news
| Dec 05, 2024 | AI systems are omni-present, yet extrapolate unreliably. Improving AI safety and capabilities hinges on comprehension of uncertainty and actively making decisions to resolve it. Instead of cumbersome probabilistic models, my team leverages a predictive view of uncertainty to build a scalable framework based on autoregressive models. Watch this recent Simons talk to learn more. |
|---|---|
| Oct 15, 2024 | My Ph.D. student Ethan Che is on the faculty job market. He works on AI-driven approaches to large-scale operational decision-making. His thesis has taken strides in scalable auto-differentiation-based methods for queueing network control and adaptive experimentation. |
| Jun 10, 2024 | In this significantly updated paper, we use rigorous and extensive empirical analysis to highlight the shortcomings of robust learning algorithms and advocate for new data-driven inductive paradigm for algorithm development. Also check out our NeurIPS 2023 tutorial on distribution shifts and my DRO brown bag overviewing my group’s work in this direction. |
| Dec 15, 2023 | Watch my SNAPP talk on Adaptive Experimentation at Scale. |
| May 15, 2023 | Watch my talk on Robust Causal Inference that I gave at the IFDS workshop on distributional robustness in data science. |