This paper introduces Meta-Q-Learning (MQL), a new off-policy algorithm for meta-Reinforcement Learning (meta-RL). MQL builds upon three simple ideas. First, we show that Q-learning is competitive with state of the art meta-RL algorithms if given access to a context variable that is a representation of the past trajectory. Second, using a multi-task objective to maximize the average reward across the training tasks is an effective method to meta-train RL policies. Third, past data from the meta-training replay buffer can be recycled to adapt the policy on a new task using off-policy updates. MQL draws upon ideas in propensity estimation to do so and thereby amplifies the amount of available data for adaptation. Experiments on standard continuous-control benchmarks suggest that MQL compares favorably with state of the art meta-RL algorithms.

Deep Learning has established itself to be a common occurrence in the business lexicon. The unprecedented success of deep learning in recent years can be attributed to: abundance of data, availability of gargantuan compute capabilities offered by GPUs, and adoption of open-source philosophy by the researchers and industry. Deep neural networks can be decomposed into a series of different operators. MIOpen, AMD's open-source deep learning primitives library for GPUs, provides highly optimized implementations of such operators, shielding researchers from internal implementation details and hence, accelerating the time to discovery. This paper introduces MIOpen and provides details about the internal workings of the library and supported features. MIOpen innovates on several fronts, such as implementing fusion to optimize for memory bandwidth and GPU launch overheads, providing an auto-tuning infrastructure to overcome the large design space of problem configurations, and implementing different algorithms to optimize convolutions for different filter and input sizes. MIOpen is one of the first libraries to publicly support the bfloat16 data-type for convolutions, allowing efficient training at lower precision without the loss of accuracy.

Variational inference has become one of the most widely used methods in latent variable modeling. In its basic form, variational inference employs a fully factorized variational distribution and minimizes its KL divergence to the posterior. As the minimization can only be carried out approximately, this approximation induces a bias. In this paper, we revisit perturbation theory as a powerful way of improving the variational approximation. Perturbation theory relies on a form of Taylor expansion of the log marginal likelihood, vaguely in terms of the log ratio of the true posterior and its variational approximation. While first order terms give the classical variational bound, higher-order terms yield corrections that tighten it. However, traditional perturbation theory does not provide a lower bound, making it inapt for stochastic optimization. In this paper, we present a similar yet alternative way of deriving corrections to the ELBO that resemble perturbation theory, but that result in a valid bound. We show in experiments on Gaussian Processes and Variational Autoencoders that the new bounds are more mass covering, and that the resulting posterior covariances are closer to the true posterior and lead to higher likelihoods on held-out data.

In this work we introduce a semi-supervised approach to the voice conversion problem, in which speech from a source speaker is converted into speech of a target speaker. The proposed method makes use of both parallel and non-parallel utterances from the source and target simultaneously during training. This approach can be used to extend existing parallel data voice conversion systems such that they can be trained with semi-supervision. We show that incorporating semi-supervision improves the voice conversion performance compared to fully supervised training when the number of parallel utterances is limited as in many practical applications. Additionally, we find that increasing the number non-parallel utterances used in training continues to improve performance when the amount of parallel training data is held constant.

Department of Data Science, Medical Data Science Ltd., Bulgaria Editor: Abstract Implied posterior probability of a given model (say, Support Vector Machines (SVM)) at a point x is an estimate of the class posterior probability pertaining to the class of functions of the model applied to a given dataset. It can be regarded as a score (or estimate) for the true posterior probability, which can then be calibrated/mapped onto expected (non-implied by the model) posterior probability implied by the underlying functions, which have generated the data. In this tutorial we discuss how to compute implied posterior probabilities of SVMs for the binary classification case as well as how to calibrate them via a standard method of isotonic regression. Keywords: Posterior probability, Bayes rule, Classification, SVMs 1. Introduction The implied posterior probability method for estimating class posterior probability has recently been proposed (Nalbantov and Ivanov, 2019). The method provides a score (or estimate) for the true posterior probability, which can then be calibrated/mapped onto expected (non-implied by the model) posterior probability implied by the underlying functions, which have generated the data. The main difference with other methods for solving this problem is the non-reliance on the original model built on the data to estimate posterior probabilities for points which do not belong to the separation surface of the model. Rather, the estimates are based on the class of functions used to build the (original) model, as applied to different versions of the dataset, where the relative weight of the instances varies between the classes. For each such relative weight a different model is built, which is relevant for the estimation of a particular value of the posterior probability.

In many review classification applications, a fine-grained analysis of the reviews is desirable, because different segments (e.g., sentences) of a review may focus on different aspects of the entity in question. However, training supervised models for segment-level classification requires segment labels, which may be more difficult or expensive to obtain than review labels. In this paper, we employ Multiple Instance Learning (MIL) and use only weak supervision in the form of a single label per review. First, we show that when inappropriate MIL aggregation functions are used, then MIL-based networks are outperformed by simpler baselines. Second, we propose a new aggregation function based on the sigmoid attention mechanism and show that our proposed model outperforms the state-of-the-art models for segment-level sentiment classification (by up to 9.8% in F1). Finally, we highlight the importance of fine-grained predictions in an important public-health application: finding actionable reports of foodborne illness. We show that our model achieves 48.6% higher recall compared to previous models, thus increasing the chance of identifying previously unknown foodborne outbreaks.

