The control of complex systems is of critical importance in many branches of science, engineering, and industry. Controlling an unsteady fluid flow is particularly important, as flow control is a key enabler for technologies in energy (e.g., wind, tidal, and combustion), transportation (e.g., planes, trains, and automobiles), security (e.g., tracking airborne contamination), and health (e.g., artificial hearts and artificial respiration). However, the high-dimensional, nonlinear, and multi-scale dynamics make real-time feedback control infeasible. Fortunately, these high-dimensional systems exhibit dominant, low-dimensional patterns of activity that can be exploited for effective control in the sense that knowledge of the entire state of a system is not required. Advances in machine learning have the potential to revolutionize flow control given its ability to extract principled, low-rank feature spaces characterizing such complex systems. We present a novel deep learning model predictive control (DeepMPC) framework that exploits low-rank features of the flow in order to achieve considerable improvements to control performance. Instead of predicting the entire fluid state, we use a recurrent neural network (RNN) to accurately predict the control relevant quantities of the system. The RNN is then embedded into a MPC framework to construct a feedback loop, and incoming sensor data is used to perform online updates to improve prediction accuracy. The results are validated using varying fluid flow examples of increasing complexity.

Tensor decomposition methods (TDMs) have recently gained popularity as ways of performing inference for latent variable models [Anandkumar et al., 2014]. The interest in these methods is motivated by the fact that they come with theoretical global convergence guarantees in the limit of infinite data [Anandkumar et al., 2012, Arora et al., 2013]. However, a main limitation of these methods is that they lack natural methods for regularization or encouraging desired properties on the model parameters when the amount of data is limited. Previous works attempted to alleviate this drawback by modifying existing tensor decomposition methods to incorporate specific constraints, such as sparsity [Sun et al., 2015], or incorporate modeling assumptions, such as the existence of anchor words [Arora et al., 2013, Nguyen et al., 2014]. All of these works develop bespoke algorithms tailored to those constraints or assumptions. Furthermore, many of these methods impose hard constraints on the learned model, which may be detrimental as the size of the data grow--framed in the context of Bayesian intuition, when we have a lot of data, we want our methods to allow the evidence to overwhelm our priors. We introduce an alternative approach which can be applied to encourage any (differentiable) desired structure or properties on the model parameters, and which will only encourage this "prior" information when the data is insufficient. Specifically, we adopt the common view of Bayesian priors as representing "pseudo-observations" of artificial data which bias our learned model parameters towards our prior belief [Bishop, 2006]. We apply the tensor decomposition method of Anandkumar et al.

Recent reinforcement learning algorithms, though achieving impressive results in various fields, suffer from brittle training effects such as regression in results and high sensitivity to initialization and parameters. We claim that some of the brittleness stems from variance differences, i.e. when different environment areas - states and/or actions - have different rewards variance. This causes two problems: First, the "Boring Areas Trap" in algorithms such as Q-learning, where moving between areas depends on the current area variance, and getting out of a boring area is hard due to its low variance. Second, the "Manipulative Consultant" problem, when value-estimation functions used in DQN and Actor-Critic algorithms influence the agent to prefer boring areas, regardless of the mean rewards return, as they maximize estimation precision rather than rewards. This sheds a new light on how exploration contribute to training, as it helps with both challenges. Cognitive experiments in humans showed that noised reward signals may paradoxically improve performance. We explain this using the two mentioned problems, claiming that both humans and algorithms may share similar challenges. Inspired by this result, we propose the Adaptive Symmetric Reward Noising (ASRN), by which we mean adding Gaussian noise to rewards according to their states' estimated variance, thus avoiding the two problems while not affecting the environment's mean rewards behavior. We conduct our experiments in a Multi Armed Bandit problem with variance differences. We demonstrate that a Q-learning algorithm shows the brittleness effect in this problem, and that the ASRN scheme can dramatically improve the results. We show that ASRN helps a DQN algorithm training process reach better results in an end to end autonomous driving task using the AirSim driving simulator.

Robustness to adversarial perturbations has become an essential feature in the design of modern classifiers --in particular, of deep neural networks. This phenomenon originates from several empirical observations, such as [1] and [2], which show deep networks are vulnerable to adversarial attacks in the input space. So far, plenty of novel methodologies have been introduced to compensate for this shortcoming. Adversarial Training (AT) [3], Virtual AT [4] or Distillation [5] are just examples of some promising methods in this area. The majority of these approaches seek an effective defense against a point-wise adversary, who shifts input data-points toward adversarial directions, in a separate manner. However, as shown by [6], a distributional adversary who can shift the data distribution instead of the input data-points is provably more detrimental to learning. This suggests that one can greatly improve the robustness of a classifier by improving its defense against a distributional adversary rather than a point-wise one. This motivation has led to the development of Distributionally Robust Learning (DRL) [7], which has attracted intensive research interest over the last few years [8, 9, 10, 11]. Despite of all the advancements in supervised or unsupervised DRL, the amount of researches tackling this problem from a semi-supervised angle is slim to none [12].

