Matches in SemOpenAlex for { <https://semopenalex.org/work/W2946981623> ?p ?o ?g. }
- W2946981623 abstract "Entropy integrals are widely used as a powerful tool to obtain upper bounds for the rates of convergence of global empirical risk minimizers (ERMs), in standard settings such as density estimation and regression. The upper bound for the convergence rates thus obtained typically matches the minimax lower bound when the entropy integral converges, but admits a strict gap compared with the lower bound when it diverges. [BM93] provided a striking example showing that such a gap is real with the entropy structure alone: for a variant of the natural Holder class with low regularity, the global ERM actually converges at the rate predicted by the entropy integral that substantially deviates from the lower bound. The counter-example has spawned a long-standing negative position on the use of global ERMs in the regime where the entropy integral diverges, as they are heuristically believed to converge at a sub-optimal rate in a variety of models. The present paper demonstrates that this gap can be closed if the models admit certain degree of `shape constraints' in addition to the entropy structure. In other words, the global ERMs in such `shape-constrained' models will indeed be rate-optimal, matching the lower bound even when the entropy integral diverges. The models with `shape constraints' we investigate include (i) edge estimation with additive and multiplicative errors, (ii) binary classification, (iii) multiple isotonic regression, (iv) $s$-concave density estimation, all in general dimensions when the entropy integral diverges. Here `shape constraints' are interpreted broadly in the sense that the complexity of the underlying models can be essentially captured by the size of the empirical process over certain class of measurable sets, for which matching upper and lower bounds are obtained to facilitate the derivation of sharp convergence rates for the associated global ERMs." @default.
- W2946981623 created "2019-06-07" @default.
- W2946981623 creator A5084054903 @default.
- W2946981623 date "2019-05-30" @default.
- W2946981623 modified "2023-09-26" @default.
- W2946981623 title "Global empirical risk minimizers with shape constraints are rate optimal in general dimensions" @default.
- W2946981623 cites W1495241956 @default.
- W2946981623 cites W1524622012 @default.
- W2946981623 cites W1564947197 @default.
- W2946981623 cites W1872195782 @default.
- W2946981623 cites W1974340805 @default.
- W2946981623 cites W1981292117 @default.
- W2946981623 cites W1981601376 @default.
- W2946981623 cites W1983021114 @default.
- W2946981623 cites W1996268356 @default.
- W2946981623 cites W1996419656 @default.
- W2946981623 cites W1997817606 @default.
- W2946981623 cites W2000475131 @default.
- W2946981623 cites W2004060143 @default.
- W2946981623 cites W2025215390 @default.
- W2946981623 cites W2032369139 @default.
- W2946981623 cites W2034398085 @default.
- W2946981623 cites W2049393399 @default.
- W2946981623 cites W2051387260 @default.
- W2946981623 cites W2054098737 @default.
- W2946981623 cites W2080872718 @default.
- W2946981623 cites W2082764406 @default.
- W2946981623 cites W2083774319 @default.
- W2946981623 cites W2087357084 @default.
- W2946981623 cites W2093030681 @default.
- W2946981623 cites W2115986460 @default.
- W2946981623 cites W2127991572 @default.
- W2946981623 cites W2159058260 @default.
- W2946981623 cites W2799286036 @default.
- W2946981623 cites W2962686593 @default.
- W2946981623 cites W2962732336 @default.
- W2946981623 cites W2963320582 @default.
- W2946981623 cites W2963537613 @default.
- W2946981623 cites W2963676822 @default.
- W2946981623 cites W2964236124 @default.
- W2946981623 cites W2964256917 @default.
- W2946981623 cites W2971051513 @default.
- W2946981623 cites W3102610673 @default.
- W2946981623 cites W3105849782 @default.
- W2946981623 cites W3105994413 @default.
- W2946981623 cites W3127801611 @default.
- W2946981623 hasPublicationYear "2019" @default.
- W2946981623 type Work @default.
- W2946981623 sameAs 2946981623 @default.
- W2946981623 citedByCount "12" @default.
- W2946981623 countsByYear W29469816232018 @default.
- W2946981623 countsByYear W29469816232019 @default.
- W2946981623 countsByYear W29469816232020 @default.
- W2946981623 countsByYear W29469816232021 @default.
- W2946981623 crossrefType "posted-content" @default.
- W2946981623 hasAuthorship W2946981623A5084054903 @default.
- W2946981623 hasConcept C105795698 @default.
- W2946981623 hasConcept C106301342 @default.
- W2946981623 hasConcept C121332964 @default.
- W2946981623 hasConcept C126255220 @default.
- W2946981623 hasConcept C127162648 @default.
- W2946981623 hasConcept C134306372 @default.
- W2946981623 hasConcept C149728462 @default.
- W2946981623 hasConcept C171752962 @default.
- W2946981623 hasConcept C185429906 @default.
- W2946981623 hasConcept C28826006 @default.
- W2946981623 hasConcept C31258907 @default.
- W2946981623 hasConcept C33923547 @default.
- W2946981623 hasConcept C41008148 @default.
- W2946981623 hasConcept C42747912 @default.
- W2946981623 hasConcept C57869625 @default.
- W2946981623 hasConcept C62520636 @default.
- W2946981623 hasConcept C77553402 @default.
- W2946981623 hasConceptScore W2946981623C105795698 @default.
- W2946981623 hasConceptScore W2946981623C106301342 @default.
- W2946981623 hasConceptScore W2946981623C121332964 @default.
- W2946981623 hasConceptScore W2946981623C126255220 @default.
- W2946981623 hasConceptScore W2946981623C127162648 @default.
- W2946981623 hasConceptScore W2946981623C134306372 @default.
- W2946981623 hasConceptScore W2946981623C149728462 @default.
- W2946981623 hasConceptScore W2946981623C171752962 @default.
- W2946981623 hasConceptScore W2946981623C185429906 @default.
- W2946981623 hasConceptScore W2946981623C28826006 @default.
- W2946981623 hasConceptScore W2946981623C31258907 @default.
- W2946981623 hasConceptScore W2946981623C33923547 @default.
- W2946981623 hasConceptScore W2946981623C41008148 @default.
- W2946981623 hasConceptScore W2946981623C42747912 @default.
- W2946981623 hasConceptScore W2946981623C57869625 @default.
- W2946981623 hasConceptScore W2946981623C62520636 @default.
- W2946981623 hasConceptScore W2946981623C77553402 @default.
- W2946981623 hasLocation W29469816231 @default.
- W2946981623 hasOpenAccess W2946981623 @default.
- W2946981623 hasPrimaryLocation W29469816231 @default.
- W2946981623 hasRelatedWork W1669551046 @default.
- W2946981623 hasRelatedWork W2066649525 @default.
- W2946981623 hasRelatedWork W2068269714 @default.
- W2946981623 hasRelatedWork W2072206784 @default.
- W2946981623 hasRelatedWork W2079313454 @default.
- W2946981623 hasRelatedWork W2146433171 @default.
- W2946981623 hasRelatedWork W2254991832 @default.