5 Hits in 3.6 sec

Shuffle Private Linear Contextual Bandits [article]

Sayak Ray Chowdhury, Xingyu Zhou
2022 arXiv   pre-print
We propose a general algorithmic framework for linear contextual bandits under the shuffle trust model, where there exists a trusted shuffler in between users and the central server, that randomly permutes  ...  Differential privacy (DP) has been recently introduced to linear contextual bandits to formally address the privacy concerns in its associated personalized services to participating users (e.g., recommendations  ...  Achieving SDP via LDP Amplification In this section, we show that our general framework (Algorithm 1) enables us to directly utilize existing LDP mechanisms for linear contextual bandits to achieve a finer  ... 
arXiv:2202.05567v1 fatcat:z5mnuy4jtvhubfitvvfccfpvke

Local Differential Privacy for Regret Minimization in Reinforcement Learning [article]

Evrard Garcelon, Vianney Perchet, Ciara Pike-Burke, Matteo Pirotta
2021 arXiv   pre-print
We formulate this notion of privacy for RL by leveraging the local differential privacy (LDP) framework.  ...  We establish a lower bound for regret minimization in finite-horizon MDPs with LDP guarantees which shows that guaranteeing privacy has a multiplicative effect on the regret.  ...  Algorithms for differentially private multi-armed bandits. In AAAI, pages 2087-2093. AAAI Press, 2016. Roshan Shariff and Or Sheffet. Differentially private contextual linear bandits.  ... 
arXiv:2010.07778v3 fatcat:76bncyh47zgr3bvtu5qf52gxnm

A Roadmap for Big Model [article]

Sha Yuan, Hanyu Zhao, Shuai Zhao, Jiahong Leng, Yangxiao Liang, Xiaozhi Wang, Jifan Yu, Xin Lv, Zhou Shao, Jiaao He, Yankai Lin, Xu Han (+88 others)
2022 arXiv   pre-print
With the rapid development of deep learning, training Big Models (BMs) for multiple downstream tasks becomes a popular paradigm.  ...  In this paper, we cover not only the BM technologies themselves but also the prerequisites for BM training and applications with BMs, dividing the BM review into four parts: Resource, Models, Key Technologies  ...  transformer for learning contextualized video embeddings.  ... 
arXiv:2203.14101v4 fatcat:rdikzudoezak5b36cf6hhne5u4

Machine learning for quantum and complex systems [article]

Aaron Tranter, University, The Australian National
The combination of these two advances yields an opportunity for study, namely leveraging the power of machine learning to control and optimise quantum (and more generally complex) systems.  ...  If we are to one day harness the true power of quantum key distribution for secure transimission of information, and more general quantum computating tasks, it will almost certainly involve the use of  ...  Ruvi, the Baileys loving bandit, thanks for the laughs. Daniel, your opinions on specific details that I never would have thought of is great, all the best.  ... 
doi:10.25911/antn-e124 fatcat:3ymhah5e7rgq7eqaiyjheu7zfe

Salvaging the subject: mediant fiction contra the mass media

Mario Thomas Trono
Each extension is an amplification that in varying but measurable degrees, alters the hierarchy o f sensory preference in ordering daily experience and environment for whole populations.  ...  Entering this odeum, as reader at the termination of the story, transcendence via a rainbow arc is denied you; you wait not for God or Godot, but for the social agent that shapes your life; you "wait there  ... 
doi:10.7939/r3-654m-d331 fatcat:hr2sdkptbjeihloj2fjikwrqxe