TimeSpace Tradeoffs for Learning Finite Functions from Random Evaluations, with Applications to Polynomials
[edit]
Proceedings of the 31st Conference On Learning Theory, PMLR 75:843856, 2018.
Abstract
We develop an extension of recent analytic methods for obtaining timespace tradeoff lower bounds for problems of learning from uniformly random labelled examples. With our methods we can obtain bounds for learning concept classes of finite functions from random evaluations even when the sample space of random inputs can be significantly smaller than the concept class of functions and the function values can be from an arbitrary finite set. At the core of our results, we reduce the timespace complexity of learning from random evaluations to the question of how much the corresponding evaluation matrix amplifies the 2norms of “almost uniform” probability distributions. To analyze the latter, we formulate it as a semidefinite program, and we analyze its dual. In order to handle function values from arbitrary finite sets, we apply this norm amplification analysis to complex matrices. As applications that follow from our new techniques, we show that any algorithm that learns $n$variate polynomial functions of degree at most $d$ over $\mathbb{F}_2$ with success at least $2^{O(n)}$ from evaluations on randomly chosen inputs either requires space $\Omega(nm/d)$ or $2^{\Omega(n/d)}$ time where $m=(n/d)^{\Theta(d)}$ is the dimension of the space of such polynomials. These bounds are asymptotically optimal for polynomials of arbitrary constant degree since they match the tradeoffs achieved by natural learning algorithms for the problems. We extend these results to learning polynomials of degree at most $d$ over any odd prime field $\mathbb{F}_p$ where we show that $\Omega((mn/d)\log p)$ space or time $p^{\Omega(n/d)}$ is required. To derive our bounds for learning polynomials over finite fields, we show that an analysis of the dual of the corresponding semidefinite program follows from an understanding of the distribution of the bias of all degree $d$ polynomials with respect to uniformly random inputs.
Related Material


