Extractor-Based Time-Space Lower Bounds for Learning

A matrix corresponds to the following learning problem: An unknown element is chosen uniformly at random. A learner tries to learn from a stream of samples, , where for every , is chosen uniformly at random and . Assume that are such that any submatrix of of at least rows and at least columns, has a bias of at most . We show that any learning algorithm for the learning problem corresponding to requires either a memory of size at least , or at least samples. The result holds even if the learner has an exponentially small success probability (of ). In particular, this shows that for a large class of learning problems, any learning algorithm requires either a memory of size at least or an exponential number of samples, achieving a tight lower bound on the size of the memory, rather than a bound of obtained in previous works [R17,MM17b]. Moreover, our result implies all previous memory-samples lower bounds, as well as a number of new applications. Our proof builds on [R17] that gave a general technique for proving memory-samples lower bounds.
View on arXiv