Beyond Worst Case: When Complex Feedback Can Improve the Label Complexity of Active Learning
364 views · Published 17 November 2016 · 43:12 · Indexed 30 October 2026
Channel: Simons Institute for the Theory of Computing · 2016 · Education
Kamalika Chaudhuri, UC San Diego https://simons.berkeley.edu/talks/kamalika-chaudhuri-2016-11-17 Learning, Algorithm Design and Beyond Worst-Case Analysis
More from this channel
-
35:16
Probabilistic Polynomials and Hamming Nearest Neighbors
-
15:16
Addition is Exponentially Harder than Counting for Shallow Monotone Circuits
-
55:22
Thinking Algorithmically About Impossibility
-
27:28
The Query Complexity of Correlated Equilibria
-
31:37
Robustness and Separation in Multidimensional Mechanism Design
-
33:01
Revenue Maximization in Interdependent Value Settings
-
34:31
Algorithmic Bayesian Mechanism Design
-
37:51
On Maximizing Revenue for Multi-Item Auctions