Alan Chan

Alan Chan

PhD Student

Mila

Introduction

I am a PhD student at Mila, advised by Nicolas Le Roux. Previously at Amii + UAlberta, I was an MSc student with Martha White. My research interests broadly include value alignment and AI governance. Recently, I have been interested in interpretability and assessing the implicit knowledge in language models. Please feel free to reach out to chat about anything!

Interests

  • Value alignment
  • AI governance

Education

  • PhD in Computer Science, 2024

    Université de Montréal

  • MSc in Computing Science, 2020

    University of Alberta

  • BSc in Mathematics, 2018

    University of Alberta

Research

I am broadly interested in the scientific and governance work in aligning AI systems with human values. My scientific research revolves around understanding and controlling the values that machine‑learning models express, with a focus on the measurement of harms from language models. On the governance side, I have recently been interested in regulation for the explainability of algorithmic systems.

Recent Papers

Loss of Control: "Normal Accidents" and AI Systems

A thread in recent work on the social impacts of AI systems is whether certain properties of a domain should preclude the application …
PDF

The Limits of Global Inclusion in AI Development

Those best-positioned to profit from the proliferation of artificial intelligence (AI) systems are those with the most economic power. …
Alan Chan, Chinasa Okolo, Zachary Terner, Angelina Wang
PDF

Approaching Ethical Impacts in AI Research: The Role of a Graduate Student

Extant societal challenges and the problematic applications of algorithmic systems so far have motivated broader consideration of the …
PDF

Inverse Policy Evaluation for Value-based Sequential Decision-making

Value-based methods for reinforcement learning lack generally applicable ways to derive behavior from a value function. Many approaches …
Alan Chan, Kris de Asis, Richard S. Sutton
PDF

Training Recurrent Neural Networks Online by Learning Explicit State Variables

Recurrent neural networks (RNNs) allow an agent to construct a state-representation from a stream of experience, which is essential in …
Somjit Nath, Vincent Liu, Alan Chan, Xin Li, Adam White, Martha White
PDF
See all publications

Recent & Upcoming Talks

MSc Seminar

My seminar for my MSc thesis.
Aug 14, 2020 12:00 AM
PDF

Problems with Fair ML

This talk will be a mostly non-technical dive into problems that I find with a lot of fair ML research today. I will begin with some …
Jul 28, 2020 12:00 AM
PDF

Recent Posts

Education

One of the defining experiences of my intellectual development was the entirety of high school social studies, two years of which I spent with somebody who has shaped my thought the most critically.
Last updated on Jun 14, 2020 3 min read

Languages

I always struggle with the languages box on applications: what do I put for Cantonese and Mandarin? I’m sure that I don’t speak them fluently or even moderately well, but I’m not a beginner either.
Last updated on Nov 18, 2020 8 min read

Talking to Strangers

My last daily chat with a stranger was several months ago. Last year, motivated mostly by the positive experiences of a friend who had done a similar challenge, I decided to find somebody new—usually a student on campus—to talk to every day.
Last updated on Oct 2, 2020 7 min read

Coping and Learning

When I was in junior high school, I had already grown a shell of isolation. When we feel lonely, especially after a prolonged period of time, it is more difficult to reach out, even accept, the social interaction we need to warm the frigidity in our hearts.
Last updated on Aug 10, 2020 5 min read

Conflicts in Categorizing

Disclaimers I use the word category quite loosely in this piece. I do not refer to the mathematical field of Category Theory, although there may be some interesting, unexplored connections there.
Last updated on Aug 2, 2020 9 min read
See all posts