Neural Information Processing Systems http://nips.cc/

Neural Information Processing Systems http://nips.cc/

Probabilistic forecasting consists in predicting a distribution of possible future outcomes. In this paper, we address this problem for non-stationary time series, which is very challenging yet crucially important. We introduce the STRIPE model for representing structured diversity based on shape and time features, ensuring both probable predictions while being sharp and accurate.

Heat pumps can save you about $370 per year and are good for the planet. Heat pumps date back to the 1850s and are more energy efficient than furnaces or boilers. Breakthroughs, discoveries, and DIY tips sent every weekday. Colder weather is quickly approaching, which means it's time for many folks to start cranking up the heat in their homes and apartments. But for many Americans, heating up their homes is a costly affair-and it's only getting more expensive.

Scientists have a lot of questions about our planet's most important carbon sink--and a new project could help answer them. NEW YORK, NEW YORK - APRIL 16: Eric Schmidt, former chairman and CEO at GOOGLE visits Fox Business Network Studios on April 16, 2019 in New York City. A foundation created by Eric Schmidt, the former CEO of Google, will fund a project to send drone boats out into the rough ocean around Antarctica to collect data that could help solve a crucial climate puzzle. The project is part of a suite of funding announced today from Schmidt Sciences, which Schmidt and his wife Wendy created to focus on projects tackling research into the global carbon cycle. It will spend $45 million over the next five years to fund these projects, which includes the Antarctic research.

Additionally, we find that merely mixing features does not result in the same calibration benefit and that the label smoothing in mixup training plays a significant role in improving calibration.

The control of uncertain systems is a long-standing problem, to which a vast body of literature is dedicated.

Neural Information Processing Systems http://nips.cc/

We propose a method for combining two sources of astronomical data, spectroscopy and photometry, that carry information about sources of light (e.g., stars, galaxies, and quasars) at extremely different spectral resolutions. Our model treats the spectral energy distribution (SED) of the radiation from a source as a latent variable that jointly explains both photometric and spectroscopic observations. We place a flexible, nonparametric prior over the SED of a light source that admits a physically interpretable decomposition, and allows us to tractably perform inference. We use our model to predict the distribution of the redshift of a quasar from five-band (low spectral resolution) photometric data, the so called "photo-z" problem. Our method shows that tools from machine learning and Bayesian statistics allow us to leverage multiple resolutions of information to make accurate predictions with well-characterized uncertainties.

Neural Information Processing Systems http://nips.cc/