Jonathan Li(ght)
I am currently a Ph.D. student at Rensselaer Polytechnic Institute, Troy NY (RPI).
Broadly speaking, I am interested in the interplay between incentives (economics), algorithms (computer science), and learning (statistics), including
algorithmic game theory, online learning, sequential decision making, reinforcement learning, data economics, market design, multi-agent systems.
My current work is focused on foundation models for decision making, where we combine traditional sequential decision making methods with foundation models.
I like collaborations! Reach out if you've got a cool problem you'd like to chat about.
"Know what you know and know what you do not know. That is true wisdom." -- Confucious
In modern words, know the known knowns, known unknowns, and unknown unknowns. I feel like this is a good way to approach research, and life in general, and is particularly relevant to creating intelligent machines.
In my spare time, I enjoy playing and designing board games, reading science fiction, electronic music composition, and fencing. I find well designed games to be extremely elegant, and a great inspiration for research.
Email  / 
LinkedIn  / 
Github  / 
CV
(may be slightly outdated)
|
|
Education
Ph.D.           Sep 2023 - Present
                       Rensselaer Polytechnic Institute (RPI), Troy, NY, U.S.
                       Ph.D. student in Computer Science
|
|
M.S.              Aug 2021 - Mar 2023
                       University of Chicago, Chicago, IL, U.S.
                       M.S. in Financial Mathematics
|
|
B.S.              Aug 2017 - May 2021
                       Reed College, Portland, OR, U.S.
                       B.S. in Mathematics and Economics
|
|
|
|
From Text to Tactic: Evaluating LLMs Playing the Game of Avalon
Jonathan Light*, Min Cai, Sheng Shen, Ziniu Hu
NeurIPS Foundation Models for Decision Making Workshop , 2023
|
|
Strategist: Learning Strategic Skills by LLMs via Bi-Level Tree Search
Jonathan Light*, Min Cai, Weiqin Chen, Guanzhi Wang, Xiusi Chen, Wei Cheng, Yisong Yue, Ziniu Hu
ICML Automated Reinforcement Learning: Exploring Meta-Learning, AutoML, and LLMs Workshop, 2024
|
|
Dataset Distillation for Offline Reinforcement Learning
Jonathan Light*, Yuanzhe Liu, Ziniu Hu
ICML Data-centric Machine Learning Research Workshop, 2024
|
Teaching
-
Teaching Assistant, AI and Blockchain, Dacheng Xiu. Booth School of Business Executive MBA Program, 2023 Summer
-
Teaching Assistant, Options Pricing, Roger Lee. University of Chicago PSD, 2023 Spring
-
Teaching Assistant, Bayesian Statistical Inference and ML, Gordan Ritter. University of Chicago PSD, 2023 Spring
-
Teaching Assistant, Decoding Fintech, Dacheng Xiu. Booth School of Business, 2023 Winter
-
Teaching Assistant, Mathematical Statistics, Jonathan Wells. Reed College, 2021 Spring
-
Teaching Assistant, Probability Theory, Jonathan Wells. Reed College, 2020 Fall
-
Teaching Assistant, Macroeconomics, Zhe (Jasmine) Jiang. Reed College, 2020 Fall
-
Teaching Assistant, Econometrics, Fellipe Carrera. Reed College, 2020 Fall
-
Teaching Assistant, Introduction to Analysis, David Krumm. Reed College, 2019 Fall
|
Honors and Awards
-
Phi Beta Kappa, 2021
-
Reed Commendation for Excellence in Scholarship, 2018, 2019, 2020, 2021
-
Reed Science Research Fellow, 2020
-
Reed Financial Services Fellow, 2019
|
Other Notes
I go by either Jonathan Li or Jonathan Light. I usually use Light in publications because
-
Li is a very common last name and people often get confused with all the other people that share the same name as me
-
Light is the semantic translation of both my Chinese given name and courtesy name
-
Light nearly preserves the lexigraphic ordering of Li
I've also considered using 'Plum' (semantic translation of my last name), but it doesn't have the same ring to it, nor does it preserve the lexigraphic ordering of Li. Generally I find semantic translations to be more faithful to the original meaning, as convenient as pinyin is for romanization.
|
Other Quotes and Historical Tidbits
I find quotes and historical tidbits to be a great source of inspiration and very fascinating. Here are some of my favorites that I've collected over the years.
Quotes:
-
"Ask yourself whether you are happy, and you cease to be so" -- John Stuart Mill. Says something about opportunity cost and the paradox of choice
-
"The best is the enemy of the good" -- Voltaire. This principle is used so often in optimization, approximation, and machine learning
-
"Stay hungry. Stay foolish" -- Steve Jobs. It's good to be foolish. Then you can ask the questions that others are afraid to ask
|
|