This paper develops several average-case reduction techniques to show new hardness results for three central high-dimensional statistics problems, implying a statistical-computational gap induced by robustness, a detection-recovery gap and a universality principle for these gaps. A main feature of our approach is to map to these problems via a common intermediate problem that we introduce, which we call Imbalanced Sparse Gaussian Mixtures. We assume the planted clique conjecture for a version of the planted clique problem where the position of the planted clique is mildly constrained, and from this obtain the following computational lower bounds: (1) a $k$-to-$k^2$ statistical-computational gap for robust sparse mean estimation, providing the first average-case evidence for a conjecture of Li (2017) and Balakrishnan et al. (2017); (2) a tight lower bound for semirandom planted dense subgraph, which shows that a semirandom adversary shifts the detection threshold in planted dense subgraph to the conjectured recovery threshold; and (3) a universality principle for $k$-to-$k^2$ gaps in a broad class of sparse mixture problems that includes many natural formulations such as the spiked covariance model. Our main approach is to introduce several average-case techniques to produce structured and Gaussianized versions of an input graph problem, and then to rotate these high-dimensional Gaussians by matrices carefully constructed from hyperplanes in $\mathbb{F}_r^t$. For our universality result, we introduce a new method to perform an algorithmic change of measure tailored to sparse mixtures. We also provide evidence that the mild promise in our variant of planted clique does not change the complexity of the problem.

This paper introduces a new dataset called "ToyADMOS" designed for anomaly detection in machine operating sounds (ADMOS). To the best our knowledge, no large-scale datasets are available for ADMOS, although large-scale datasets have contributed to recent advancements in acoustic signal processing. This is because anomalous sound data are difficult to collect. To build a large-scale dataset for ADMOS, we collected anomalous operating sounds of miniature machines (toys) by deliberately damaging them. The released dataset consists of three sub-datasets for machine-condition inspection, fault diagnosis of machines with geometrically fixed tasks, and fault diagnosis of machines with moving tasks. Each sub-dataset includes over 180 hours of normal machine-operating sounds and over 4,000 samples of anomalous sounds collected with four microphones at a 48-kHz sampling rate. The dataset is freely available for download at https://github.com/YumaKoizumi/ToyADMOS-dataset

Classification-as-a-Service (CaaS) is widely deployed today in machine intelligence stacks for a vastly diverse set of applications including anything from medical prognosis to computer vision tasks to natural language processing to identity fraud detection. The computing power required for training complex models on large datasets to perform inference to solve these problems can be very resource-intensive. A CaaS provider may cheat a customer by fraudulently bypassing expensive training procedures in favor of weaker, less computationally-intensive algorithms which yield results of reduced quality. Given a classification service supplier $S$, intermediary CaaS provider $P$ claiming to use $S$ as a classification backend, and customer $C$, our work addresses the following questions: (i) how can $P$'s claim to be using $S$ be verified by $C$? (ii) how might $S$ make performance guarantees that may be verified by $C$? and (iii) how might one design a decentralized system that incentivizes service proofing and accountability? To this end, we propose a variety of methods for $C$ to evaluate the service claims made by $P$ using probabilistic performance metrics, instance seeding, and steganography. We also propose a method of measuring the robustness of a model using a blackbox adversarial procedure, which may then be used as a benchmark or comparison to a claim made by $S$. Finally, we propose the design of a smart contract-based decentralized system that incentivizes service accountability to serve as a trusted Quality of Service (QoS) auditor.

The learning rate warmup heuristic achieves remarkable success in stabilizing training, accelerating convergence and improving generalization for adaptive stochastic optimization algorithms like RMSprop and Adam. Here, we study its mechanism in details. Pursuing the theory behind warmup, we identify a problem of the adaptive learning rate (i.e., it has problematically large variance in the early stage), suggest warmup works as a variance reduction technique, and provide both empirical and theoretical evidence to verify our hypothesis. We further propose RAdam, a new variant of Adam, by introducing a term to rectify the variance of the adaptive learning rate. Extensive experimental results on image classification, language modeling, and neural machine translation verify our intuition and demonstrate the effectiveness and robustness of our proposed method. All implementations are available at: https://github.com/LiyuanLucasLiu/RAdam.

Waveform physiological data is important in the treatment of critically ill patients in the intensive care unit. Such recordings are susceptible to artefacts, which must be removed before the data can be re-used for alerting or reprocessed for other clinical or research purposes. The current gold-standard is human annotation, which is painstaking when recordings span many days and has question marks over its reproducibility. In this work, we present DeepClean; a prototype self-supervised artefact detection system using a convolutional variational autoencoder deep neural network that avoids costly manual annotation, requiring only easily-obtained `good' data for training. For a test case with invasive arterial blood pressure, we demonstrate that our algorithm can detect the presence of an artefact within a 10-second sample of data with sensitivity and specificity around 90\%. Furthermore, DeepClean was able to identify regions of artefact within such samples with high accuracy and we show that it significantly outperforms a baseline principle component analysis approach in both signal reconstruction and artefact detection. DeepClean learns a generative model and therefore may also be used for imputation of missing data. Accurate removal of artefacts reduces both bias and uncertainty in clinical assessment and the false negative rate of intensive care unit alarms, and is therefore a key component in providing optimal clinical care.

