Country
e19ab2dde2e60cf68d1ded18c38938f4-Paper-Conference.pdf
Fortraining,PPOfirst collects trajectoriesฯ using the old policy networkฯฮธold right before the update.
Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networks
Ali Shafahi, W. Ronny Huang, Mahyar Najibi, Octavian Suciu, Christoph Studer, Tudor Dumitras, Tom Goldstein
This paper explores poisoning attacks on neural nets.
Hyperparameter Learning via Distributional Transfer
Ho Chung Law, Peilin Zhao, Leung Sing Chan, Junzhou Huang, Dino Sejdinovic
However, BO suffers from the so called'cold start' problem [
Factored Bandits
Julian Zimmert, Yevgeny Seldin
Neural Information Processing Systems http://nips.cc/
Unveiling the Bias Impact on Symmetric Moral Consistency of Large Language Models
We find that the ability of LLMs to maintain consistency varies across different moral scenarios.
cpSGD: Communication-efficient and differentially-private distributed SGD
Naman Agarwal, Ananda Theertha Suresh, Felix Xinnan X. Yu, Sanjiv Kumar, Brendan McMahan
Neural Information Processing Systems http://nips.cc/