Zobrazeno 1 - 6
of 6
pro vyhledávání: '"Dung, Daniel"'
Recent developments in generative models have demonstrated its ability to create high-quality synthetic data. However, the pervasiveness of synthetic content online also brings forth growing concerns that it can be used for malicious purposes. To ens
Externí odkaz:
http://arxiv.org/abs/2409.14700
We consider the problem of model multiplicity in downstream decision-making, a setting where two predictive models of equivalent accuracy cannot agree on the best-response action for a downstream loss function. We show that even when the two predicti
Externí odkaz:
http://arxiv.org/abs/2405.19667
Federated Learning (FL) aims to foster collaboration among a population of clients to improve the accuracy of machine learning without directly sharing local data. Although there has been rich literature on designing federated learning algorithms, mo
Externí odkaz:
http://arxiv.org/abs/2302.08533
Consider a bandit algorithm that recommends actions to self-interested users in a recommendation system. The users are free to choose other actions and need to be incentivized to follow the algorithm's recommendations. While the users prefer to explo
Externí odkaz:
http://arxiv.org/abs/2206.00494
We study privacy-preserving exploration in sequential decision-making for environments that rely on sensitive data such as medical records. In particular, we focus on solving the problem of reinforcement learning (RL) subject to the constraint of (jo
Externí odkaz:
http://arxiv.org/abs/2202.01292
Publikováno v:
Highland Medical Research Journal; Vol 17, No 1 (2017); 50-54
Background: Anaesthesia has evolved over the decades to have become a specialty in medicine. The dearth of personnel and unavailability of required equipment world over has made safe delivery of anaesthesia difficult. This study evaluated workforce s