Matches in SemOpenAlex for { <https://semopenalex.org/work/W2912271671> ?p ?o ?g. }
Showing items 1 to 82 of
82
with 100 items per page.
- W2912271671 abstract "Consider the Fisher information for estimating a vector $theta in mathbb {R}^{d}$ from the quantized version of a statistical sample $X sim f(x|theta)$. Let M be a k-bit quantization of $X.$ We provide a geometric characterization of the trace of the Fisher information matrix $I_{M}(theta)$ in terms of the score function $S_{theta }(X)$. When $k=1$, we exactly solve the extremal problem of maximizing this geometric quantity for the Gaussian location model, which allows us to conclude that in this model, a half-space quantization is the one-bit quantization that maximizes $Tr(I_{M}(theta))$. Under assumptions on the tail of the distribution of $S_{theta }(X)$ projected onto any unit vector in $mathbb {R}^{d}$, we give upper bounds demonstrating how $Tr(I_{M}(theta))$ can scale with k. We apply these results to find lower bounds on the minimax risk of estimating $theta $ from multiple quantized samples of X, for example in a distributed setting where the samples are distributed across multiple nodes and each node has a total budget of k-bits to communicate its sample to a centralized estimator. Our bounds apply in a unified way to many common statistical models including the Gaussian location model and discrete distribution estimation, and they recover and generalize existing results in the literature with simpler and more transparent proofs." @default.
- W2912271671 created "2019-02-21" @default.
- W2912271671 creator A5003322209 @default.
- W2912271671 creator A5029028070 @default.
- W2912271671 creator A5077972639 @default.
- W2912271671 date "2018-10-01" @default.
- W2912271671 modified "2023-09-27" @default.
- W2912271671 title "A Geometric Characterization of Fisher Information from Quantized Samples with Applications to Distributed Statistical Estimation" @default.
- W2912271671 cites W1507943102 @default.
- W2912271671 cites W1966650560 @default.
- W2912271671 cites W2042179958 @default.
- W2912271671 cites W2099924374 @default.
- W2912271671 cites W2144785473 @default.
- W2912271671 cites W2158336584 @default.
- W2912271671 cites W2171801319 @default.
- W2912271671 cites W2885907219 @default.
- W2912271671 cites W2963422939 @default.
- W2912271671 cites W3133603318 @default.
- W2912271671 cites W4210551624 @default.
- W2912271671 doi "https://doi.org/10.1109/allerton.2018.8635899" @default.
- W2912271671 hasPublicationYear "2018" @default.
- W2912271671 type Work @default.
- W2912271671 sameAs 2912271671 @default.
- W2912271671 citedByCount "11" @default.
- W2912271671 countsByYear W29122716712019 @default.
- W2912271671 countsByYear W29122716712020 @default.
- W2912271671 countsByYear W29122716712022 @default.
- W2912271671 crossrefType "proceedings-article" @default.
- W2912271671 hasAuthorship W2912271671A5003322209 @default.
- W2912271671 hasAuthorship W2912271671A5029028070 @default.
- W2912271671 hasAuthorship W2912271671A5077972639 @default.
- W2912271671 hasConcept C100279318 @default.
- W2912271671 hasConcept C105795698 @default.
- W2912271671 hasConcept C11413529 @default.
- W2912271671 hasConcept C114614502 @default.
- W2912271671 hasConcept C118615104 @default.
- W2912271671 hasConcept C121332964 @default.
- W2912271671 hasConcept C126255220 @default.
- W2912271671 hasConcept C134306372 @default.
- W2912271671 hasConcept C149728462 @default.
- W2912271671 hasConcept C163716315 @default.
- W2912271671 hasConcept C185429906 @default.
- W2912271671 hasConcept C28826006 @default.
- W2912271671 hasConcept C28855332 @default.
- W2912271671 hasConcept C29406490 @default.
- W2912271671 hasConcept C33923547 @default.
- W2912271671 hasConcept C62520636 @default.
- W2912271671 hasConcept C84316537 @default.
- W2912271671 hasConceptScore W2912271671C100279318 @default.
- W2912271671 hasConceptScore W2912271671C105795698 @default.
- W2912271671 hasConceptScore W2912271671C11413529 @default.
- W2912271671 hasConceptScore W2912271671C114614502 @default.
- W2912271671 hasConceptScore W2912271671C118615104 @default.
- W2912271671 hasConceptScore W2912271671C121332964 @default.
- W2912271671 hasConceptScore W2912271671C126255220 @default.
- W2912271671 hasConceptScore W2912271671C134306372 @default.
- W2912271671 hasConceptScore W2912271671C149728462 @default.
- W2912271671 hasConceptScore W2912271671C163716315 @default.
- W2912271671 hasConceptScore W2912271671C185429906 @default.
- W2912271671 hasConceptScore W2912271671C28826006 @default.
- W2912271671 hasConceptScore W2912271671C28855332 @default.
- W2912271671 hasConceptScore W2912271671C29406490 @default.
- W2912271671 hasConceptScore W2912271671C33923547 @default.
- W2912271671 hasConceptScore W2912271671C62520636 @default.
- W2912271671 hasConceptScore W2912271671C84316537 @default.
- W2912271671 hasLocation W29122716711 @default.
- W2912271671 hasOpenAccess W2912271671 @default.
- W2912271671 hasPrimaryLocation W29122716711 @default.
- W2912271671 hasRelatedWork W1964781732 @default.
- W2912271671 hasRelatedWork W1973573083 @default.
- W2912271671 hasRelatedWork W2049357966 @default.
- W2912271671 hasRelatedWork W2069885834 @default.
- W2912271671 hasRelatedWork W2161506102 @default.
- W2912271671 hasRelatedWork W2550577760 @default.
- W2912271671 hasRelatedWork W2912271671 @default.
- W2912271671 hasRelatedWork W2952094919 @default.
- W2912271671 hasRelatedWork W644150314 @default.
- W2912271671 hasRelatedWork W2186123070 @default.
- W2912271671 isParatext "false" @default.
- W2912271671 isRetracted "false" @default.
- W2912271671 magId "2912271671" @default.
- W2912271671 workType "article" @default.