Coordination Event Detection and Initiator Identification in Time Series Data. (arXiv:1603.01570v2 [cs.SI] CROSS LISTED)

Behavior initiation is a form of leadership and is an important aspect of social organization that affects the processes of group formation, dynamics, and decision-making in human societies and other social animal species. In this work, we formalize the “Coordination Initiator Inference Problem” and propose a simple yet powerful framework for extracting periods of coordinated…

Behavior Regularized Offline Reinforcement Learning. (arXiv:1911.11361v1 [cs.LG])

In reinforcement learning (RL) research, it is common to assume access to direct online interactions with the environment. However in many real-world applications, access to the environment is limited to a fixed offline dataset of logged experience. In such settings, standard RL algorithms have been shown to diverge or otherwise yield poor performance. Accordingly, recent…

Gradient Perturbation is Underrated for Differentially Private Convex Optimization. (arXiv:1911.11363v1 [cs.LG])

Gradient perturbation, widely used for differentially private optimization, injects noise at every iterative update to guarantee differential privacy. Previous work first determines the noise level that can satisfy the privacy requirement and then analyzes the utility of noisy gradient updates as in non-private case. In this paper, we explore how the privacy noise affects the…

Representation Learning: A Statistical Perspective. (arXiv:1911.11374v1 [stat.ML])

Learning representations of data is an important problem in statistics and machine learning. While the origin of learning representations can be traced back to factor analysis and multidimensional scaling in statistics, it has become a central theme in deep learning with important applications in computer vision and computational neuroscience. In this article, we review recent…

Text2FaceGAN: Face Generation from Fine Grained Textual Descriptions. (arXiv:1911.11378v1 [cs.LG])

Powerful generative adversarial networks (GAN) have been developed to automatically synthesize realistic images from text. However, most existing tasks are limited to generating simple images such as flowers from captions. In this work, we extend this problem to the less addressed domain of face generation from fine-grained textual descriptions of face, e.g., “A person has…

Using Physics-Informed Super-Resolution Generative Adversarial Networks for Subgrid Modeling in Turbulent Reactive Flows. (arXiv:1911.11380v1 [cs.LG])

Turbulence is still one of the main challenges for accurately predicting reactive flows. Therefore, the development of new turbulence closures which can be applied to combustion problems is essential. Data-driven modeling has become very popular in many fields over the last years as large, often extensively labeled, datasets became available and training of large neural…

Multi-View Multiple Clusterings using Deep Matrix Factorization. (arXiv:1911.11396v1 [cs.LG])

Multi-view clustering aims at integrating complementary information from multiple heterogeneous views to improve clustering results. Existing multi-view clustering solutions can only output a single clustering of the data. Due to their multiplicity, multi-view data, can have different groupings that are reasonable and interesting from different perspectives. However, how to find multiple, meaningful, and diverse clustering…

A new set of cluster driven composite development indicators. (arXiv:1911.11226v1 [econ.GN])

Composite development indicators used in policy making often subjectively aggregate a restricted set of indicators. We show, using dimensionality reduction techniques, including Principal Component Analysis (PCA) and for the first time information filtering and hierarchical clustering, that these composite indicators miss key information on the relationship between different indicators. In particular, the grouping of indicators…

Neural network for pricing and universal static hedging of contingent claims. (arXiv:1911.11362v1 [q-fin.CP])

We present here a regress later based Monte Carlo approach that uses neural networks for pricing high-dimensional contingent claims. The choice of specific architecture of the neural networks used in the proposed algorithm provides for interpretability of the model, a feature that is often desirable in the financial context. Specifically, the interpretation leads us to…

Closed Quantum Black-Scholes: Quantum Drift and the Heisenberg Equation of Motion. (arXiv:1911.11475v1 [q-fin.MF])

In this article we model a financial derivative price as an observable on the market state function. We apply geometric techniques to integrating the Heisenberg Equation of Motion. We illustrate how the non-commutative nature of the model introduces quantum interference effects that can act as either a drag or a boost on the resulting return.…