Gaussian processes are ubiquitous in nature and engineering. A case in point is a class of neural networks in the infinite-width limit, whose priors correspond to Gaussian processes. Here we perturbatively extend this correspondence to finite-width neural networks, yielding non-Gaussian processes as priors. The methodology developed herein allows us to track the flow of preactivation distributions by progressively integrating out random variables from lower to higher layers, reminiscent of renormalization-group flow. We further develop a perturbative procedure to perform Bayesian inference with weakly non-Gaussian priors.

October 1, 2019 Abstract We focus on the problem of black-box adversarial attacks, where the aim is to generate adversarial examples using information limited to loss function evaluations of input-output pairs. We use Bayesian optimization (BO) to specifically cater to scenarios involving low query budgets to develop query efficient adversarial attacks. We alleviate the issues surrounding BO in regards to optimizing high dimensional deep learning models by effective dimension upsampling techniques. Our proposed approach achieves performance comparable to the state of the art black-box adversarial attacks albeit with a much lower average query count. In particular, in low query budget regimes, our proposed method reduces the query count up to 80% with respect to the state of the art methods. 1 Introduction Neural networks are now well-known to be vulnerable to adversarial examples: additive perturbations that, when applied to the input, change the network's output classification [9]. Work investigating this lack of robustness to adversarial examples often takes the form of a back-and-forth between newly proposed adversarial attacks, methods for quickly and efficiently crafting adversarial examples, and corresponding defenses that modify the classifier at either training or test time to improve robustness. The most successful adversarial attacks use gradient-based optimization methods [9, 17], which require complete knowledge of the architecture and parameters of the target network; this assumption is referred to as the white-box attack setting.

Training neural networks to be certifiably robust is a powerful defense against adversarial attacks. However, while promising, state-of-the-art results with certified training are far from satisfactory. Currently, it is very difficult to train a neural network that is both accurate and certified on realistic datasets and specifications (e.g., robustness). Given this difficulty, a pressing existential question is: given a dataset and a specification, is there a network that is both certified and accurate with respect to these? While the evidence suggests "no", we prove that for realistic datasets and specifications, such a network does exist and its certification can be established by propagating lower and upper bounds of each neuron through the network (interval analysis) - the most relaxed yet computationally efficient convex relaxation. Our result can be seen as a Universal Approximation Theorem for interval-certified ReLU networks. To the best of our knowledge, this is the first work to prove the existence of accurate, interval-certified networks.

Applying deep neural networks (DNNs) in mobile and safety-critical systems, such as autonomous vehicles, demands a reliable and efficient execution on hardware. Optimized dedicated hardware accelerators are being developed to achieve this. However, the design of efficient and reliable hardware has become increasingly difficult, due to the increased complexity of modern integrated circuit technology and its sensitivity against hardware faults, such as random bit-flips. It is thus desirable to exploit optimization potential for error resilience and efficiency also at the algorithmic side, e.g. by optimizing the architecture of the DNN. Since there are numerous design choices for the architecture of DNNs, with partially opposing effects on the preferred characteristics (such as small error rates at low latency), multi-objective optimization strategies are necessary. In this paper, we develop an evolutionary optimization technique for the automated design of hardware-optimized DNN architectures. For this purpose, we derive a set of easily computable objective functions, which enable the fast evaluation of DNN architectures with respect to their hardware efficiency and error resilience solely based on the network topology. We observe a strong correlation between predicted error resilience and actual measurements obtained from fault injection simulations. Keywords Neural Network Hardware · Error Resilience · Hardware Faults · Neural Architecture Search · Multi-Objective Optimization · AutoML 1 Introduction The application of deep neural networks (DNNs) in safety-critical perception systems, for example autonomous vehicles (A Vs), poses some challenges on the design of the underlying hardware platforms. On the one hand, efficient and fast accelerators are needed, since DNNs for computer vision exhibit massive computational requirements [55]. On the other hand, resilience against random hardware faults has to be ensured. In many driving scenarios, entering a fail-safe state is not sufficient, but fail-operational behavior and fault tolerance are required [48]. However, fault tolerance techniques at the hardware level often entail large redundancy overheads in silicon area, latency, and power consumption. These overheads stand in contrast to the low-power and low-latency requirements of embedded real-time DNN accelerators. Reliability concerns in nanoscale integrated circuits, for instance soft errors in memory and logic, represent an additional challenge for the realization of fault tolerance mechanisms at the hardware level [2, 33, 36, 68, 83]. Moreover, techniques such as near-threshold computing [26] and approximate computing [65] are desirable to meet power constraints, but can further increase error rates.