On the rationale of maximum-entropy methods

By E. Jaynes. 1982

How researchers see this paper

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

Citations in the corpus

Privacy in Pharmacogenetics: An End-to-End Case Study of Personalized Warfarin Dosing (2014, positive): “To characterize the unbiased prior that satisfies these constraints, we apply the prinicipal of maximum entropy2 [22], which in our setting gives the prior:”
More than Mean Effects: Modeling the Effect of Climate on the Higher Order Moments of Crop Yields (2012, unknown): “Additional descriptions of the method of maximum entropy can be found in Jaynes (1982); Zellner and Highfield (1988); Golan, Judge, and Miller (1996), Mittelhammer, Judge, and Miller (2000), Ormoneit and White (1999), and Tagliani (1993).”
A Theory of Usable Information Under Computational Constraints (2020, background): “Under mild conditions (Wainwright et al., 2008) − A ∗ ( µ ) = H ( P µ ) where P µ is the maximum entropy distribution out of all distributions satisfying E y ∼ P µ [ t ( y )] = µ (Jaynes, 1982), and H ( · ) is the Shannon entropy.”
Bayesian Maximum Entropy prediction of soil categories using a traditional soil map as soft information (2008, background): “For an enlightening discussion about the rationale of the maximum entropy principle, see Jaynes (1982).”
Comparison of Iterative Deconvolution Algorithms for the Mapping of Acoustic Sources (2007, methodology): “These are classical approaches like the CLEAN algorithm introduced by Högbom [7] and Schwarz [8], themaximum entropymethod (MEM) [9], the nonnegative least-squares (NNLS) approach of Lawson and Hanson [10], or maximum likelihood algorithms like the Richardson–Lucy method [11,12].”
Speech Recognition Using Augmented Conditional Random Fields (2009, methodology): “The state characterizing function for each frame was given in (3); is binary valued and can be used to specify the transition topology.”
AdaRNN: Adaptive Learning and Forecasting of Time Series (2021, background): “1 Temporal distribution characterization Based on the principle of maximum entropy [17], maximizing the utilization of shared knowledge underlying a times series under temporal covariate shift can be done by finding periods which are most dissimilar to each other, which is also considered as the wor”
Markov Random Field Modeling in Image Analysis (2001, background): “The maximum entropy criterion is simply taking this fact into account: Configurations with higher entropy are more likely because nature can generate them in more ways (Jaynes 1982).”
Modelling and predicting fungal distribution patterns using herbarium data (2008, background): “Based on the maximum-entropy principle (Jaynes, 1982), Maxent finds the probability distribution/ habitat suitability for the species that maximizes entropy (is closest to the uniform distribution), given the following constraints in the data set: the expected value (true mean values) for the specie”
The Prior Can Often Only Be Understood in the Context of the Likelihood (2017, background): “Examples of structural information include exchangeability in hierarchical models and maximum entropy models in physics, which [3] and others have applied to more general statistical settings.”
Moment Closure—A Brief Review (2015, background): “From a statistical physics perspective, it may be more natural to view (40) as an entropy maximization problem [70] by introducing another minus sign.”
Entropy theory for derivation of infiltration equations (2010, background): “Jaynes [1958, 1982] says that the least biased probability distribution of I, f(I), will be the one that will maximize H(I) given by equation (1b), subject to the given information on I expressed as constraints.”
Entropy Densities: With an Application to Autoregressive Conditional Skewness and Kurtosis (2002, methodology): “Method s basedon the entropy principle of Shannon (1948), andpopularizedby Jaynes (1957, 1982) , have mad e their way into econometrics, e.g.”