Covariate Distribution Balance via Propensity Scores. (arXiv:1810.01370v3 [econ.EM] UPDATED)

This paper proposes new estimators for the propensity score that aim to maximize the covariate distribution balance among different treatment groups. The proposed propensity score estimators, which we call the integrated propensity score (IPS), are data-driven, do not rely on tuning parameters such as bandwidths, admit an asymptotic linear representation, and can be used to…

State Drug Policy Effectiveness: Comparative Policy Analysis of Drug Overdose Mortality. (arXiv:1909.01936v2 [stat.AP] UPDATED)

Opioid overdose rates have reached an epidemic level and state-level policy innovations have followed suit in an effort to prevent overdose deaths. State-level drug law is a set of policies that may reinforce or undermine each other, and analysts have a limited set of tools for handling the policy collinearity using statistical methods. This paper…

Group Average Treatment Effects for Observational Studies. (arXiv:1911.02688v2 [econ.EM] UPDATED)

The paper proposes an estimator to make inference on key features of heterogeneous treatment effects sorted by impact groups (GATES) for non-randomised experiments. Observational studies are standard in policy evaluation from labour markets, educational surveys, and other empirical studies. To control for a potential selection-bias we implement a doubly-robust estimator in the first stage. Keeping…

Topological entropy of nonautonomous dynamical systems. (arXiv:1911.07993v1 [math.DS])

Let $\mathcal{M}(X)$ be the space of Borel probability measures on a compact metric space $X$ endowed with the weak$^\ast$-topology. In this paper, we prove that if the topological entropy of a nonautonomous dynamical system $(X,\{f_n\}_{n=1}^{+\infty})$ vanishes, then so does that of its induced system $(\mathcal{M}(X),\{f_n\}_{n=1}^{+\infty})$; moreover, once the topological entropy of $(X,\{f_n\}_{n=1}^{+\infty})$ is positive, that…

Normal and Equivolumetric Coordinate Systems for Cortical Areas. (arXiv:1911.07999v1 [math.OC])

We describe coordinate systems adapted for the space between two surfaces, such as those delineating the highly folded cortex in mammalian brains. These systems are estimated in order to satisfy geometric priors, including streamline normality or equivolumetric conditions on layers. We give a precise mathematical formulation of these problems, and present numerical simulations based on…

Low Complexity Autoencoder based End-to-End Learning of Coded Communications Systems. (arXiv:1911.08009v1 [cs.IT])

End-to-end learning of a communications system using the deep learning-based autoencoder concept has drawn interest in recent research due to its simplicity, flexibility and its potential of adapting to complex channel models and practical system imperfections. In this paper, we have compared the bit error rate (BER) performance of autoencoder based systems and conventional channel…

Noncommutative coordinates for symplectic representations. (arXiv:1911.08014v1 [math.DG])

We introduce coordinates on the space of Lagrangian decorated and framed representations of the fundamental group of a surface with punctures into the symplectic group Sp(2n,R). These coordinates provide a non-commutative generalization of the parametrizations of the spaces of representations into SL(2,R) given by Thurston, Penner, and Fock-Goncharov. With these coordinates, the space of framed…

Complex Sparse Code Priors Improve the Statistical Models of Neurons in Primate Primary Visual Cortex. (arXiv:1911.08241v1 [q-bio.QM])

Statistical modeling techniques, such as projection pursuit regression (PPR) and convolutional neural network (CNN) approaches, provide state-of-the-art performance in characterizing visual cortical neurons’ receptive fields and predicting their responses to arbitrary input stimuli. However, the latent feature components recovered by these methods, particularly that of CNN, are often noisy and lack coherent structures, making it…

Coexistence, extinction, and optimal harvesting in discrete-time stochastic population models. (arXiv:1911.08398v1 [q-bio.PE])

We analyze the long term behavior of interacting populations which can be controlled through harvesting. The dynamics is assumed to be discrete in time and stochastic due to the effect of environmental fluctuations. We present extinction and coexistence criteria when there are one or two interacting species. We then use these tools in order to…