Technology
Using Self-Supervised Learning Can Improve Model Robustness and Uncertainty
Dan Hendrycks, Mantas Mazeika, Saurav Kadavath, Dawn Song
Neural Information Processing Systems http://nips.cc/
Evolved Policy Gradients
Rein Houthooft, Yuhua Chen, Phillip Isola, Bradly Stadie, Filip Wolski, OpenAI Jonathan Ho, Pieter Abbeel
The idea is to evolve a differentiable loss function, such thatanagent, which optimizes itspolicytominimize thisloss, willachieve highrewards.
Learning and Testing Causal Models with Interventions
Jayadev Acharya, Arnab Bhattacharyya, Constantinos Daskalakis, Saravanan Kandasamy
Neural Information Processing Systems http://nips.cc/
Learning Latent Process from High-Dimensional Event Sequences via Efficient Sampling
Qitian Wu, Zixuan Zhang, Xiaofeng Gao, Junchi Yan, Guihai Chen
There are plenty of previous studies targeting the problem from different aspects. For temporal point process, agreat number of works [3, 13, 15, 16, 28] attempt to model the intensify function from statistic views, and recent studies harness deep recurrent model [24], generative adversarial network [23] and reinforcement learning [19, 18] to learn the temporal process. These researches mainly focus on one-dimension eventsequences where eacheventpossesses thesame marker.
