About Me

I am a PhD student at the Department of Computer Science at Stanford University advised by Stefano Ermon. I research prediction models and autonomous agents that can be reliably deployed in high-stakes applications, and can continuously accumulate knowledge and acquire information to improve performance. Topics I am currently interested in include probabilistic deep learning, uncertainty quantification, experimental design, and ML for science.

Contact: sjzhao at stanford dot edu

Selected Publications

For a full list of publications sorted by topic see here

  • Comparing Distributions by Measuring Differences that Affect Decision Making
    Shengjia Zhao*, Abhishek Sinha*, Yutong He*, Aidan Perreault, Jiaming Song, Stefano Ermon [openreview] (ICLR’22 Outstanding paper award 0.15%)

  • Calibrating Predictions to Decisions: A Novel Approach to Multi-Class Calibration
    Shengjia Zhao, Michael P Kim, Roshni Sahoo, Tengyu Ma, Stefano Ermon [arXiv] (Neurips’2021)

  • Reliable Decisions with Threshold Calibration
    Roshni Sahoo, Shengjia Zhao, Alyssa Chen, Stefano Ermon (Neurips’2021)

  • Right Decisions from Wrong Predictions: A Mechanism Design Alternative to Individual Calibration
    Shengjia Zhao, Stefano Ermon [arXiv] (AISTATS’2021 Oral 3.1%)

  • Improved Autoregressive Modeling with Distribution Smoothing
    Chenlin Meng, Jiaming Song, Yang Song, Shengjia Zhao, Stefano Ermon (ICLR’2021 Oral 1.8%) openreview

  • Individual Calibration with Randomized Forecast
    Shengjia Zhao, Tengyu Ma, Stefano Ermon [arXiv] (ICML’2020)

  • A framework for Sample Efficient Interval Estimation with Control Variates
    Shengjia Zhao, Christopher Yeh, Stefano Ermon [arXiv] (AISTATS’2020)

  • A Theory of Usable Information under Computational Constraints
    Yilun Xu, Shengjia Zhao, Jiaming Song, Russell Stewart, Stefano Ermon [arXiv] (ICLR’2020 Oral 1.9%)

  • InfoVAE: Balancing Learning and Inference in Variational Autoencoders
    Shengjia Zhao, Jiaming Song, Stefano Ermon [arXiv] (AAAI’2019)

  • Adaptive Antithetic Sampling for Variance Reduction
    Hongyu Ren*, Shengjia Zhao*, Stefano Ermon [paper] (ICML’2019)

  • Learning Neural PDE Solvers with Convergence Guarantees
    Jun-Ting Hsieh*, Shengjia Zhao*, Lucia Mirabella, Stefano Ermon [arXiv] (ICLR’2019)

  • Bias and Generalization in Deep Generative Models: An Empirical Study
    Shengjia Zhao*, Hongyu Ren*, Arianna Yuan, Jiaming Song, Noah Goodman, Stefano Ermon [arXiv] (NeurIPS’2018 Spotlight 3%)

  • A Lagrangian Perspective on Latent Variable Generative Models
    Shengjia Zhao, Jiaming Song, Stefano Ermon [arXiv] (UAI’2018 Oral 8.6%)

  • A-NICE-MC: Adversarial Training for MCMC
    Jiaming Song, Shengjia Zhao, Stefano Ermon [arXiv] [code] (NeurIPS’2017)

  • Learning Hierarchical Features from Generative Models
    Shengjia Zhao, Jiaming Song, Stefano Ermon [arXiv] (ICML’2017)

  • Adaptive Concentration Inequalities for Sequential Decision Problems
    Shengjia Zhao, Enze Zhou, Ashish Sabharwal, Stefano Ermon [pdf] (NeurIPS’2016)

Awards and Fellowships

  • ICLR’2022 Outstanding Paper Award (2022)
  • JP Morgan PhD Fellowship (2019)
  • Qualcomm Innovation Fellowship (QInF) (2018)
  • Qualcomm Scholarship (2016)
  • Google Excellence Scholarship (2015)

Teaching and Services

  • Reviewer: NeurIPS (2017, 2019, 2020, 2021), ICLR (2019, 2020, 2021), ICML (2019, 2020, 2021)
  • Organizer: Information Theory and Machine Learning (ITML) Workshop (NeurIPS’2019)
  • Teaching: CS228 Head TA (2019 and 2021)