In this paper, we propose a bootstrap method applied to massive data processed distributedly in a large number of machines. This new method is computationally efficient in that we bootstrap on the master machine without over-resampling, typically required by existing methods \cite{kleiner2014scalable,sengupta2016subsampled}, while provably achieving optimal statistical efficiency with minimal communication. Our method does not require repeatedly re-fitting the model but only applies multiplier bootstrap in the master machine on the gradients received from the worker machines. Simulations validate our theory.

Despite progress in training neural networks for lossy image compression, current approaches fail to maintain both perceptual quality and high-level features at very low bitrates. Encouraged by recent success in learning discrete representations with Vector Quantized Variational AutoEncoders (VQ-VAEs), we motivate the use of a hierarchy of VQ-VAEs to attain high factors of compression. We show that the combination of quantization and hierarchical latent structure aids likelihood-based image compression. This leads us to introduce a more probabilistic framing of the VQ-VAE, of which previous work is a limiting case. Our hierarchy produces a Markovian series of latent variables that reconstruct high-quality images which retain semantically meaningful features. These latents can then be further used to generate realistic samples. We provide qualitative and quantitative evaluations of reconstructions and samples on the CelebA and MNIST datasets.

Optimizing a given metric is a central aspect of most current AI approaches, yet overemphasizing metrics leads to manipulation, gaming, a myopic focus on short-term goals, and other unexpected negative consequences. This poses a fundamental contradiction for AI development. Through a series of real-world case studies, we look at various aspects of where metrics go wrong in practice and aspects of how our online environment and current business practices are exacerbating these failures. Finally, we propose a framework towards mitigating the harms caused by overemphasis of metrics within AI by: (1) using a slate of metrics to get a fuller and more nuanced picture, (2) combining metrics with qualitative accounts, and (3) involving a range of stakeholders, including those who will be most impacted.

We introduce a method called TrackIn that computes the influence of a training example on a prediction made by the model, by tracking how the loss on the test point changes during the training process whenever the training example of interest was utilized. We provide a scalable implementation of TrackIn via a combination of a few key ideas: (a) a first-order approximation to the exact computation, (b) using random projections to speed up the computation of the first-order approximation for large models, (c) using saved checkpoints of standard training procedures, and (d) cherry-picking layers of a deep neural network. An experimental evaluation shows that TrackIn is more effective in identifying mislabelled training examples than other related methods such as influence functions and representer points. We also discuss insights from applying the method on vision, regression and natural language tasks.

Planning for hybrid systems is important for dealing with real-world applications, and PDDL+ supports this representation of domains with mixed discrete and continuous dynamics. In this paper we present a new approach for planning for hybrid systems, based on encoding the planning problem as a Satisfiability Modulo Theories (SMT) formula. This is the first SMT encoding that can handle the whole set of PDDL+ features (including processes and events), and is implemented in the planner SMTPlan. SMTPlan not only covers the full semantics of PDDL+, but can also deal with non-linear polynomial continuous change without discretization. This allows it to generate plans with non-linear dynamics that are correct-by-construction. The encoding is based on the notion of happenings, and can be applied on domains with nonlinear continuous change. We describe the encoding in detail and provide in-depth examples. We apply this encoding in an iterative deepening planning algorithm. Experimental results show that the approach dramatically outperforms existing work in finding plans for PDDL+ problems. We also present experiments which explore the performance of the proposed approach on temporal planning problems, showing that the scalability of the approach is limited by the size of the discrete search space. We further extend the encoding to include planning with control parameters. The extended encoding allows the definition of actions to include infinite domain parameters, called control parameters. We present experiments on a set of problems with control parameters to demonstrate the positive effect they provide to the approach of planning via SMT.

