Matches in SemOpenAlex for { <https://semopenalex.org/work/W2964339905> ?p ?o ?g. }
Showing items 1 to 64 of
64
with 100 items per page.
- W2964339905 abstract "We consider the problem of learning a target probability distribution over a set of N binary variables from the knowledge of the expectation values (with this target distribution) of M observables, drawn uniformly at random. The space of all probability distributions compatible with these M expectation values within some fixed accuracy, called version space, is studied. We introduce a biased measure over the version space, which gives a boost increasing exponentially with the entropy of the distributions and with an arbitrary inverse ‘temperature’ $$Gamma $$ . The choice of $$Gamma $$ allows us to interpolate smoothly between the unbiased measure over all distributions in the version space ( $$Gamma =0$$ ) and the pointwise measure concentrated at the maximum entropy distribution ( $$Gamma rightarrow infty $$ ). Using the replica method we compute the volume of the version space and other quantities of interest, such as the distance R between the target distribution and the center-of-mass distribution over the version space, as functions of $$alpha =(log M)/N$$ and $$Gamma $$ for large N. Phase transitions at critical values of $$alpha $$ are found, corresponding to qualitative improvements in the learning of the target distribution and to the decrease of the distance R. However, for fixed $$alpha $$ , the distance R does not vary with $$Gamma $$ , which means that the maximum entropy distribution is not closer to the target distribution than any other distribution compatible with the observable values. Our results are confirmed by Monte Carlo sampling of the version space for small system sizes ( $$Nle 10$$ )." @default.
- W2964339905 created "2019-07-30" @default.
- W2964339905 creator A5002693245 @default.
- W2964339905 creator A5016002177 @default.
- W2964339905 creator A5032310325 @default.
- W2964339905 date "2016-03-15" @default.
- W2964339905 modified "2023-09-23" @default.
- W2964339905 title "Learning probabilities from random observables in high dimensions: the maximum entropy distribution and others" @default.
- W2964339905 hasPublicationYear "2016" @default.
- W2964339905 type Work @default.
- W2964339905 sameAs 2964339905 @default.
- W2964339905 citedByCount "0" @default.
- W2964339905 crossrefType "journal-article" @default.
- W2964339905 hasAuthorship W2964339905A5002693245 @default.
- W2964339905 hasAuthorship W2964339905A5016002177 @default.
- W2964339905 hasAuthorship W2964339905A5032310325 @default.
- W2964339905 hasConcept C105795698 @default.
- W2964339905 hasConcept C106301342 @default.
- W2964339905 hasConcept C110121322 @default.
- W2964339905 hasConcept C121332964 @default.
- W2964339905 hasConcept C121864883 @default.
- W2964339905 hasConcept C134306372 @default.
- W2964339905 hasConcept C32848918 @default.
- W2964339905 hasConcept C33923547 @default.
- W2964339905 hasConcept C62520636 @default.
- W2964339905 hasConcept C9679016 @default.
- W2964339905 hasConceptScore W2964339905C105795698 @default.
- W2964339905 hasConceptScore W2964339905C106301342 @default.
- W2964339905 hasConceptScore W2964339905C110121322 @default.
- W2964339905 hasConceptScore W2964339905C121332964 @default.
- W2964339905 hasConceptScore W2964339905C121864883 @default.
- W2964339905 hasConceptScore W2964339905C134306372 @default.
- W2964339905 hasConceptScore W2964339905C32848918 @default.
- W2964339905 hasConceptScore W2964339905C33923547 @default.
- W2964339905 hasConceptScore W2964339905C62520636 @default.
- W2964339905 hasConceptScore W2964339905C9679016 @default.
- W2964339905 hasLocation W29643399051 @default.
- W2964339905 hasOpenAccess W2964339905 @default.
- W2964339905 hasPrimaryLocation W29643399051 @default.
- W2964339905 hasRelatedWork W106806933 @default.
- W2964339905 hasRelatedWork W1591826202 @default.
- W2964339905 hasRelatedWork W1600938032 @default.
- W2964339905 hasRelatedWork W1671637897 @default.
- W2964339905 hasRelatedWork W1750591676 @default.
- W2964339905 hasRelatedWork W1977446320 @default.
- W2964339905 hasRelatedWork W2034226112 @default.
- W2964339905 hasRelatedWork W2054270169 @default.
- W2964339905 hasRelatedWork W2079698760 @default.
- W2964339905 hasRelatedWork W2084512915 @default.
- W2964339905 hasRelatedWork W2136222558 @default.
- W2964339905 hasRelatedWork W2143237234 @default.
- W2964339905 hasRelatedWork W2253142379 @default.
- W2964339905 hasRelatedWork W2611613734 @default.
- W2964339905 hasRelatedWork W3098829777 @default.
- W2964339905 hasRelatedWork W3103131901 @default.
- W2964339905 hasRelatedWork W3123440128 @default.
- W2964339905 hasRelatedWork W3125257878 @default.
- W2964339905 hasRelatedWork W3128496304 @default.
- W2964339905 hasRelatedWork W3207464738 @default.
- W2964339905 hasVolume "2016" @default.
- W2964339905 isParatext "false" @default.
- W2964339905 isRetracted "false" @default.
- W2964339905 magId "2964339905" @default.
- W2964339905 workType "article" @default.