About

I am a CS PhD student at Stanford’s STAIR lab, where we are working on human-AI alignment. My research focuses on developing scalable oversight mechanisms and aligning AI systems with human preferences, drawing from mechanism design, information theory, and complex systems to create principled frameworks for human-AI collaboration. I have a strong theoretical background in optimization, learning theory, and probability theory, with experience integrating language models and reasoning to process complex information. I place a strong emphasis on rigorous empirical evaluation through ablation studies, benchmark development, and human-in-the-loop experiments.

Prior to Stanford, I obtained a masters in CS from UIUC and a bachelor’s in Computational and Applied Mathematics from University of Chicago. I have gained diverse research experience through internships at Google, where I designed tractable surrogates for welfare maximization with applications in ad click-through-rate prediction; Lam Research, optimizing semiconductor wafer production using reinforcement learning; and the Robot Intelligence through Perception Lab at TTIC, working on sparse-depth completion and natural language instruction following for robotic manipulation. I have also conducted research at the Exo-Planets Group at UChicago, improving spectrograph calibration using machine learning, and contributed to the Algorithmic Dynamics Lab, developing algorithms for estimating algorithmic complexity. Additionally, I bring technical business experience from Allen and Company, where I evaluated quantum computing startups and cryptocurrencies.

CV

Contact me

zroberts@stanford.edu

Ongoing Projects

  1. Zachary Robertson. GPT4 is Slightly Helpful for Peer-Review Assistance: A Pilot Study. arXiv preprint arXiv:2307.05492, 2023
  2. Zachary Robertson and Sanmi Koyejo. No Bidding, No Regret: Pairwise-Feedback Mechanisms for Digital Goods and Data Auctions. ISIT Workshop on Information-Theoretic Methods for Trustworthy Machine Learning, 2024

Publications

  1. Zachary Robertson and Sanmi Koyejo. Implicit Regularization in Feedback Alignment Learning Mechanisms for Neural Network. ICML, 2024.
  2. Boxiang Lyu, Zhe Feng, Zachary Robertson, and Sanmi Koyejo. Pairwise Ranking Losses of Click-Through Rates Prediction for Welfare Maximization in Ad Auctions. ICML, 2023
  3. Zachary Robertson, Hantao Zhang, and Sanmi Koyejo. Cooperative inverse decision theory for uncertain preferences. AISTATS, 2023
  4. Zachary Robertson, Hantao Zhang, and Sanmi Koyejo. Probabilistic performance metric elicitation. 1st Workshop on Human and Machine Decisions (WHMD 2021) at NeurIPS 2021, 2022
  5. Zachary Robertson and Matthew Walter. Concurrent training improves the performance of behavioral cloning from observation. arXiv preprint arXiv:2008.01205, 2020
  6. Julian Stürmer, Andreas Seifahrt, Zachary Robertson, Christian Schwab, and Jacob L Bean. Echelle++, a fast generic spectrum simulator. Publications of the Astronomical Society of the Pacific, 131(996):024502, 2018