Energy
Seeing the Wind: Visual Wind Speed Prediction with a Coupled Convolutional and Recurrent Neural Network
Jennifer Cardona, Michael Howland, John Dabiri
Wind energy resource quantification, air pollution monitoring, and weather forecasting all rely on rapid, accurate measurement of local wind conditions.
Nonconvex Low-Rank Tensor Completion from Noisy Data
Changxiao Cai, Gen Li, H. Vincent Poor, Yuxin Chen
Focusing on "incoherent" and well-conditioned tensors of a constant CP rank, we propose a two-stage nonconvex algorithm -- (vanilla) gradient descent following a rough initialization -- that achieves the best of both worlds.
Learning Latent Seasonal-Trend Representations for Time Series Forecasting
However, clear patterns are still hard to extract since time series are often composed of several intricately entangled components.
Error Correction Code Transformer
BCH(7,4) code with N = 6, d = 32, similarly to the results presented in Section 6.1. Interestingly, in the early stage of the decoding, ECCT seems to focus its processing of the syndrome. Once the network corrects the bit (last layers(s)), the values return to normal. Using multiple heads is clearly beneficial for the model's performance. The proposed shallow ECCTs are able to compete and even surpass the SCL for some of the codes and SNRs.
Error Correction Code Transformer
We encode each channel's output dimension to a high dimension for better representation of the bits' information to be processed separately.
Regret Minimization for Reinforcement Learning by Evaluating the Optimal Bias Function
Therefore, there is a trade-off between exploration and exploitation, i.e., taking actions we have not learned accurately enough and taking actions which
Re-Analyze Gauss: Bounds for Private Matrix Approximation via Dyson Brownian Motion Oren Mangoubi Worcester Polytechnic Institute Nisheeth K. Vishnoi Yale University
Given a symmetric matrix M and a vector, we present new bounds on the Frobenius-distance utility of the Gaussian mechanism for approximating M by a matrix whose spectrum is,u n d e r ( Á, ") -di erential privacy. Our bounds depend on both and the gaps in the eigenvalues of M, and hold whenever the top k +1 eigenvalues of M have su ciently large gaps. When applied to the problems of private rank-k covariance matrix approximation and subspace recovery, our bounds yield improvements over previous bounds. Our bounds are obtained by viewing the addition of Gaussian noise as a continuous-time matrix Brownian motion. This viewpoint allows us to track the evolution of eigenvalues and eigenvectors of the matrix, which are governed by stochastic di erential equations discovered by Dyson. These equations allow us to bound the utility as the square-root of a sum-of-squares of perturbations to the eigenvectors, as opposed to a sum of perturbation bounds obtained via Davis-Kahan-type theorems.
Differentiable Convex Optimization Layers
Akshay Agrawal, Brandon Amos, Shane Barratt, Stephen Boyd, Steven Diamond, J. Zico Kolter
Neural Information Processing Systems http://nips.cc/
A Closer Look at AUROC and AUPRC under Class Imbalance
Prompted by these insights, we reviewed over 1.5 million scientific papers to understand the origin of this invalid
ChaosBench: A Multi-Channel, Physics-Based Benchmark for Subseasonal-to-Seasonal Climate Prediction Supplementary Material Juan Nathaniel
ChaosBench is published under the open source GNU General Public License. Furthermore, we are committed to maintaining and preserving the ChaosBench benchmark. User feedback will be closely monitored via the GitHub issue tracker. Dataset: All our dataset, present and future (e.g., with more years, multi-resolution support, etc) are Here, we provide a detailed description on how to prepare the necessary data, perform training, and benchmark your own model. B.1 Data Preparation First, navigate to the repository directory and install the necessary dependencies.