Users increasingly rely on social media feeds for consuming daily information. The items in a feed, such as news, questions, songs, etc., usually result from the complex interplay of a user's social contacts, her interests and her actions on the platform. The relationship of the user's own behavior and the received feed is often puzzling, and many users would like to have a clear explanation on why certain items were shown to them. Transparency and explainability are key concerns in the modern world of cognitive overload, filter bubbles, user tracking, and privacy risks. This paper presents FAIRY, a framework that systematically discovers, ranks, and explains relationships between users' actions and items in their social media feeds. We model the user's local neighborhood on the platform as an interaction graph, a form of heterogeneous information network constructed solely from information that is easily accessible to the concerned user. We posit that paths in this interaction graph connecting the user and her feed items can act as pertinent explanations for the user. These paths are scored with a learning-to-rank model that captures relevance and surprisal. User studies on two social platforms demonstrate the practical viability and user benefits of the FAIRY method.

Recently, several authors have advocated the use of rule learning algorithms to model multi-label data, as rules are interpretable and can be comprehended, analyzed, or qualitatively evaluated by domain experts. Many rule learning algorithms employ a heuristic-guided search for rules that model regularities contained in the training data and it is commonly accepted that the choice of the heuristic has a significant impact on the predictive performance of the learner. Whereas the properties of rule learning heuristics have been studied in the realm of single-label classification, there is no such work taking into account the particularities of multi-label classification. This is surprising, as the quality of multi-label predictions is usually assessed in terms of a variety of different, potentially competing, performance measures that cannot all be optimized by a single learner at the same time. In this work, we show empirically that it is crucial to trade off the consistency and coverage of rules differently, depending on which multi-label measure should be optimized by a model. Based on these findings, we emphasize the need for configurable learners that can flexibly use different heuristics. As our experiments reveal, the choice of the heuristic is not straight-forward, because a search for rules that optimize a measure locally does usually not result in a model that maximizes that measure globally.

Continuous reinforcement learning such as DDPG and A3C are widely used in robot control and autonomous driving. However, both methods have theoretical weaknesses. While DDPG cannot control noises in the control process, A3C does not satisfy the continuity conditions under the Gaussian policy. To address these concerns, we propose a new continues reinforcement learning method based on stochastic differential equations and we call it Incremental Reinforcement Learning (IRL). This method not only guarantees the continuity of actions within any time interval, but controls the variance of actions in the training process. In addition, our method does not assume Markov control in agents' action control and allows agents to predict scene changes for action selection. With our method, agents no longer passively adapt to the environment. Instead, they positively interact with the environment for maximum rewards.

This technology has provided near-human performance on many prediction tasks Geirhos et al. (2017), and left deep marks on entire fields of business and science, to the extent that large computational and engineering efforts are routinely dedicated to neural network training and optimization Dean et al. (2012). However, neural networks are often criticized for their complexity and lack of interpretability. There are many arguments that favor simple models over more complex ones. In many applications (including healthcare Ahmad et al. (2018), Cabitza et al. (2017), insurance and finance Song et al. (2014), Thomas et al. (2002), flight control and other safety-critical tasks (Kurd et al. (2007)), interpretation of the underlying model is a critical requirement. On the other hand, traditional statistical tools, including simple linear models, remain popular because they are simple and explainable, with cheap, efficient computational tools being readily available.

From massive face-recognition-based surveillance and machine-learning-based decision systems predicting crime recidivism rates, to the move towards automated health diagnostic systems, artificial intelligence (AI) is being used in scenarios that have serious consequences in people's lives. However, this rapid permeation of AI into society has not been accompanied by a thorough investigation of the sociopolitical issues that cause certain groups of people to be harmed rather than advantaged by it. For instance, recent studies have shown that commercial face recognition systems have much higher error rates for dark skinned women while having minimal errors on light skinned men. A 2016 ProPublica investigation uncovered that machine learning based tools that assess crime recidivism rates in the US are biased against African Americans. Other studies show that natural language processing tools trained on newspapers exhibit societal biases (e.g. finishing the analogy "Man is to computer programmer as woman is to X" by homemaker). At the same time, books such as Weapons of Math Destruction and Automated Inequality detail how people in lower socioeconomic classes in the US are subjected to more automated decision making tools than those who are in the upper class. Thus, these tools are most often used on people towards whom they exhibit the most bias. While many technical solutions have been proposed to alleviate bias in machine learning systems, we have to take a holistic and multifaceted approach. This includes standardization bodies determining what types of systems can be used in which scenarios, making sure that automated decision tools are created by people from diverse backgrounds, and understanding the historical and political factors that disadvantage certain groups who are subjected to these tools.