Chris Cundy

Machine Learning PhD Student

Stanford University

Hi

I am broadly interested in Artificial Intelligence (AI), particularly in ensuring that sophisticated AI systems will robustly and reliably carry out the tasks that we want them to.

If you’re a student at Stanford (undergraduate/masters/PhD) who wants to work on a project involving safe and reliable machine learning: get in touch!

I studied Physics as an undergraduate at Cambridge University before switching area to take a computer science master’s degree. During my master’s, it was a pleasure to work with Carl E. Rasmussen, developing variational methods for Gaussian Process State-Space Models.

Before starting my PhD at Stanford, I worked at the Centre for Human Compatible AI, collaborating with Stuart Russell and Daniel Filan. I have also worked at the Future of Humanity Institute at Oxford University, collaborating with Owain Evans on scalable human supervision of complex AI tasks.

Get in touch at chris dot j dot cundy at gmail dot com

Interests

Probabilistic Machine Learning
Generative Models
Reinforcement Learning
Safe and Reliable ML

Education

PhD in Computer Science, 2018-Ongoing
Stanford University
MEng in Computer Science, 2017
Cambridge University
BA in Natural Sciences (Physics), 2016
Cambridge University

Recent Publications

Quickly discover relevant content by filtering publications.

IQ-Learn: Inverse soft-Q Learning for Imitation

In many sequential decision-making problems (e.g., robotics control, game playing, sequential prediction), human or expert data is …

Divyansh Garg, Shuvam Chakraborty, Chris Cundy, Jiaming Song, Stefano Ermon

Scalable Variational Approaches for Bayesian Causal Discovery

A structural equation model (SEM) is an effective framework to reason over causal relationships represented via a directed acyclic …

Chris Cundy, Aditya Grover, Stefano Ermon

Privacy-Constrained Policies via Mutual Information Regularized Policy Gradients

As reinforcement learning techniques are increasingly applied to real-world decision problems, attention has turned to how these …

Chris Cundy, Stefano Ermon

Flexible Approximate Inference via Stratified Normalizing Flows

Chris Cundy, Stefano Ermon

Exploring hierarchy-aware inverse reinforcement learning

Chris Cundy, Daniel Filan

See all publications

Recent Posts

Using Codex in the Wild

Introduction Following on from my previous article about using codex in emacs, I’ve found my plug-in more and more useful in everyday programming. Some general impressions At the moment, the results are on par with what I’d expect from a decent undergraduate programmer.

Last updated on Apr 15, 2022 3 min read

Using Codex in Emacs

Introduction Recently OpenAI released their ‘editing mode’ API for their language models. In this mode (which you can select by clicking on the ‘mode’ selector on the right-hand-side), we are able to put a piece of context (such as a code snippet) called the ‘input’ and an instruction (such as change the sort to use a heapsort’).

Last updated on May 15, 2022 7 min read

The Adjoint Method in a Dozen Lines of JAX

The Adjoint Method is a powerful method for computing derivatives of functions involving constrained optimization. It’s been around for a long time, but recently has been popping up in machine learning, used in papers such as the Neural ODE and many others.

Last updated on Mar 26, 2022 5 min read

Running GPT-J On Several Smaller GPUs

Introduction Recently several large language models have been open-sourced. Particularly interesting is GPT-J, which has completely open-sourced weights and provides pre-trained weights. The model itself has performance comparable to the smallest version of GPT3.

Last updated on Mar 26, 2022 2 min read

Mutual Information Regularization for Reward Hacking

Introduction In some recent work that we just put up on arxiv, we explore the idea of training reinforcement agents which obey privacy constraints. Something I’ve wanted to explore for a while is the possibility of using this constrained RL approach for dealing with reward hacking.

Last updated on Mar 26, 2022 9 min read