Matches in SemOpenAlex for { <https://semopenalex.org/work/W4323323013> ?p ?o ?g. }
Showing items 1 to 69 of
69
with 100 items per page.
- W4323323013 abstract "In the online learning with experts problem, an algorithm must make a prediction about an outcome on each of $T$ days (or times), given a set of $n$ experts who make predictions on each day (or time). The algorithm is given feedback on the outcomes of each day, including the cost of its prediction and the cost of the expert predictions, and the goal is to make a prediction with the minimum cost, specifically compared to the best expert in the set. Recent work by Srinivas, Woodruff, Xu, and Zhou (STOC 2022) introduced the study of the online learning with experts problem under memory constraints. However, often the predictions made by experts or algorithms at some time influence future outcomes, so that the input is adaptively chosen. Whereas deterministic algorithms would be robust to adaptive inputs, existing algorithms all crucially use randomization to sample a small number of experts. In this paper, we study deterministic and robust algorithms for the experts problem. We first show a space lower bound of $widetilde{Omega}left(frac{nM}{RT}right)$ for any deterministic algorithm that achieves regret $R$ when the best expert makes $M$ mistakes. Our result shows that the natural deterministic algorithm, which iterates through pools of experts until each expert in the pool has erred, is optimal up to polylogarithmic factors. On the positive side, we give a randomized algorithm that is robust to adaptive inputs that uses $widetilde{O}left(frac{n}{Rsqrt{T}}right)$ space for $M=Oleft(frac{R^2 T}{log^2 n}right)$, thereby showing a smooth space-regret trade-off." @default.
- W4323323013 created "2023-03-07" @default.
- W4323323013 creator A5018283928 @default.
- W4323323013 creator A5024805876 @default.
- W4323323013 creator A5059004637 @default.
- W4323323013 date "2023-03-02" @default.
- W4323323013 modified "2023-10-01" @default.
- W4323323013 title "Streaming Algorithms for Learning with Experts: Deterministic Versus Robust" @default.
- W4323323013 doi "https://doi.org/10.48550/arxiv.2303.01709" @default.
- W4323323013 hasPublicationYear "2023" @default.
- W4323323013 type Work @default.
- W4323323013 citedByCount "0" @default.
- W4323323013 crossrefType "posted-content" @default.
- W4323323013 hasAuthorship W4323323013A5018283928 @default.
- W4323323013 hasAuthorship W4323323013A5024805876 @default.
- W4323323013 hasAuthorship W4323323013A5059004637 @default.
- W4323323013 hasBestOaLocation W43233230131 @default.
- W4323323013 hasConcept C111919701 @default.
- W4323323013 hasConcept C11413529 @default.
- W4323323013 hasConcept C114614502 @default.
- W4323323013 hasConcept C118615104 @default.
- W4323323013 hasConcept C119857082 @default.
- W4323323013 hasConcept C121332964 @default.
- W4323323013 hasConcept C134306372 @default.
- W4323323013 hasConcept C140479938 @default.
- W4323323013 hasConcept C154945302 @default.
- W4323323013 hasConcept C177264268 @default.
- W4323323013 hasConcept C196921405 @default.
- W4323323013 hasConcept C199360897 @default.
- W4323323013 hasConcept C2778572836 @default.
- W4323323013 hasConcept C2779557605 @default.
- W4323323013 hasConcept C33923547 @default.
- W4323323013 hasConcept C41008148 @default.
- W4323323013 hasConcept C50817715 @default.
- W4323323013 hasConcept C62520636 @default.
- W4323323013 hasConceptScore W4323323013C111919701 @default.
- W4323323013 hasConceptScore W4323323013C11413529 @default.
- W4323323013 hasConceptScore W4323323013C114614502 @default.
- W4323323013 hasConceptScore W4323323013C118615104 @default.
- W4323323013 hasConceptScore W4323323013C119857082 @default.
- W4323323013 hasConceptScore W4323323013C121332964 @default.
- W4323323013 hasConceptScore W4323323013C134306372 @default.
- W4323323013 hasConceptScore W4323323013C140479938 @default.
- W4323323013 hasConceptScore W4323323013C154945302 @default.
- W4323323013 hasConceptScore W4323323013C177264268 @default.
- W4323323013 hasConceptScore W4323323013C196921405 @default.
- W4323323013 hasConceptScore W4323323013C199360897 @default.
- W4323323013 hasConceptScore W4323323013C2778572836 @default.
- W4323323013 hasConceptScore W4323323013C2779557605 @default.
- W4323323013 hasConceptScore W4323323013C33923547 @default.
- W4323323013 hasConceptScore W4323323013C41008148 @default.
- W4323323013 hasConceptScore W4323323013C50817715 @default.
- W4323323013 hasConceptScore W4323323013C62520636 @default.
- W4323323013 hasLocation W43233230131 @default.
- W4323323013 hasOpenAccess W4323323013 @default.
- W4323323013 hasPrimaryLocation W43233230131 @default.
- W4323323013 hasRelatedWork W1964399277 @default.
- W4323323013 hasRelatedWork W1973671234 @default.
- W4323323013 hasRelatedWork W1985773538 @default.
- W4323323013 hasRelatedWork W2020792090 @default.
- W4323323013 hasRelatedWork W2024634642 @default.
- W4323323013 hasRelatedWork W2055355518 @default.
- W4323323013 hasRelatedWork W2079220110 @default.
- W4323323013 hasRelatedWork W2165966680 @default.
- W4323323013 hasRelatedWork W2964437461 @default.
- W4323323013 hasRelatedWork W4231250804 @default.
- W4323323013 isParatext "false" @default.
- W4323323013 isRetracted "false" @default.
- W4323323013 workType "article" @default.