Suppose that we wish to estimate a user's preference vector $w$ from paired comparisons of the form "does user $w$ prefer item $p$ or item $q$?," where both the user and items are embedded in a low-dimensional Euclidean space with distances that reflect user and item similarities. Such observations arise in numerous settings, including psychometrics and psychology experiments, search tasks, advertising, and recommender systems. In such tasks, queries can be extremely costly and subject to varying levels of response noise; thus, we aim to actively choose pairs that are most informative given the results of previous comparisons. We provide new theoretical insights into the benefits and challenges of greedy information maximization in this setting, and develop two novel strategies that maximize lower bounds on information gain and are simpler to analyze and compute respectively. We use simulated responses from a real-world dataset to validate our strategies through their similar performance to greedy information maximization, and their superior preference estimation over state-of-the-art selection methods as well as random queries.

Performance of end-to-end neural networks on a given hardware platform is a function of its compute and memory signature, which in-turn, is governed by a wide range of parameters such as topology size, primitives used, framework used, batching strategy, latency requirements, precision etc. Current benchmarking tools suffer from limitations such as a) being either too granular like DeepBench [1] (or) b) mandate a working implementation that is either framework specific or hardware-architecture specific or both (or) c) provide only high level benchmark metrics. In this paper, we present NTP (Neural Net Topology Profiler), a sophisticated benchmarking framework, to effectively identify memory and compute signature of an end-to-end topology on multiple hardware architectures, without the need for an actual implementation. NTP is tightly integrated with hardware specific benchmarking tools to enable exhaustive data collection and analysis. Using NTP, a deep learning researcher can quickly establish baselines needed to understand performance of an end-to-end neural network topology and make high level architectural decisions. Further, integration of NTP with frameworks like Tensorflow, Pytorch, Intel OpenVINO etc. allows for performance comparison along several vectors like a) Comparison of different frameworks on a given hardware b) Comparison of different hardware using a given framework c) Comparison across different heterogeneous hardware configurations for given framework etc. These capabilities empower a researcher to effortlessly make architectural decisions needed for achieving optimized performance on any hardware platform. The paper documents the architectural approach of NTP and demonstrates the capabilities of the tool by benchmarking Mozilla DeepSpeech, a popular Speech Recognition topology.

In this work, we investigate black-box optimization from the perspective of frequentist kernel methods. We propose a novel batch optimization algorithm to jointly maximize the acquisition function and select points from a whole batch in a holistic way. Theoretically, we derive regret bounds for both the noise-free and perturbation settings. Moreover, we analyze the property of the adversarial regret that is required by robust initialization for Bayesian Optimization (BO), and prove that the adversarial regret bounds decrease with the decrease of covering radius, which provides a criterion for generating (initialization point set) to minimize the bound. We then propose fast searching algorithms to generate a point set with a small covering radius for the robust initialization. Experimental results on both synthetic benchmark problems and real-world problems show the effectiveness of the proposed algorithms.

The Hawkes process has been widely applied to modeling self-exciting events, including neuron spikes, earthquakes and tweets. To avoid designing parametric kernel functions and to be able to quantify the prediction confidence, non-parametric Bayesian Hawkes processes have been proposed. However the inference of such models suffers from unscalability or slow convergence. In this paper, we first propose a new non-parametric Bayesian Hawkes process whose triggering kernel is modeled as a squared sparse Gaussian process. Second, we present the variational inference scheme for the model optimization, which has the advantage of linear time complexity by leveraging the stationarity of the triggering kernel. Third, we contribute a tighter lower bound than the evidence lower bound of the marginal likelihood for the model selection. Finally, we exploit synthetic data and large-scale social media data to validate the efficiency of our method and the practical utility of our approximate marginal likelihood. We show that our approach outperforms state-of-the-art non-parametric Bayesian and non-Bayesian methods.

This article investigates the quality of the estimator of the linear Monge mapping between distributions. We provide the first concentration result on the linear mapping operator and prove a sample complexity of $n^{-1/2}$ when using empirical estimates of first and second order moments. This result is then used to derive a generalization bound for domain adaptation with optimal transport. As a consequence, this method approaches the performance of theoretical Bayes predictor under mild conditions on the covariance structure of the problem. We also discuss the computational complexity of the linear mapping estimation and show that when the source and target are stationary the mapping is a convolution that can be estimated very efficiently using fast Fourier transforms. Numerical experiments reproduce the behavior of the proven bounds on simulated and real data for mapping estimation and domain adaptation on images.

We propose a decentralized learning algorithm over a general social network. The algorithm leaves the training data distributed on the mobile devices while utilizing a peer to peer model aggregation method. The proposed algorithm allows agents with local data to learn a shared model explaining the global training data in a decentralized fashion. The proposed algorithm can be viewed as a Bayesian and peer-to-peer variant of federated learning in which each agent keeps a "posterior probability distribution" over a global model parameters. The agent update its "posterior" based on 1) the local training data and 2) the asynchronous communication and model aggregation with their 1-hop neighbors. This Bayesian formulation allows for a systematic treatment of model aggregation over any arbitrary connected graph. Furthermore, it provides strong analytic guarantees on converge in the realizable case as well as a closed form characterization of the rate of convergence. We also show that our methodology can be combined with efficient Bayesian inference techniques to train Bayesian neural networks in a decentralized manner. By empirical studies we show that our theoretical analysis can guide the design of network/social interactions and data partitioning to achieve convergence.