Curriculum Self-Paced Learning for Cross-Domain Object Detection. (arXiv:1911.06849v1 [cs.CV])

Training (source) domain bias affects state-of-the-art object detectors, such as Faster R-CNN, when applied to new (target) domains. To alleviate this problem, researchers proposed various domain adaptation methods to improve object detection results in the cross-domain setting, e.g. by translating images with ground-truth labels from the source domain to the target domain using Cycle-GAN or…

Empirical Study of Off-Policy Policy Evaluation for Reinforcement Learning. (arXiv:1911.06854v1 [cs.LG])

Off-policy policy evaluation (OPE) is the problem of estimating the online performance of a policy using only pre-collected historical data generated by another policy. Given the increasing interest in deploying learning-based methods for safety-critical applications, many recent OPE methods have recently been proposed. Due to disparate experimental conditions from recent literature, the relative performance of…

Stochastic decompositions in bivariate risk and queueing models with mutual assistance. (arXiv:1911.06867v1 [math.PR])

We consider two bivariate models with two-way interactions in context of risk and queueing theory. The two entities interact with each other by providing assistance but otherwise evolve independently. We focus on certain random quantities underlying the joint survival probability and the joint stationary workload, and show that these admit stochastic decomposition. Each one can…

Deep Learning with Persistent Homology for Orbital Angular Momentum (OAM) Decoding. (arXiv:1911.06858v1 [eess.SP])

Orbital angular momentum (OAM)-encoding has recently emerged as an effective approach for increasing the channel capacity of free-space optical communications. In this paper, OAM-based decoding is formulated as a supervised classification problem. To maintain lower error rate in presence of severe atmospheric turbulence, a new approach that combines effective machine learning tools from persistent homology…

Low Frequency Asymptotics and Electro-Magneto-Statics for Time-Harmonic Maxwell’s Equations in Exterior Weak Lipschitz Domains with Mixed Boundary Conditions. (arXiv:1911.06871v1 [math.AP])

We prove that the time-harmonic solutions to Maxwell’s equations in a 3D exterior domain converge to a certain static solution as the frequency tends to zero. We work in weighted Sobolev spaces and construct new compactly supported replacements for Dirichlet-Neumann fields. Moreover, we even show convergence in operator norm.

Learning Behavioral Representations from Wearable Sensors. (arXiv:1911.06959v1 [cs.LG])

The ubiquity of mobile devices and wearable sensors offers unprecedented opportunities for continuous collection of multimodal physiological data. Such data enables temporal characterization of an individual’s behaviors, which can provide unique insights into her physical and psychological health. Understanding the relation between different behaviors/activities and personality traits such as stress or work performance can help…

Spectral stability of smooth solitary waves for the Degasperis-Procesi Equation. (arXiv:1911.06885v1 [math.AP])

The Degasperis-Procesi equation is an approximating model of shallow-water wave propagating mainly in one direction to the Euler equations. Such a model equation is analogous to the Camassa-Holm approximation of the two-dimensional incompressible and irrotational Euler equations with the same asymptotic accuracy, and is integrable with the bi-Hamiltonian structure. In the present study, we establish…