Wednesday, September 28 |
| 1 p.m. | Sohir Maskey | LMU Munich | 'Stability to Deformations in Manifold Neural Networks. |
| 1:15 p.m. | Darshan Thaker | Johns Hopkins University | Generalization Analysis of Message Passing Neural Networks on Large Random Graphs |
| 1:30 p.m. | Muthu Chidambaram | Duke | Adaptive Conformal Inference Under Distribution Shift |
| 1:45 p.m. | John Cherian | Stanford | Probabilistically Robust Learning: Balancing Average- and Worst-case Performance |
| 2 p.m. | Chenwei Wu | Duke | T-Cal: An optimal test for the calibration of predictive models |
| 2:15 p.m. | Coffee Break |
| 3 p.m. | Alex Robey | Penn State | The Value of Out-of-Distribution Data |
| 3:15 p.m. | Alex Wei | Berkeley | Convolutional Filtering and Neural Networks with Non Commutative Algebras |
| 3:30 p.m. | Donghwan Lee | University of Pennsylvania | Reverse Engineering ℓp attacks: A block-sparse optimization approach with recovery guarantees |
| 3:45 p.m. | Liangzu Peng | Johns Hopkins | Collaborative Linear Bandits with Adversarial Agents: Near-Optimal Regret Bounds |
| 4 p.m. | Simon Zhai | Berkeley | Computational Benefits of Intermediate Rewards for Goal-Reaching Policy Learning |
| 4:15 p.m. | Yixuan Tan | Duke | Diffusion of Information on Networked Lattices by Gossip |
| 4:30 p.m. | Isaac Gibbs | Stanford | Distribution-free Prediction Sets Adaptive to Unknown Covariate Shift |
Friday, September 30 |
| 2:15 p.m. | Hans Reiss | University of Pennsylvania | Learning by Transference: Training Graph Neural Networks on Growing Graphs |
| 2:30 p.m. | Chen Xu | Duke | Space-Time Graph Neural Networks |
| 2:45 p.m. | Teresa Huang | Johns Hopkins University | Graph Neural Networks Are More Powerful Than We Think |
| 3 p.m. | Coffee Break |
| 3:30 p.m. | Ziqing Xu | Johns Hopkins University | More Than a Toy: Random Matrix Models Predict How Real-World Neural Representations Generalize |
| 3:45 p.m. | Juan Cervino | University of Pennslyvania | Global Linear and Local Superlinear Convergence of IRLS for Non-Smooth Robust Regression |
| 4:07 p.m. | Alejandro Parada-Mayorga | University of Pennslyvania | Towards Understanding the Data Dependency of Mixup-Style Training |
| 4:20 p.m. | Zhiyang Wang | University of Pennslyvania | Dissecting Hessian: Understanding Common Structure of Hessian in Neural Networks |
| 4:35 p.m. | Ashwin De Silva | Johns Hopkins University | Invertible Neural Networks for Graph Prediction |
| Samar Hadou | University of Pennslyvania | |
| Charilaos Kanatsoulis | University of Pennslyvania | From Local to Global: Spectral-Inspired Graph Neural Networks |
