要优化多个竞争的黑盒目标。当目标是昂贵的评估时，多目标贝叶斯优化（BO）是一种流行的方法，因为其样品效率很高。但是，即使有了最近的方法学进步，大多数现有的多目标BO方法在具有超过几十个参数的搜索空间上的表现较差，并且依赖于随着观测值数量进行立方体扩展的全局替代模型。在这项工作中，我们提出了Morbo，这是高维搜索空间上多目标BO的可扩展方法。 Morbo通过使用协调策略并行在设计空间的多个局部区域中执行BO来确定全球最佳解决方案。我们表明，Morbo在几种高维综合问题和现实世界应用中的样品效率中的最新效率显着提高，包括光学显示设计问题和146和222参数的车辆设计问题。在这些问题上，如果现有的BO算法无法扩展和表现良好，Morbo为从业者提供了刻度级别的效率，则在当前方法上可以提高样本效率。
translated by 谷歌翻译
Bayesian optimization provides sample-efficient global optimization for a broad range of applications, including automatic machine learning, engineering, physics, and experimental design. We introduce BOTORCH, a modern programming framework for Bayesian optimization that combines Monte-Carlo (MC) acquisition functions, a novel sample average approximation optimization approach, autodifferentiation, and variance reduction techniques. BOTORCH's modular design facilitates flexible specification and optimization of probabilistic models written in PyTorch, simplifying implementation of new acquisition functions. Our approach is backed by novel theoretical convergence results and made practical by a distinctive algorithmic foundation that leverages fast predictive distributions, hardware acceleration, and deterministic optimization. We also propose a novel "one-shot" formulation of the Knowledge Gradient, enabled by a combination of our theoretical and software contributions. In experiments, we demonstrate the improved sample efficiency of BOTORCH relative to other popular libraries.34th Conference on Neural Information Processing Systems (NeurIPS 2020),
translated by 谷歌翻译
Neural compression offers a domain-agnostic approach to creating codecs for lossy or lossless compression via deep generative models. For sequence compression, however, most deep sequence models have costs that scale with the sequence length rather than the sequence complexity. In this work, we instead treat data sequences as observations from an underlying continuous-time process and learn how to efficiently discretize while retaining information about the full sequence. As a consequence of decoupling sequential information from its temporal discretization, our approach allows for greater compression rates and smaller computational complexity. Moreover, the continuous-time approach naturally allows us to decode at different time intervals. We empirically verify our approach on multiple domains involving compression of video and motion capture sequences, showing that our approaches can automatically achieve reductions in bit rates by learning how to discretize.
translated by 谷歌翻译
This paper extends quantile factor analysis to a probabilistic variant that incorporates regularization and computationally efficient variational approximations. By means of synthetic and real data experiments it is established that the proposed estimator can achieve, in many cases, better accuracy than a recently proposed loss-based estimator. We contribute to the literature on measuring uncertainty by extracting new indexes of low, medium and high economic policy uncertainty, using the probabilistic quantile factor methodology. Medium and high indexes have clear contractionary effects, while the low index is benign for the economy, showing that not all manifestations of uncertainty are the same.
translated by 谷歌翻译
We introduce organism networks, which function like a single neural network but are composed of several neural particle networks; while each particle network fulfils the role of a single weight application within the organism network, it is also trained to self-replicate its own weights. As organism networks feature vastly more parameters than simpler architectures, we perform our initial experiments on an arithmetic task as well as on simplified MNIST-dataset classification as a collective. We observe that individual particle networks tend to specialise in either of the tasks and that the ones fully specialised in the secondary task may be dropped from the network without hindering the computational accuracy of the primary task. This leads to the discovery of a novel pruning-strategy for sparse neural networks
translated by 谷歌翻译
Overfitting is a problem in Convolutional Neural Networks (CNN) that causes poor generalization of models on unseen data. To remediate this problem, many new and diverse data augmentation methods (DA) have been proposed to supplement or generate more training data, and thereby increase its quality. In this work, we propose a new data augmentation algorithm: VoronoiPatches (VP). We primarily utilize non-linear recombination of information within an image, fragmenting and occluding small information patches. Unlike other DA methods, VP uses small convex polygon-shaped patches in a random layout to transport information around within an image. Sudden transitions created between patches and the original image can, optionally, be smoothed. In our experiments, VP outperformed current DA methods regarding model variance and overfitting tendencies. We demonstrate data augmentation utilizing non-linear re-combination of information within images, and non-orthogonal shapes and structures improves CNN model robustness on unseen data.
translated by 谷歌翻译
An optimal delivery of arguments is key to persuasion in any debate, both for humans and for AI systems. This requires the use of clear and fluent claims relevant to the given debate. Prior work has studied the automatic assessment of argument quality extensively. Yet, no approach actually improves the quality so far. Our work is the first step towards filling this gap. We propose the task of claim optimization: to rewrite argumentative claims to optimize their delivery. As an initial approach, we first generate a candidate set of optimized claims using a sequence-to-sequence model, such as BART, while taking into account contextual information. Our key idea is then to rerank generated candidates with respect to different quality metrics to find the best optimization. In automatic and human evaluation, we outperform different reranking baselines on an English corpus, improving 60% of all claims (worsening 16% only). Follow-up analyses reveal that, beyond copy editing, our approach often specifies claims with details, whereas it adds less evidence than humans do. Moreover, its capabilities generalize well to other domains, such as instructional texts.
translated by 谷歌翻译
We consider distributed learning in the presence of slow and unresponsive worker nodes, referred to as stragglers. In order to mitigate the effect of stragglers, gradient coding redundantly assigns partial computations to the worker such that the overall result can be recovered from only the non-straggling workers. Gradient codes are designed to tolerate a fixed number of stragglers. Since the number of stragglers in practice is random and unknown a priori, tolerating a fixed number of stragglers can yield a sub-optimal computation load and can result in higher latency. We propose a gradient coding scheme that can tolerate a flexible number of stragglers by carefully concatenating gradient codes for different straggler tolerance. By proper task scheduling and small additional signaling, our scheme adapts the computation load of the workers to the actual number of stragglers. We analyze the latency of our proposed scheme and show that it has a significantly lower latency than gradient codes.
translated by 谷歌翻译