Ensembles, where multiple neural networks are trained individually and their predictions are averaged, have been shown to be widely successful for improving both the accuracy and predictive uncertainty of single neural networks. However, an ensemble's cost for both training and testing increases linearly with the number of networks, which quickly becomes untenable. In this paper, we propose BatchEnsemble, an ensemble method whose computational and memory costs are significantly lower than typical ensembles. BatchEnsemble achieves this by defining each weight matrix to be the Hadamard product of a shared weight among all ensemble members and a rank-one matrix per member. Unlike ensembles, BatchEnsemble is not only parallelizable across devices, where one device trains one member, but also parallelizable within a device, where multiple ensemble members are updated simultaneously for a given mini-batch. Across CIFAR-10, CIFAR-100, WMT14 EN-DE/EN-FR translation, and out-of-distribution tasks, BatchEnsemble yields competitive accuracy and uncertainties as typical ensembles; the speedup at test time is 3X and memory reduction is 3X at an ensemble of size 4. We also apply BatchEnsemble to lifelong learning, where on Split-CIFAR-100, BatchEnsemble yields comparable performance to progressive neural networks while having a much lower computational and memory costs. We further show that BatchEnsemble can easily scale up to lifelong learning on Split-ImageNet which involves 100 sequential learning tasks.

This paper proposes a simple yet effective method for human action recognition in video. The proposed method separately extracts local appearance and motion features using state-of-the-art three-dimensional convolutional neural networks from sampled snippets of a video. These local features are then concatenated to form global representations which are then used to train a linear SVM to perform the action classification using full context of the video, as partial context as used in previous works. The videos undergo two simple proposed preprocessing techniques, optical flow scaling and crop filling. We perform an extensive evaluation on three common benchmark dataset to empirically show the benefit of the SVM, and the two preprocessing steps.

It is an active topic to investigate the schemes based on machine learning (ML) methods for detecting pulsars as the data volume growing exponentially in modern surveys. To improve the detection performance, input features into an ML model should be investigated specifically. In the existing pulsar detection researches based on ML methods, there are mainly two kinds of feature designs: the empirical features and statistical features. Due to the combinational effects from multiple features, however, there exist some redundancies and even irrelevant components in the available features, which can reduce the accuracy of a pulsar detection model. Therefore, it is essential to select a subset of relevant features from a set of available candidate features and known as {\itshape feature selection.} In this work, two feature selection algorithms ----\textit{Grid Search} (GS) and \textit{Recursive Feature Elimination} (RFE)---- are proposed to improve the detection performance by removing the redundant and irrelevant features. The algorithms were evaluated on the Southern High Time Resolution University survey (HTRU-S) with five pulsar detection models. The experimental results verify the effectiveness and efficiency of our proposed feature selection algorithms. By the GS, a model with only two features reach a recall rate as high as 99\% and a false positive rate (FPR) as low as 0.65\%; By the RFE, another model with only three features achieves a recall rate 99\% and an FPR of 0.16\% in pulsar candidates classification. Furthermore, this work investigated the number of features required as well as the misclassified pulsars by our models.

Fine-tuning from pre-trained ImageNet models has become the de-facto standard for various computer vision tasks. Current practices for fine-tuning typically involve selecting an ad-hoc choice of hyperparameters and keeping them fixed to values normally used for training from scratch. This paper re-examines several common practices of setting hyperparameters for fine-tuning. Our findings are based on extensive empirical evaluation for fine-tuning on various transfer learning benchmarks. (1) While prior works have thoroughly investigated learning rate and batch size, momentum for fine-tuning is a relatively unexplored parameter. We find that the value of momentum also affects fine-tuning performance and connect it with previous theoretical findings. (2) Optimal hyperparameters for fine-tuning, in particular, the effective learning rate, are not only dataset dependent but also sensitive to the similarity between the source domain and target domain. This is in contrast to hyperparameters for training from scratch. (3) Reference-based regularization that keeps models close to the initial model does not necessarily apply for "dissimilar" datasets. Our findings challenge common practices of fine-tuning and encourages deep learning practitioners to rethink the hyperparameters for fine-tuning.

Building machine learning models requires a suite of tools for interpretation, understanding, and debugging. Many existing methods have been proposed, but it can still be difficult to probe for examples which communicate model behaviour. We introduce Bayes-Probe, a model inspection method for analyzing neural networks by generating distribution-conforming examples of known prediction confidence. By selecting appropriate distributions and confidence prediction values, Bayes-Probe can be used to synthesize ambivalent predictions, uncover in-distribution adversarial examples, and understand novel-class extrapolation and domain adaptation behaviours. Bayes-Probe is model agnostic, requiring only a data generator and classifier prediction. We use Bayes-Probe to analyze models trained on both procedurally-generated data (CLEVR) and organic data (MNIST and Fashion-MNIST). Code is available at https://github.com/serenabooth/Bayes-Probe.