We study regret minimization problems in a two-sided matching market where uniformly valued demand side agents (a.k.a. agents) continuously compete for getting matched with supply side agents (a.k.a. arms) with
Deep Involutive Generative Models for Neural MCMC. (arXiv:2006.15167v1 [stat.ML])
We introduce deep involutive generative models, a new architecture for deep generative modeling, and use them to define Involutive Neural MCMC, a new approach to fast neural MCMC. An involutive
Train and You’ll Miss It: Interactive Model Iteration with Weak Supervision and Pre-Trained Embeddings. (arXiv:2006.15168v1 [stat.ML])
Our goal is to enable machine learning systems to be trained interactively. This requires models that perform well and train quickly, without large amounts of hand-labeled data. We take a
A Comparison of Uncertainty Estimation Approaches in Deep Learning Components for Autonomous Vehicle Applications. (arXiv:2006.15172v1 [cs.LG])
A key to ensuring safety in Autonomous Vehicles (AVs) is to avoid any abnormal behaviors under undesirable and unpredicted circumstances. As AVs increasingly rely on Deep Neural Networks (DNNs) to
Interpretable Factorization for Neural Network ECG Models. (arXiv:2006.15189v1 [cs.LG])
The ability of deep learning (DL) to improve the practice of medicine and its clinical outcomes faces a looming obstacle: model interpretation. Without description of how outputs are generated, a
Is SGD a Bayesian sampler? Well, almost. (arXiv:2006.15191v1 [cs.LG])
Overparameterised deep neural networks (DNNs) are highly expressive and so can, in principle, generate almost any function that fits a training dataset with zero error. The vast majority of these
The gas, metal and dust evolution in low-metallicity local and high-redshift galaxies. (arXiv:2006.15146v1 [astro-ph.GA])
The chemical enrichment in the interstellar medium (ISM) of galaxies is regulated by several physical processes: stellar evolution, grain formation and destruction, galactic inflows and outflows. Understanding such processes is
CMacIonize 2.0: a novel task-based approach to Monte Carlo radiation transfer. (arXiv:2006.15147v1 [astro-ph.IM])
(Context) Monte Carlo radiative transfer (MCRT) is a widely used technique to model the interaction between radiation and a medium, and plays an important role in astrophysical modelling and when
Split SIMPs with Decays. (arXiv:2006.15148v1 [hep-ph])
We discuss a minimal realization of the strongly interacting massive particle (SIMP) framework. The model includes a dark copy of QCD with three colors and three light flavors. A massive
C19-TraNet: an empirical, global index-case transmission network of SARS-CoV-2. (arXiv:2006.15162v1 [q-bio.PE])
Originating in Wuhan, the novel coronavirus, severe acute respiratory syndrome 2 (SARS-CoV-2), has astonished health-care systems across globe due to its rapid and simultaneous spread to the neighboring and distantly