Online Learning and Resource-Bounded Dimension: Winnow Yields New Lower Bounds for Hard Sets
John M. Hitchcock
Abstract
We establish a relationship between the online mistake-bound model of learning and resource-bounded dimension. This connection is combined with the Winnow algorithm to obtain new results about the density of hard sets under adaptive reductions. This improves previous work of Fu (1995) and Lutz and Zhao (2000), and solves one of Lutz and Mayordomo's "Twelve Problems in Resource-Bounded Measure" (1999).
Create a lesson
Related papers
Pseudodeterminism and MA != NPBPP in Communication Complexity
Thomas Watson
Group Isomorphism and the Polylogarithmic-Time Hierarchy: Depth-212 Circuits and Lower Bounds
Joshua A. Grochow, Gülce Kardeş, Michael Levet
Continuous Computational Social Choice: A Case Study in Bribery
Martin Koutecký, Nikolaos Melissinos, Tung Anh Vu et al.
Pseudorandom Functions in NC1 from LWE/LPN/CDH (Or: How to Build PRFs in NC1, Generically)
Youlong Ding, Aayush Jain, Ilan Komargodski
Parameterized Complexity of Lp-Lipschitz Constants for Input Convex Neural Networks and Lp-Norm Maximization over Zonotopes
Aritra Das, Vincent Froese, Moritz Grillo et al.
Exact CVP Is NP-Complete for Principal Cyclotomic Ideals
Jiaqi Liu, Yansong Feng, Yanbin Pan