The cartoon by Nicky Case explaining digital contact tracing: https://ncase.me/contact-tracing/

The white paper explaining the DP-3T protocol app: https://github.com/DP-3T/documents/blob/master/DP3T%20White%20Paper.pdf

In this episode, we discuss the security and privacy challenges in machine learning.

A Marauder's Map of Security and Privacy in Machine Learning | Nicolas Papernot https://arxiv.org/abs/1811.01134

We discuss the exploration-exploitation dilemma and near-optimal solutions found by mathematicians.

Some relevant ressources include:

Bayesian Adaptive Methods for Clinical Trials. CRC Press. Berry, Carlin, Lee & Muller (2010).

https://www.crcpress.com/Bayesian-Adaptive-Methods-for-Clinical-Trials/Berry-Carlin-Lee-Muller/p/book/9781439825488

Bayesian adaptive clinical trials: a dream for statisticians only? Statistics in Medicine. Chrevret (2011).

https://onlinelibrary.wiley.com/doi/abs/10.1002/sim.4363

Multi-armed Bandit Models for the Optimal Design of Clinical Trials: Benefits and Challenges. Statistical Science. Villar, Bowden & Wason (2015).

"Across this literature, the use of bandit models to optimally design clinical trials became a typical motivating application, yet little of the resulting theory has ever been used in the actual design and analysis of clinical trials."

https://arxiv.org/pdf/1507.08025.pdf

Machine learning applications in drug development. Computational and Structural Biotechnology Journal. Réda, Kaufmann & Delahaye-Duriez (2019).

https://www.sciencedirect.com/science/article/pii/S2001037019303988

Rethinking the Gold Standard With Multi-armed Bandits: Machine Learning Allocation Algorithms for Experiments. Kaibel & Bieman (2019)

https://journals.sagepub.com/doi/abs/10.1177/1094428119854153

Cancer specialists in disagreement about purpose of clinical trials. Journal of the National Cancer Institute (2012).

https://www.eurekalert.org/pub_releases/2002-12/jotn-csi121202.php

WHO launches global megatrial of the four most promising coronavirus treatments. Science Mag. Kupferschmidt & Cohen (2020).

https://www.sciencemag.org/news/2020/03/who-launches-global-megatrial-four-most-promising-coronavirus-treatments

AI Safety via Debate:

https://arxiv.org/pdf/1805.00899.pdf

In this episode, Lê Louis and El Mahdi discuss social media manipulation and the difficult question of misinformation spread on social media. We also comment a bit on the current coronavirus pandemic context.

SmarterEveryday playlist on Social Media Manipulation: https://www.youtube.com/watch?v=MUiYglgGbos&list=PLjHf9jaFs8XVAQpJLdNNyA8tzhXzhpZHu

WeBuildAI: Participatory Framework for Algorithmic Governance. LKKKY+19

https://www.cs.cmu.edu/~akahng/papers/webuildai.pdf

Find out more on the RB Wiki:

https://robustlybeneficial.org/wiki/index.php?title=Social_choice

https://robustlybeneficial.org/wiki/index.php?title=Interpretability

A Roadmap for Robust End-to-End Alignment. Lê Nguyên Hoang 18.

https://arxiv.org/pdf/1809.01036

Find out more on the Robustly Beneficial Wiki:

https://robustlybeneficial.org/wiki/index.php?title=ABCDE_roadmap

Next week's paper is WeBuildAI: Participatory Framework for Algorithmic

Governance. PACMHCI. LKKKY+19.

https://www.cs.cmu.edu/~akahng/papers/webuildai.pdf

Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model.

SAHSS+19.

https://arxiv.org/abs/1911.08265

Find out more on the Robustly Beneficial Wiki:

https://robustlybeneficial.org/wiki/index.php?title=Reinforcement_learning

Next week's paper is:

A Roadmap for Robust End-to-End Alignment. LN Hoang 18.

https://arxiv.org/abs/1809.01036

Intelligent Autonomous Things on the Battlefield. AI for the Internet of Everything. A Kott and E Stump 19.

https://arxiv.org/ftp/arxiv/papers/1902/1902.10086.pdf

Slaughterbots. Future of life Institute 17.

https://www.youtube.com/watch?v=HipTO_7mUOw

The Future of War, and How It Affects YOU (Multi-Domain Operations). Smarter Every Day 211.

https://www.youtube.com/watch?v=qOTYgcdNrXE

Find out more on the Robustly Beneficial Wiki:

https://robustlybeneficial.org/wiki/index.php?title=Robustly_beneficial

https://robustlybeneficial.org/wiki/index.php?title=Robust_statistics

Next week's paper is about MuZero.

Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model. SAHSS+20.

https://arxiv.org/abs/1911.08265

Preference learning from comparisons. Lucas Maystre 2018. EPFL PhD Thesis.

https://infoscience.epfl.ch/record/255399/files/EPFL_TH8637.pdf

Find out more on our Wiki:

https://robustlybeneficial.org/wiki/index.php?title=Volition

https://robustlybeneficial.org/wiki/index.php?title=Preference_learning_from_comparisons