Matches in SemOpenAlex for { <https://semopenalex.org/work/W2809144492> ?p ?o ?g. }
Showing items 1 to 87 of
87
with 100 items per page.
- W2809144492 startingPage "121" @default.
- W2809144492 abstract "A matrix M: A × X → {−1,1} corresponds to the following learning problem: An unknown element x ∈ X is chosen uniformly at random. A learner tries to learn x from a stream of samples, (a1, b1), (a2, b2) …, where for every i, ai ∈ A is chosen uniformly at random and bi = M(ai,x). Assume that k, l, r are such that any submatrix of M of at least 2−k · |A| rows and at least 2−l · |X| columns, has a bias of at most 2−r. We show that any learning algorithm for the learning problem corresponding to M requires either a memory of size at least Ω(k · l ), or at least 2Ω(r) samples. The result holds even if the learner has an exponentially small success probability (of 2−Ω(r)). In particular, this shows that for a large class of learning problems, any learning algorithm requires either a memory of size at least Ω((log|X|) · (log|A|)) or an exponential number of samples, achieving a tight Ω((log|X|) · (log|A|)) lower bound on the size of the memory, rather than a bound of Ω(min{(log|X|)2,(log|A|)2}) obtained in previous works by Raz [FOCS’17] and Moshkovitz and Moshkovitz [ITCS’18]. Moreover, our result implies all previous memory-samples lower bounds, as well as a number of new applications. Our proof builds on the work of Raz [FOCS’17] that gave a general technique for proving memory samples lower bounds." @default.
- W2809144492 created "2018-06-29" @default.
- W2809144492 creator A5041545934 @default.
- W2809144492 creator A5049425955 @default.
- W2809144492 creator A5051447099 @default.
- W2809144492 date "2017-01-01" @default.
- W2809144492 modified "2023-09-22" @default.
- W2809144492 title "Extractor-Based Time-Space Lower Bounds for Learning." @default.
- W2809144492 hasPublicationYear "2017" @default.
- W2809144492 type Work @default.
- W2809144492 sameAs 2809144492 @default.
- W2809144492 citedByCount "0" @default.
- W2809144492 crossrefType "journal-article" @default.
- W2809144492 hasAuthorship W2809144492A5041545934 @default.
- W2809144492 hasAuthorship W2809144492A5049425955 @default.
- W2809144492 hasAuthorship W2809144492A5051447099 @default.
- W2809144492 hasConcept C106487976 @default.
- W2809144492 hasConcept C111919701 @default.
- W2809144492 hasConcept C11413529 @default.
- W2809144492 hasConcept C114614502 @default.
- W2809144492 hasConcept C117978034 @default.
- W2809144492 hasConcept C118615104 @default.
- W2809144492 hasConcept C127413603 @default.
- W2809144492 hasConcept C134306372 @default.
- W2809144492 hasConcept C135598885 @default.
- W2809144492 hasConcept C154945302 @default.
- W2809144492 hasConcept C159985019 @default.
- W2809144492 hasConcept C192562407 @default.
- W2809144492 hasConcept C203313322 @default.
- W2809144492 hasConcept C21880701 @default.
- W2809144492 hasConcept C2777212361 @default.
- W2809144492 hasConcept C2778572836 @default.
- W2809144492 hasConcept C33923547 @default.
- W2809144492 hasConcept C41008148 @default.
- W2809144492 hasConcept C63553672 @default.
- W2809144492 hasConcept C77088390 @default.
- W2809144492 hasConcept C77553402 @default.
- W2809144492 hasConceptScore W2809144492C106487976 @default.
- W2809144492 hasConceptScore W2809144492C111919701 @default.
- W2809144492 hasConceptScore W2809144492C11413529 @default.
- W2809144492 hasConceptScore W2809144492C114614502 @default.
- W2809144492 hasConceptScore W2809144492C117978034 @default.
- W2809144492 hasConceptScore W2809144492C118615104 @default.
- W2809144492 hasConceptScore W2809144492C127413603 @default.
- W2809144492 hasConceptScore W2809144492C134306372 @default.
- W2809144492 hasConceptScore W2809144492C135598885 @default.
- W2809144492 hasConceptScore W2809144492C154945302 @default.
- W2809144492 hasConceptScore W2809144492C159985019 @default.
- W2809144492 hasConceptScore W2809144492C192562407 @default.
- W2809144492 hasConceptScore W2809144492C203313322 @default.
- W2809144492 hasConceptScore W2809144492C21880701 @default.
- W2809144492 hasConceptScore W2809144492C2777212361 @default.
- W2809144492 hasConceptScore W2809144492C2778572836 @default.
- W2809144492 hasConceptScore W2809144492C33923547 @default.
- W2809144492 hasConceptScore W2809144492C41008148 @default.
- W2809144492 hasConceptScore W2809144492C63553672 @default.
- W2809144492 hasConceptScore W2809144492C77088390 @default.
- W2809144492 hasConceptScore W2809144492C77553402 @default.
- W2809144492 hasLocation W28091444921 @default.
- W2809144492 hasOpenAccess W2809144492 @default.
- W2809144492 hasPrimaryLocation W28091444921 @default.
- W2809144492 hasRelatedWork W1975124543 @default.
- W2809144492 hasRelatedWork W1975173196 @default.
- W2809144492 hasRelatedWork W2003983974 @default.
- W2809144492 hasRelatedWork W2029029634 @default.
- W2809144492 hasRelatedWork W2049661027 @default.
- W2809144492 hasRelatedWork W2145921860 @default.
- W2809144492 hasRelatedWork W2162446681 @default.
- W2809144492 hasRelatedWork W2236877502 @default.
- W2809144492 hasRelatedWork W2272045681 @default.
- W2809144492 hasRelatedWork W2806847441 @default.
- W2809144492 hasRelatedWork W2945408305 @default.
- W2809144492 hasRelatedWork W2949204716 @default.
- W2809144492 hasRelatedWork W2953237671 @default.
- W2809144492 hasRelatedWork W2956244693 @default.
- W2809144492 hasRelatedWork W2963316509 @default.
- W2809144492 hasRelatedWork W2964156975 @default.
- W2809144492 hasRelatedWork W3006072605 @default.
- W2809144492 hasRelatedWork W3021153856 @default.
- W2809144492 hasRelatedWork W3116741339 @default.
- W2809144492 hasRelatedWork W3184421319 @default.
- W2809144492 hasVolume "24" @default.
- W2809144492 isParatext "false" @default.
- W2809144492 isRetracted "false" @default.
- W2809144492 magId "2809144492" @default.
- W2809144492 workType "article" @default.