Michael Zhang
I’m Michael Zhang, a fifth year PhD student at the University of Toronto and Vector Institute, where I am fortunate to be supervised by Jimmy Ba and supported by the NSERC CGS Fellowship.
I'm interested in improving our understanding of neural networks and developing algorithms which are theoretically motivated and work across a broad set of problems. I did my undergrad and Master's at the University of California, Berkeley, where I did robotics research in Pieter Abbeel's group. I've previously done internships at Tesla, Google Research, and LinkedIn.
You can contact me at [first name] @cs.toronto.edu.
CV  / 
Google Scholar  / 
Twitter  / 
Substack
|
|
News
- May 2023: I'm grateful to receive the Schwartz Reisman Institute graduate fellowship!
- Apr 2023: We released a new preprint on a prompt boosting algorithm with large language models: arxiv.
- Feb 2023: Multi-Rate VAE received an oral presentation (top-5% of accepted papers) at ICLR.
- Jan 2023: I am an instructor for CSC311: Intro to Machine Learning this semester!
|
Research
Some topics I am currently interested in:
-improving our understanding of deep neural network optimization
-Can we make hyperparameter tuning easier (e.g. more efficient and automated)?
-How can we develop current and future AI models that are more likely to be socially positive?
A full list of publications is on Google Scholar.
|
Decomposed Prompting to Answer Questions on a Course Discussion Board
Brandon Jaipersaud, Paul Zhang, Jimmy Ba, Andrew Petersen, Lisa Zhang, Michael R. Zhang
AIED 2023
Paper
We propose and evaluate a question-answering system that uses decomposed prompting to classify and answer student questions on a course discussion board.
|
Multi-Rate VAE: Train Once, Get the Full Rate-Distortion Curve
Juhan Bae, Michael R. Zhang, Michael Ruan, Eric Wang, So Hasegawa, Jimmy Ba, Roger Grosse
ICLR 2023 (top-5% of accepted papers)
Paper
We propose Multi-Rate VAE (MR-VAE), a hypernetwork which is capable of learning multiple VAEs with different rates in a single training run.
|
Autoregressive Models for Offline Policy Evaluation and Optimization
Michael R. Zhang, Tom Le Paine, Ofir Nachum, Cosmin Paduraru, George Tucker, Ziyu Wang, Mohammad Norouzi
ICLR 2021
Paper /
Video
Autoregressive models are better for learning dynamics models than standard feedforward models in the fixed dataset setting.
|
Analyzing Monotonic Linear Interpolation in Neural Network Loss Landscapes
James Lucas, Juhan Bae, Michael R. Zhang , Stanislav Fort, Richard Zemel, Roger Grosse
ICML 2021
Paper
We investigate and analyze why many neural networks have the loss decreasing monotonically in weight space from initialization to final solution.
|
Objective Social Choice: Using Auxiliary Information to Improve Voting Outcomes
Silviu Pitis, Michael R. Zhang
AAMAS 2020
Paper /
Code /
Video
Framework and aggregation rules for combining the preferences of multiple agents with noisy views of some ground truth.
|
Lookahead Optimizer: k steps forward, 1 step back
Michael R. Zhang, James Lucas, Geoffrey Hinton, Jimmy Ba
NeurIPS 2019
Paper /
Code /
Video
Optimization algorithm that speeds up training by using a search direction generated by multiple steps of an inner optimizer.
|
Reverse Curriculum Generation for Reinforcement Learning
Carlos Florensa, David Held, Markus Wulfmeier, Michael Zhang, Pieter Abbeel
CoRL 2017
Webpage /
Paper /
Blog post
Approach for tackling sparse reward tasks by generating goals of intermediate difficulty.
|
Probabilistically Safe Policy Transfer
David Held, Zoe McCarthy, Michael Zhang, Fred Shentu, Pieter Abbeel
ICRA 2017
Paper /
Video
Framework for safely transferring policies learning in simulation to the real world.
|
Misc.
I try to adhere to the principle "journey before destination" (Brandon Sanderson).
Some activities I enjoy: basketball, running, exploring new places, reading, improv.
2020 Book Recs
|
|