Asymptotic Theory of Statistics and Probability

By Anirban Dasgupta. 2008

800 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Statistical and Nonlinear Physics, Statistics and Probability

View Paper: https://www.semanticscholar.org/paper/94d642ba3b0f46109dfe531509a910475fb33366

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Statistical and Nonlinear Physics

In Statistics and Probability

Citations in the corpus

Testing relevant hypotheses in functional time series via self‐normalization (2018, neutral): “1 in DasGupta (2008). 2”
Estimation of the mean of functional time series and a two‐sample problem (2011, methodology): “…〈"i,m,ψl〉: Next, we use the central limit theorem for stationary m-dependent sequences of random vectors (see Lehmann (1999) and the Cramér-Wold theorems in DasGupta (2008), pages 9 and 120) and obtain that ( 1 N1=2 ∑ 1 i N 〈"i,m,ψl〉, 1 l K )T d→NK.0, ΔK/, where NK.0, ΔK/ is a K -dimensional…”
Learning Energy-Based Models in High-Dimensional Spaces with Multiscale Denoising-Score Matching (2019, background): “LSM is also known as the Fisher divergence or the Fisher information distance [21,22], LSM = DFD(pσ0||pm), where pm(x) = e−E(x)/Z is the normalized distribution from the model energy function.”
Change‐point detection in panel data (2012, methodology): “Applying the Cramér-Wold rule (cf. DasGupta, 2008, p. 9), we obtain the convergence of the finite dimensional distributions to a normal law.”
Multivariate Outlier Detection With High-Breakdown Estimators (2010, result): “This conclusion is remarkably different from that obtained when considering y(j) and the sample mean ȳ = ∑i yi/n (see, e.g., DasGupta 2008, p. 95).”
Double/debiased machine learning for treatment and structural parameters (2017, positive): “We use the term “cross-fitting” to characterize our recommended procedure, partly borrowing the jargon from Fan et al. (2012) which employed a slightly different form of sample-splitting to estimate the scale parameter in a high-dimensional sparse regression.”
Finite Sample Differentially Private Confidence Intervals (2017, positive): “ 6.1 when Pθ0 and Pθ1 are two normal distributions with θ0 = (µ0,σ2) and θ1 = (µ1,σ2). Since the total variation distance between N(µ0,σ2) and N(µ1,σ2) is upper bounded by |µ0 −µ1|/σ (see for example DasGupta (2008)), we get the following Corollary: Corollary 1. Let Pθ0 and Pθ1 be two normal distrib”
On the inductive bias of dropout (2014, background): “1 of DasGupta [2008]) relates binomial distributions to the normal distribution using these moments, and directly implies that”
Evaluating Public Programs with Close Substitutes: The Case of Head Start (2016, background): “As K → ∞ this distribution can approximate any marginal distribution of potential outcomes (see Theorem 33.2 of DasGupta, 2008) .”