Kaiwen Wu PhD Student Computer and Information Science University of Pennsylvania Email: kaiwenwu@seas.upenn.edu Links to GitHub, Twitter, Google Scholar, Blog. How to pronounce my first name

About Me

I am a third-year PhD student in computer and information science at the University of Pennsylvania, advised by Jacob Gardner. Previously, I completed my MMath degree in computer science at the University of Waterloo, where I worked on trustworthy machine learning with Yaoliang Yu. I did my undergraduate at Nanjing University.

I am interested in machine learning and optimization. My recent work focuses on scaling up computation in probabilistic machine learning. Specifically, I work on Gaussian processes, variational inference, and Bayesian optimization. I am also interested in convex optimization and deep generative modeling.

Research

* indicates equal contribution. See Google Scholar for a complete list of publications.

Publications

• Understanding Stochastic Natural Gradient Variational Inference
  Kaiwen Wu and Jacob R. Gardner
  International Conference on Machine Learning (ICML 2024)
  [arXiv] [code]


• Large-Scale Gaussian Processes via Alternating Projection
  Kaiwen Wu, Jonathan Wenger, Haydn Jones, Geoff Pleiss and Jacob R. Gardner
  International Conference on Artificial Intelligence and Statistics (AISTATS 2024)
  [arXiv] [code]


• The Behavior and Convergence of Local Bayesian Optimization
  Kaiwen Wu, Kyurae Kim, Roman Garnett and Jacob R. Gardner
  Advances in Neural Information Processing Systems (NeurIPS 2023)
  Spotlight Presentation
  [arXiv] [code]


• On the Convergence of Black-Box Variational Inference
  Kyurae Kim, Jisu Oh, Kaiwen Wu, Yian Ma and Jacob R. Gardner
  Advances in Neural Information Processing Systems (NeurIPS 2023)
  [arXiv] [code]


• Local Bayesian Optimization via Maximizing Probability of Descent
  Quan Nguyen*, Kaiwen Wu*, Jacob R. Gardner and Roman Garnett
  Advances in Neural Information Processing Systems (NeurIPS 2022)
  Oral Presentation
  [arXiv] [code]


• Stronger and Faster Wasserstein Adversarial Attacks
  Kaiwen Wu, Allen Houze Wang and Yaoliang Yu
  International Conference on Machine Learning (ICML 2020)
  [arXiv] [code]


• On Minimax Optimality of GANs for Robust Mean Estimation
  Kaiwen Wu, Gavin Weiguang Ding, Ruitong Huang and Yaoliang Yu
  International Conference on Artificial Intelligence and Statistics (AISTATS 2020)
  [proceedings] [code]

Workshop Papers

• A Fast, Robust Elliptical Slice Sampling Implementation for Linearly Truncated Multivariate Normal Distributions
  Kaiwen Wu and Jacob R. Gardner
  Workshop on Bayesian Decision-Making and Uncertainty at NeurIPS 2024
  [arXiv] [code]


• Newton-type Methods for Minimax Optimization
  Guojun Zhang, Kaiwen Wu, Pascal Poupart and Yaoliang Yu
  Workshop on Beyond First-Order Methods in ML Systems at ICML 2021
  [arXiv] [code]

Miscellaneous

I write notes when I have time. Sadly, some notes take forever to finish.

• A Gentle Introduction to Variational Gaussian Processes
• Concepts in Smooth Manifolds and Differential Geometry
• Normalization in GP
• L1 Norm Projection

I have reviewed (or will review) for the following conferences: AAAI 2021, AISTATS 2021, ICML 2023, NeurIPS 2023, ICLR 2024, AISTATS 2024, ICML 2024, NeurIPS 2024, ICLR 2025.

A website calculating an upper bound of the Erdős number. (Yes, it overestimates my Erdős number.)