Matches in SemOpenAlex for { <https://semopenalex.org/work/W3208496729> ?p ?o ?g. }
- W3208496729 abstract "We investigate the calibration of estimations to increase performance with an optimal monotone transform on the estimator outputs. We start by studying the traditional square error setting with its weighted variant and show that the optimal monotone transform is in the form of a unique staircase function. We further show that this staircase behavior is preserved for general strictly convex loss functions. Their optimal monotone transforms are also unique, i.e., there exist a single staircase transform that achieves the minimum loss. We propose a linear time and space algorithm that can find such optimal transforms for specific loss settings. Our algorithm has an online implementation where the optimal transform for the samples observed so far are found in linear space and amortized time when the samples arrive in an ordered fashion. We also extend our results to cases where the functions are not trivial to individually optimize and propose an anytime algorithm, which has linear space and pseudo-linearithmic time complexity." @default.
- W3208496729 created "2021-11-08" @default.
- W3208496729 creator A5016493309 @default.
- W3208496729 creator A5046978392 @default.
- W3208496729 date "2021-10-31" @default.
- W3208496729 modified "2023-09-27" @default.
- W3208496729 title "Efficient, Anytime Algorithms for Calibration with Isotonic Regression under Strictly Convex Losses." @default.
- W3208496729 cites W1517796226 @default.
- W3208496729 cites W1527842677 @default.
- W3208496729 cites W1542959211 @default.
- W3208496729 cites W1570963478 @default.
- W3208496729 cites W1579410832 @default.
- W3208496729 cites W1598033630 @default.
- W3208496729 cites W1618905105 @default.
- W3208496729 cites W1965085799 @default.
- W3208496729 cites W1965755064 @default.
- W3208496729 cites W1974191159 @default.
- W3208496729 cites W1977245551 @default.
- W3208496729 cites W2012942264 @default.
- W3208496729 cites W2016511206 @default.
- W3208496729 cites W2030947209 @default.
- W3208496729 cites W2049934117 @default.
- W3208496729 cites W2081887000 @default.
- W3208496729 cites W2098824882 @default.
- W3208496729 cites W2099830893 @default.
- W3208496729 cites W2100512350 @default.
- W3208496729 cites W2102179694 @default.
- W3208496729 cites W2107103101 @default.
- W3208496729 cites W2109912732 @default.
- W3208496729 cites W2122410182 @default.
- W3208496729 cites W2129160848 @default.
- W3208496729 cites W2137556846 @default.
- W3208496729 cites W2148825261 @default.
- W3208496729 cites W2149988068 @default.
- W3208496729 cites W2158316397 @default.
- W3208496729 cites W2163599171 @default.
- W3208496729 cites W2169015875 @default.
- W3208496729 cites W2170112109 @default.
- W3208496729 cites W2254249950 @default.
- W3208496729 cites W2398242707 @default.
- W3208496729 cites W2518477451 @default.
- W3208496729 cites W2548748044 @default.
- W3208496729 cites W2754755697 @default.
- W3208496729 cites W2777614967 @default.
- W3208496729 cites W2782628287 @default.
- W3208496729 cites W2793854160 @default.
- W3208496729 cites W2795929191 @default.
- W3208496729 cites W28749054 @default.
- W3208496729 cites W2895711908 @default.
- W3208496729 cites W2962710061 @default.
- W3208496729 cites W2963029447 @default.
- W3208496729 cites W3090982856 @default.
- W3208496729 cites W3194382524 @default.
- W3208496729 hasPublicationYear "2021" @default.
- W3208496729 type Work @default.
- W3208496729 sameAs 3208496729 @default.
- W3208496729 citedByCount "0" @default.
- W3208496729 crossrefType "posted-content" @default.
- W3208496729 hasAuthorship W3208496729A5016493309 @default.
- W3208496729 hasAuthorship W3208496729A5046978392 @default.
- W3208496729 hasConcept C105795698 @default.
- W3208496729 hasConcept C111110010 @default.
- W3208496729 hasConcept C111919701 @default.
- W3208496729 hasConcept C112680207 @default.
- W3208496729 hasConcept C11413529 @default.
- W3208496729 hasConcept C126255220 @default.
- W3208496729 hasConcept C134306372 @default.
- W3208496729 hasConcept C139945424 @default.
- W3208496729 hasConcept C14036430 @default.
- W3208496729 hasConcept C145446738 @default.
- W3208496729 hasConcept C157972887 @default.
- W3208496729 hasConcept C17418463 @default.
- W3208496729 hasConcept C185429906 @default.
- W3208496729 hasConcept C2524010 @default.
- W3208496729 hasConcept C2778572836 @default.
- W3208496729 hasConcept C2834757 @default.
- W3208496729 hasConcept C33923547 @default.
- W3208496729 hasConcept C41008148 @default.
- W3208496729 hasConcept C72169020 @default.
- W3208496729 hasConcept C78458016 @default.
- W3208496729 hasConcept C86803240 @default.
- W3208496729 hasConceptScore W3208496729C105795698 @default.
- W3208496729 hasConceptScore W3208496729C111110010 @default.
- W3208496729 hasConceptScore W3208496729C111919701 @default.
- W3208496729 hasConceptScore W3208496729C112680207 @default.
- W3208496729 hasConceptScore W3208496729C11413529 @default.
- W3208496729 hasConceptScore W3208496729C126255220 @default.
- W3208496729 hasConceptScore W3208496729C134306372 @default.
- W3208496729 hasConceptScore W3208496729C139945424 @default.
- W3208496729 hasConceptScore W3208496729C14036430 @default.
- W3208496729 hasConceptScore W3208496729C145446738 @default.
- W3208496729 hasConceptScore W3208496729C157972887 @default.
- W3208496729 hasConceptScore W3208496729C17418463 @default.
- W3208496729 hasConceptScore W3208496729C185429906 @default.
- W3208496729 hasConceptScore W3208496729C2524010 @default.
- W3208496729 hasConceptScore W3208496729C2778572836 @default.
- W3208496729 hasConceptScore W3208496729C2834757 @default.
- W3208496729 hasConceptScore W3208496729C33923547 @default.
- W3208496729 hasConceptScore W3208496729C41008148 @default.
- W3208496729 hasConceptScore W3208496729C72169020 @default.