Minority Voter Distributions and Partisan Gerrymandering. (arXiv:1911.09792v1 [cs.CY])

Many people believe that it is disadvantageous for members aligning with a minority party to cluster in cities, as this makes it easier for the majority party to gerrymander district boundaries to diminish the representation of the minority. We examine this effect by exhaustively computing the average representation for every possible $5\times 5$ grid of…

Multi-model mimicry for model selection according to generalised goodness-of-fit criteria. (arXiv:1911.09779v1 [stat.ME])

Selecting between candidate models is at the core of statistical practice. As statistical modelling techniques are rapidly evolving, the need for similar evolution in the ways to select between candidate models is increasing. With Akaike’s Information Criterion (AIC) and Bayesian Information Criterion (BIC) not applicable for all sets of candidate models, and likelihood not the…

Synthetic vs Real: Deep Learning on Controlled Noise. (arXiv:1911.09781v1 [cs.LG])

Performing controlled experiments on noisy data is essential in thoroughly understanding deep learning across a spectrum of noise levels. Due to the lack of suitable datasets, previous research have only examined deep learning on controlled synthetic noise, and real-world noise has never been systematically studied in a controlled setting. To this end, this paper establishes…

WildMix Dataset and Spectro-Temporal Transformer Model for Monoaural Audio Source Separation. (arXiv:1911.09783v1 [cs.LG])

Monoaural audio source separation is a challenging research area in machine learning. In this area, a mixture containing multiple audio sources is given, and a model is expected to disentangle the mixture into isolated atomic sources. In this paper, we first introduce a challenging new dataset for monoaural source separation called WildMix. WildMix is designed…

ReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation Anchoring. (arXiv:1911.09785v1 [cs.LG])

We improve the recently-proposed “MixMatch” semi-supervised learning algorithm by introducing two new techniques: distribution alignment and augmentation anchoring. Distribution alignment encourages the marginal distribution of predictions on unlabeled data to be close to the marginal distribution of ground-truth labels. Augmentation anchoring feeds multiple strongly augmented versions of an input into the model and encourages each…

LATTE: Latent Type Modeling for Biomedical Entity Linking. (arXiv:1911.09787v1 [cs.CL])

Entity linking is the task of linking mentions of named entities in natural language text, to entities in a curated knowledge-base. This is of significant importance in the biomedical domain, where it could be used to semantically annotate a large volume of clinical records and biomedical literature, to standardized concepts described in an ontology such…

An Alternative Cross Entropy Loss for Learning-to-Rank. (arXiv:1911.09798v1 [cs.LG])

Listwise learning-to-rank methods form a powerful class of ranking algorithms that are widely adopted in applications such as information retrieval. These algorithms learn to rank a set of items by optimizing a loss that is a function of the entire set—as a surrogate to a typically non-differentiable ranking metric. Despite their empirical success, existing listwise…

Efficient Drone Mobility Support Using Reinforcement Learning. (arXiv:1911.09715v1 [cs.IT])

Flying drones can be used in a wide range of applications and services from surveillance to package delivery. To ensure robust control and safety of drone operations, cellular networks need to provide reliable wireless connectivity to drone user equipments (UEs). To date, existing mobile networks have been primarily designed and optimized for serving ground UEs,…

Harmonic analysis on rank $2$ valuation group of a $2$-dimensional local field. (arXiv:1911.09718v1 [math.NT])

In this work we construct harmonic analysis on free Abelian groups of rank $2$, namely: we construct and investigate spaces of functions and distributions, Fourier transforms, actions of discrete and extended discrete Heisenberg groups. In case of rank $2$ value group of a $2$-dimensional local field with the finite last residue field we connect this…