http://www.tracyke.net New Advances in Statistics and Data Science



New Advances in Statistics and Data Science

May 24-26, 2022, Honolulu, Hawaii



Day 3 (May 26, 2022): New Advances in Machine Learning


8:40am - 10:20am: Session 1 (Chair: Tracy Ke)
  • Yingying Fan: Asymptotic Properties of High-dimensional Random Forests (abstract)

  • Edgar Dobriban: T-Cal: An Optimal Test for the Calibration of Predictive Models (abstract)

  • Jun S. Liu: Statistics Meet Neural Networks: Bootstrap, Cross-Validations, and Beyond (abstract)

  • Jianqing Fan: How Do Noise Tails Impact on Deep ReLU Networks? (abstract)

10:20am - 10:40am: Coffee break

11:20am - 12:10pm: Session 2 (Chair: Jason Lee)
  • Tony Cai: Transfer Learning: Optimality and Adaptive Algorithms (abstract)

  • Patrick Rubin-Delanchy: Manifold Structure in Graph Embeddings (abstract)

  • Tengyu Ma: Understanding Self-supervised Learning (abstract)

12:10pm - 1:40pm: Lunch break

1:40pm - 3:20pm: Session 3 (Chair: Qi Lei)
  • Jason Lee: Offline Reinforcement Learning with only Realizability (abstract)

  • Yuejie Chi: Offline Reinforcement Learning: Towards Optimal Sample Complexities (abstract)

  • Adel Javanmard: The Curse of Overparametrization in Adversarial Training (abstract)

  • Simon Du: When is Offline Two-Player Zero-Sum Markov Game Solvable? (abstract)

3:20pm - 3:40pm: Break

3:40pm - 5:20pm: Session 4 (Chair: Yuejie Chi)
  • Quan Zhou: Informed MCMC Sampling for High-dimensional Model Selection Problems (abstract)

  • Krishna Balasubramanian: Towards a Theory of Non-Log-Concave Sampling (abstract)

  • Boxiang Wang: Sparse Convoluted Rank Regression in High Dimensions (abstract)

  • Yuqi Gu: Blessing of Latent Dependence and Identifiable Deep Modeling of Discrete Latent Variables (abstract)