Quantum mechanics is inherently probabilistic in light of Born's rule. Using quantum circuits as probabilistic generative models for classical data exploits their superior expressibility and efficient direct sampling ability. However, training of quantum circuits can be more challenging compared to classical neural networks due to lack of efficient differentiable learning algorithm. We devise an adversarial quantum-classical hybrid training scheme via coupling a quantum circuit generator and a classical neural network discriminator together. After training, the quantum circuit generative model can infer missing data with quadratic speed up via amplitude amplification. We numerically simulate the learning and inference of generative adversarial quantum circuit using the prototypical Bars-and-Stripes dataset. Generative adversarial quantum circuits is a fresh approach to machine learning which may enjoy the practically useful quantum advantage on near-term quantum devices.

Adaptive stochastic gradient descent methods, such as AdaGrad, Adam, AdaDelta, Nadam, AMSGrad, \textit{etc.}, have been demonstrated efficacious in solving non-convex stochastic optimization, such as training deep neural networks. However, their convergence rates have not been touched under the non-convex stochastic circumstance except recent breakthrough results on AdaGrad \cite{ward2018adagrad} and perturbed AdaGrad \cite{li2018convergence}. In this paper, we propose two new adaptive stochastic gradient methods called AdaHB and AdaNAG which integrate coordinate-wise AdaGrad with heavy ball momentum and Nesterov accelerated gradient momentum, respectively. The $\mathcal{O}(\frac{\log{T}}{\sqrt{T}})$ non-asymptotic convergence rates of AdaHB and AdaNAG in non-convex stochastic setting are also jointly characterized by leveraging a newly developed unified formulation of these two momentum mechanisms. In particular, when momentum term vanishes we obtain convergence rate of coordinate-wise AdaGrad in non-convex stochastic setting as a byproduct.

Model Reduction with Memory and the Machine Learning of Dynamical Systems Chao Ma, Jianchun Wang †, Weinan E ‡ Abstract The well-known Mori-Zwanzig theory tells us that model reduction leads to memory effect. For a long time, modeling the memory effect accurately and efficiently has been an important but nearly impossible task in developing a good reduced model. In this work, we explore a natural analogy between recurrent neural networks and the Mori-Zwanzig formalism to establish a systematic approach for developing reduced models with memory. Two training models-a direct training model and a dynamically coupled training model-are proposed and compared. We apply these methods to the Kuramoto-Sivashinsky equation and the Navier-Stokes equation. Numerical experiments show that the proposed method can produce reduced model with good performance on both short-term prediction and long-term statistical properties. In science and engineering, many high-dimensional dynamical systems are too complicated to solve in detail. Nor is it necessary since usually we are only interested in a small subset of the variables representing the gross behavior of the system. Therefore, it is useful to develop reduced models which can approximate the variables of interest without solving the full system. This is the celebrated model reduction problem.

Machine learning models have been widely used in security applications such as intrusion detection, spam filtering, and virus or malware detection. However, it is well-known that adversaries are always trying to adapt their attacks to evade detection. For example, an email spammer may guess what features spam detection models use and modify or remove those features to avoid detection. There has been some work on making machine learning models more robust to such attacks. However, one simple but promising approach called {\em randomization} is underexplored. This paper proposes a novel randomization-based approach to improve robustness of machine learning models against evasion attacks. The proposed approach incorporates randomization into both model training time and model application time (meaning when the model is used to detect attacks). We also apply this approach to random forest, an existing ML method which already has some degree of randomness. Experiments on intrusion detection and spam filtering data show that our approach further improves robustness of random-forest method. We also discuss how this approach can be applied to other ML models.

We present a method for metric optimization in the Large Deformation Diffeomorphic Metric Mapping (LDDMM) framework, by treating the induced Riemannian metric on the space of diffeomorphisms as a kernel in a machine learning context. For simplicity, we choose the kernel Fischer Linear Discriminant Analysis (KLDA) as the framework. Optimizing the kernel parameters in an Expectation-Maximization framework, we define model fidelity via the hinge loss of the decision function. The resulting algorithm optimizes the parameters of the LDDMM norm-inducing differential operator as a solution to a group-wise registration and classification problem. In practice, this may lead to a biology-aware registration, focusing its attention on the predictive task at hand such as identifying the effects of disease. We first tested our algorithm on a synthetic dataset, showing that our parameter selection improves registration quality and classification accuracy. We then tested the algorithm on 3D subcortical shapes from the Schizophrenia cohort Schizconnect. Our Schizpohrenia-Control predictive model showed significant improvement in ROC AUC compared to baseline parameters.

Sparse deep neural networks(DNNs) are efficient in both memory and compute when compared to dense DNNs. But due to irregularity in computation of sparse DNNs, their efficiencies are much lower than that of dense DNNs on general purpose hardwares. This leads to poor/no performance benefits for sparse DNNs. Performance issue for sparse DNNs can be alleviated by bringing structure to the sparsity and leveraging it for improving runtime efficiency. But such structural constraints often lead to sparse models with suboptimal accuracies. In this work, we jointly address both accuracy and performance of sparse DNNs using our proposed class of neural networks called HBsNN ( Hierarchical Block Sparse Neural Networks).

The standard probabilistic perspective on machine learning gives rise to empirical risk-minimization tasks that are frequently solved by stochastic gradient descent (SGD) and variants thereof. We present a formulation of these tasks as classical inverse or filtering problems and, furthermore, we propose an efficient, gradient-free algorithm for finding a solution to these problems using ensemble Kalman inversion (EKI). Applications of our approach include offline and online supervised learning with deep neural networks, as well as graph-based semi-supervised learning. The essence of the EKI procedure is an ensemble based approximate gradient descent in which derivatives are replaced by differences from within the ensemble. We suggest several modifications to the basic method, derived from empirically successful heuristics developed in the context of SGD. Numerical results demonstrate wide applicability and robustness of the proposed algorithm.

Samsung is wading into the smart-speaker market with an entirely new product called the Galaxy Home. The speaker has a large, rounded body and sits on a tripod -- a very different design from competing speakers offered by Amazon.com, Samsung announced a partnership with Spotify, which is the default music player for the Galaxy Home. The speaker will be able to pick up streams from a Galaxy phone and hand it off to the speaker. The company didn't say much about the Galaxy Home apart from acknowledging its existence, and promising more details will come at its developers conference in November.

In the year 2020, Tokyo will essentially be breaking a tech record when they become the very first Olympics to use facial recognition technology in an attempt to improve security. On Tuesday, the organizing committee announced that Tokyo will be utilizing the tech for indentifying officials, athletes, media, and staff at the 2020 Paralympics and Olympics Games. It will, however, not be utilized in the identification of any spectators who attend the events. The utilization of the facial recognition technology is an effort to both increase security and hasten the entrance of authorized individuals. The Japanese IT conglomerate, NEC Corp, is currently developing the system.

For some children with autism, interacting with other people can be an uncomfortable, mystifying experience. Feeling overwhelmed with face-to-face interaction, such children may find it difficult to focus their attention and learn social skills from their teachers and therapists--the very people charged with helping them learn to socially adapt. What these children need, say some researchers, is a robot: a cute, tech-based intermediary, with a body, that can teach them how to more comfortably interact with their fellow humans. On the face of it, learning human interaction from a robot might sound counter-intuitive. But a handful of groups are studying the technology in an effort to find out just how effective these robots are at helping children with autism spectrum disorder (ASD). One of those groups is LuxAI, a young company spun out of the University of Luxembourg.