Conspiracies between Learning Algorithms, Circuit Lower Bounds and Pseudorandomness
Computational Complexity
2016-11-07 v1 Cryptography and Security
Data Structures and Algorithms
Machine Learning
Abstract
We prove several results giving new and stronger connections between learning, circuit lower bounds and pseudorandomness. Among other results, we show a generic learning speedup lemma, equivalences between various learning models in the exponential time and subexponential time regimes, a dichotomy between learning and pseudorandomness, consequences of non-trivial learning for circuit lower bounds, Karp-Lipton theorems for probabilistic exponential time, and NC-hardness for the Minimum Circuit Size Problem.
Cite
@article{arxiv.1611.01190,
title = {Conspiracies between Learning Algorithms, Circuit Lower Bounds and Pseudorandomness},
author = {Igor C. Oliveira and Rahul Santhanam},
journal= {arXiv preprint arXiv:1611.01190},
year = {2016}
}