About Me

I am a 5-th year computer science PhD student at Stanford, advised by Stefano Ermon. I completed my bachelors in engineering physics at the University of Illinois at Urbana-Champaign.

Contact: jkuck at cs dot stanford dot edu
CV

Research Interests

  • Approximate probabilistic inference
  • Combining probabilistic modeling with deep learning
  • Graph neural networks and learning on irregular data (graphs, sets, and point clouds)
  • Robotic perception: object detection and tracking
  • Uncertainty quantification

Publications

  1. Approximating the Permanent by Sampling from Adaptive Partitions
    Jonathan Kuck, Tri Dao, Hamid Rezatofighi, Ashish Sabharwal, Stefano Ermon
    Neural Information Processing Systems (NeurIPS), 2019
    [paper] [code] [poster]
  2. Adaptive Hashing for Model Counting
    Jonathan Kuck, Tri Dao, Shenjia Zhao, Burak Bartan, Ashish Sabharwal, Stefano Ermon
    Uncertainty in Artificial Intelligence (UAI), 2019
    [paper] [code] [poster]
  3. Approximate Inference via Weighted Rademacher Complexity
    Jonathan Kuck, Ashish Sabharwal, Stefano Ermon
    Conference on Artificial Intelligence (AAAI), 2018
    [paper] [code] [blog]
  4. Query-Based Outlier Detection in Heterogeneous Information Networks
    Jonathan Kuck*, Honglei Zhuang*, Xifeng Yan, Hasan Cam, Jiawei Han
    International Conference on Extending Database Technology (EDBT), 2015
    [paper]

Preprints

  1. Belief Propagation Neural Networks
    Jonathan Kuck, Shuvam Chakraborty, Hao Tang, Rachel Luo, Jiaming Song, Ashish Sabharwal, Stefano Ermon
    [paper]

Teaching

Winter 2018, Stanford: head course assistant for Probabilistic Graphical Models

Fun

I like sports. I enjoy the outdoors, rock climbing, tennis, and rolling on balance balls. I used to focus on speedskating.