Robust Inference and Local Algorithms
summary
Discusses robust inference and local algorithms in the contexts of information theory, learning, and big data, focusing on methods for making reliable inferences under uncertainty and using algorithms that operate locally (e.g., on parts of large datasets or networks). Covers theoretical approaches to robustness and locality, likely including algorithmic techniques relevant to large-scale learning and inference problems.
AI-written summary · about
chapters (12)
- 0:00Start
- 0:25Overview
- 0:51Robust Probabilistic Inference
- 2:46Robust Spam Detection
- 4:32Robust Network Failure Detection
- 12:44Our Main Result
- 15:34Where does it make a difference?
- 18:07Modeling the setting
- 19:16Optimal policies
- 20:35Local computation algorithms
- 21:57From matching to Vertex Cover
- 22:34Conclusion
related talks
28mPrivacy versus Robustness in Federated Learning: Limits and Algorithms
34mDistributional Robustness, Learning, and Empirical Likelihood
43mRobustness in High-Dimensional Inference Tasks
01h 01mRobustness, Stochastics, Uncertainty 1
37mEfficient Algorithms for Reliable Machine Learning
19mAdversities in Abstract Interpretation - Accommodating Robustness by Abstract(…)
53mRobust Algorithms for Machine Learning
12mDistribution-Free Robustness