Deep Learning
High-dimensional multivariate forecasting with low-rank Gaussian Copula Processes
David Salinas, Michael Bohlke-Schneider, Laurent Callot, Roberto Medico, Jan Gasthaus
Neural Information Processing Systems http://nips.cc/
reviewers regarding the comparison against recent DL methods, we evaluated our approach against DeepAR [ 1 ] and
We thank all reviewers for their valuable comments and suggestions. Table 1: CRPS for additional baselines (left) and comparison with [2] when measuring W APE (right). "The paper does not seem to have enough original contribution. "The synthetic data are simple periodic data, expected that predicted line follow the synthetic much more closely." "As main goal of the paper is to perform the superior forecasting, it will be fair that results will be compared to paper "The number of Monte Carlo sampling ... excessive sampling may increase the complexity of the entire model."
Language as an Abstraction for Hierarchical Deep Reinforcement Learning
YiDing Jiang, Shixiang (Shane) Gu, Kevin P. Murphy, Chelsea Finn
Solving complex, temporally-extended tasks is a long-standing problem in reinforcement learning (RL).
Variational Mixture-of-Experts Autoencoders for Multi-Modal Deep Generative Models
Yuge Shi, Siddharth N, Brooks Paige, Philip Torr
Neural Information Processing Systems http://nips.cc/
Beyond the Single Neuron Convex Barrier for Neural Network Certification
Gagandeep Singh, Rupanshu Ganvir, Markus Pรผschel, Martin Vechev
Neural Information Processing Systems http://nips.cc/
Learning Stable Deep Dynamics Models
Neural Information Processing Systems http://nips.cc/
Expressing an Image Stream with a Sequence of Natural Sentences
Neural Information Processing Systems http://nips.cc/
GPipe: Efficient Training of Giant Neural Networks using Pipeline Parallelism
Yanping Huang, Youlong Cheng, Ankur Bapna, Orhan Firat, Dehao Chen, Mia Chen, HyoukJoong Lee, Jiquan Ngiam, Quoc V. Le, Yonghui Wu, zhifeng Chen
Neural Information Processing Systems http://nips.cc/
Automatic Perturbation Analysis for Scalable Certified Robustness and Beyond Kaidi Xu
The majority of LiRP A-based methods focus on simple feed-forward networks and need particular manual derivations and implementations when extended to other architectures. In this paper, we develop an automatic framework to enable perturbation analysis on any neural network structures, by generalizing existing LiRP A algorithms such as CROWN to operate on general computational graphs.