Industry
Meta-Reinforced Synthetic Data for One-Shot Fine-Grained Visual Recognition
Satoshi Tsutsui, Yanwei Fu, David Crandall
Neural Information Processing Systems http://nips.cc/
fa84632d742f2729dc32ce8cb5d49733-Supplemental.pdf
However, a gradient is often insufficient to reconstruct the user data without any prior knowledge. By exploiting a generative model pretrained on the data distribution, we demonstrate that data privacy can be easily breached.
TeachLess, LearnMore: OntheUndistillableClassesinKnowledgeDistillation
A counter-intuitive observation is that a more expansive teacher does not make a better student, but the reasons for this phenomenon remain unclear.
Differentially Private Covariance Estimation
Kareem Amin, Travis Dick, Alex Kulesza, Andres Munoz, Sergei Vassilvitskii
Neural Information Processing Systems http://nips.cc/
DETOX: A Redundancy-based Framework for Faster and More Robust Gradient Aggregation
Shashank Rajput, Hongyi Wang, Zachary Charles, Dimitris Papailiopoulos
Neural Information Processing Systems http://nips.cc/
Discovery of Options via Meta-Learned Subgoals
Temporal abstractions in the form of options have been shown to help reinforcement learning (RL) agents learn faster.
