Technology
Global Convergence of Least Squares EM for Demixing Two Log-Concave Densities
Wei Qian, Yuqian Zhang, Yudong Chen
Neural Information Processing Systems http://nips.cc/
H-nobs: Achieving Certified Fairness and Robustness in Distributed Learning on Heterogeneous Datasets
Fairness and robustness are two important goals in the desig n of modern distributed learning systems. Despite a few prior works attemp ting to achieve both fairness and robustness, some key aspects of this direction remain underexplored. In this paper, we try to answer three largely unnoticed and un addressed questions that are of paramount significance to this topic: (i) What mak es jointly satisfying fairness and robustness difficult?
Multi-objective Bayesian optimisation with preferences over objectives
Majid Abdolshah, Alistair Shilton, Santu Rana, Sunil Gupta, Svetha Venkatesh
Neural Information Processing Systems http://nips.cc/
The Global Anchor Method for Quantifying Linguistic Shifts and Domain Adaptation
Zi Yin, Vin Sachidananda, Balaji Prabhakar
Neural Information Processing Systems http://nips.cc/
Distributed Multitask Reinforcement Learning with Quadratic Convergence
Rasul Tutunov, Dongho Kim, Haitham Bou Ammar
Multitask reinforcement learning (MTRL) suffers from scalability issues when the number of tasks or trajectories grows large.
Neural Similarity Learning
Weiyang Liu, Zhen Liu, James M. Rehg, Le Song
Neuralsimilarity naturally generalizes the convolution and enhances flexibility.
a7a3d70c6d17a73140918996d03c014f-AuthorFeedback.pdf
NSL is theoretically connected with [Implicit Regularization in Matrix Factorization,5 NeurIPS 2017] which shows that factorized learning is biased towards the minimum nuclear norm solution. Weagree with the reviewer that our method can be viewed asan22 architectural modification which is generally useful. We use a simple way to construct a dynamic network whose23 equivalent weights are dependent on the input. In fact, meta-learning is just one of the suitable applications for our24 approach. We con-27 duct allthemeta-learning experiments28 requested by the reviewer.
