Comparative Learning: A Sample Complexity Theory for Two Hypothesis Classes

Channel:
United States Simons Institute for the Theory of Computing
Subscribers:
68,700
Published on ● Video Link: https://www.youtube.com/watch?v=dEb4eYFjkvY


Duration: 23:22
254 views
7

Authors: Lunjia Hu, Charlotte Peale (Stanford University)
ITCS - Innovations in Theoretical Computer Science



Other Videos By Simons Institute for the Theory of Computing


2023-01-04Clustering Permutations: New Techniques with Streaming Applications
2023-01-04Certificate games
2023-01-04Budget Pacing in Repeated Auctions: Regret and Efficiency without Convergence
2023-01-04Is This Correct? Let's Check!
2023-01-04New Lower Bounds and Derandomization for ACC, and a...
2023-01-04On Identity Testing and Noncommutative Rank Computation over the Free Skew Field
2023-01-04The Complexity of Infinite-Horizon General-Sum Stochastic Games
2023-01-04Online Pen Testing
2023-01-04What Can Cryptography Do For Decentralized Mechanism Design?
2023-01-04Consensus Division in an Arbitrary Ratio
2023-01-04Comparative Learning: A Sample Complexity Theory for Two Hypothesis Classes
2023-01-04List Agreement Expansion from Coboundary Expansion
2023-01-04Quantum Proofs of Deletion for Learning with Errors
2023-01-04Differentially Private Continual Releases of Streaming Frequency Moment Estimations
2023-01-04Counting Subgraphs in Somewhere Dense Graphs
2023-01-04Is Untrusted Randomness Helpful?
2023-01-04Improved Inapproximability of VC Dimension and Littlestone's Dimension via (Unbalanced) Biclique
2023-01-04Making Auctions Robust to Aftermarkets
2023-01-04Asynchronous Multi-Party Quantum Computation
2023-01-04Decision Making under Miscalibration - 8 minute
2023-01-04Decision Making under Miscalibration


Tags:
Simons Institute
theoretical computer science
UC Berkeley
Computer Science
Theory of Computation
Theory of Computing
ITCS - Innovations in Theoretical Computer Science