Panel Discussion

on YouTube ↗22m

" summary

Defines robustness as controlling average error over an L2 ball of potential outcomes and provides a design that guarantees an unbiased Horvitz-Thompson estimator unbiased with marginals bounded away from 0 and 1, gives finite-sample sub-Gaussian tail bounds for confidence intervals (noting they are often conservative versus CLT-based intervals), shows intervening on a constant fraction of nodes yields logarithmically many interventions while sparser schemes need a hitting-set structure, and outlines a kernel ridge regression extension to handle nonlinear function classes.

AI-written summary · about

" chapters (10)

1. 0:00Robustness
2. 1:47Soft Interventions
3. 3:33Inferential Characteristics
4. 9:07Selfbalancing
5. 11:05Observational Study
6. 13:07Questions
7. 13:59Potential Outcomes
8. 15:33Invariance
9. 16:37Contextspecific independence
10. 19:32Learning the graph

" related talks

• 01h 15mAn overview of classical robust statistics and generalizations to the futurePo-Ling Loh · Modern Paradigms in Generalization Boot Camp 2024
• 13mAlgorithmic Advances For The Design And Analysis Of Randomized Control TrialsChristopher Harshaw · Meet the Fellows Welcome Event
• 34mDistributional Robustness, Learning, and Empirical LikelihoodJohn Duchi · Optimization, Statistics and Uncertainty
• 43mRobustness in High-Dimensional Inference TasksJelena Bradic · Robust and High-Dimensional Statistics (Simons Institute workshop, 2018)
• 53mDesigning Robust LearnersJacob Steinhardt · Emerging Challenges in Deep Learning (Simons Institute workshop, 2019)
• 01h 01mRobustness, Stochastics, Uncertainty 1Sasha Rakhlin, Ben Recht, Laurent El Ghaoui · Bridging Continuous and Discrete Optimization Boot Camp 2017
• 01h 01mRobustness, Stochastics, Uncertainty 2Sasha Rakhlin, Ben Recht, Laurent El Ghaoui · Bridging Continuous and Discrete Optimization Boot Camp 2017
• 12mDistribution-Free RobustnessSitan Chen · Meet the Fellows Welcome Event