Category: Data Science Education

The Problem of Social Cost in Multi-Agent Universal Reinforcement Learning

December 5, 2024

While I have worked on aspects of AI safety for quite a few years now, in particular privacy technologies and confidential computing, I am a late convert on the importance of Artificial General Intelligence (AGI) safety research and did not take the problem seriously until about 1 year ago. My mindset has now changed completely … More The Problem of Social Cost in Multi-Agent Universal Reinforcement Learning

Approximating Solomonoff Induction

November 23, 2024

As is well-known by now, the universal AI agent AIXI is made up of two key components: Solomonoff Induction for universal sequential prediction, and expectimax search for planning. There are several proposed and reasonably effective approximations of the Solomonoff Induction component using the factored, binarised Context Tree Weighting algorithm [WST95, VNHUS09] and its generalisation to … More Approximating Solomonoff Induction

Natural Exponential Functions in Inequalities

October 16, 2024

Have you ever wondered why the natural exponential function shows up so frequently in mathematical inequalities? Here’s a graph of the natural exponential function. The constant e has a special place in mathematics, which is beautifully chronicled in Eli Maor’s book [M94]. The definition of e that is most useful and intuitive for our purpose … More Natural Exponential Functions in Inequalities

Dealing with Linkage Attacks using Differential Privacy

September 13, 2024

A key claim of differential privacy in [DR14] is that it provides “automatic neutralization of linkage attacks, including all those attempted with all past, present, and future datasets and other forms and sources of auxiliary information”. This is an important and often repeated claim — see e.g. [N17, Section E] and [PR23] — but the … More Dealing with Linkage Attacks using Differential Privacy

Privacy Technologies for Financial Intelligence

August 20, 2024

It took a little while to write, but hopefully the following survey paper by Yang Li, Thilina Ranbaduge and yours truly can help demystify financial intelligence and privacy technologies for practitioners and technologists alike. The focus is on anti-money laundering and counter-terrorism financing, but the opportunity set is much broader. https://arxiv.org/abs/2408.09935 Here’s the abstract of … More Privacy Technologies for Financial Intelligence

What Can Differential Privacy Actually Protect?

July 6, 2024

Differential Privacy (DP) is, by now, the most widely adopted formal model of privacy protection used in industry [L23] and government [ABS22] but my sense is that its “semantics”, especially in the presence of correlated data and in the adversarial interactive setting, is still not broadly understood in the community, especially among practitioners. In the … More What Can Differential Privacy Actually Protect?

Notes on the Bretagnolle-Huber Inequality

June 28, 2024

The Bretagnolle-Huber Inequality provides a bound on the total variation distance between two probability distributions in terms of their Kullback-Leibler divergence, and it is better than Pinsker’s Inequality when the KL divergence is larger than two, and it is never vacuous, as shown in this figure from [Canonne2023]. The following is an elementary proof, which … More Notes on the Bretagnolle-Huber Inequality

A Tutorial Introduction to Lattice-based Cryptography and Homomorphic Encryption

September 3, 2022

A few of us have been working with homomorphic encryption for a number of years now, but we never found a paper / book that covers all the foundational mathematical material in one place. So we decided to write one — well my postdoc Kelvin Yang Li decided to write one and Mike Purcell and I assisted … More A Tutorial Introduction to Lattice-based Cryptography and Homomorphic Encryption