FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2890680551> ?p ?o ?g. }

• W2890680551 abstract "Risk scores are simple classification models that let users make quick risk predictions by adding and subtracting a few small numbers. These models are widely used in medicine and criminal justice, but are difficult to learn from data because they need to be calibrated, sparse, use small integer coefficients, and obey application-specific operational constraints. In this paper, we present a new machine learning approach to learn risk scores. We formulate the risk score problem as a mixed integer nonlinear program, and present a cutting plane algorithm for non-convex settings to efficiently recover its optimal solution. We improve our algorithm with specialized techniques to generate feasible solutions, narrow the optimality gap, and reduce data-related computation. Our approach can fit risk scores in a way that scales linearly in the number of samples, provides a certificate of optimality, and obeys real-world constraints without parameter tuning or post-processing. We benchmark the performance benefits of this approach through an extensive set of numerical experiments, comparing to risk scores built using heuristic approaches. We also discuss its practical benefits through a real-world application where we build a customized risk score for ICU seizure prediction in collaboration with the Massachusetts General Hospital." @default.
• W2890680551 created "2018-09-27" @default.
• W2890680551 creator A5040468715 @default.
• W2890680551 creator A5040537492 @default.
• W2890680551 date "2016-10-01" @default.
• W2890680551 modified "2023-09-28" @default.
• W2890680551 title "Learning Optimized Risk Scores" @default.
• W2890680551 cites W134253518 @default.
• W2890680551 cites W137597349 @default.
• W2890680551 cites W1453222892 @default.
• W2890680551 cites W1520704567 @default.
• W2890680551 cites W1554944419 @default.
• W2890680551 cites W1559060276 @default.
• W2890680551 cites W1575933603 @default.
• W2890680551 cites W1581558595 @default.
• W2890680551 cites W1591553815 @default.
• W2890680551 cites W1599263113 @default.
• W2890680551 cites W1618905105 @default.
• W2890680551 cites W16199803 @default.
• W2890680551 cites W1634598793 @default.
• W2890680551 cites W1648555071 @default.
• W2890680551 cites W1768331497 @default.
• W2890680551 cites W180478659 @default.
• W2890680551 cites W1855884329 @default.
• W2890680551 cites W1894775006 @default.
• W2890680551 cites W1918578756 @default.
• W2890680551 cites W1982862187 @default.
• W2890680551 cites W1995396954 @default.
• W2890680551 cites W1996352909 @default.
• W2890680551 cites W1996796871 @default.
• W2890680551 cites W200217736 @default.
• W2890680551 cites W2005688170 @default.
• W2890680551 cites W2011039300 @default.
• W2890680551 cites W2014352947 @default.
• W2890680551 cites W2014374971 @default.
• W2890680551 cites W2015067034 @default.
• W2890680551 cites W2015681706 @default.
• W2890680551 cites W2031248101 @default.
• W2890680551 cites W2035720976 @default.
• W2890680551 cites W2040825624 @default.
• W2890680551 cites W2043464706 @default.
• W2890680551 cites W2049320546 @default.
• W2890680551 cites W2054193584 @default.
• W2890680551 cites W2056418346 @default.
• W2890680551 cites W2060048272 @default.
• W2890680551 cites W2062786076 @default.
• W2890680551 cites W2063978378 @default.
• W2890680551 cites W2069808690 @default.
• W2890680551 cites W2070426678 @default.
• W2890680551 cites W2075779886 @default.
• W2890680551 cites W2082262280 @default.
• W2890680551 cites W2097360283 @default.
• W2890680551 cites W2099917845 @default.
• W2890680551 cites W2100960835 @default.
• W2890680551 cites W2101557761 @default.
• W2890680551 cites W2107103101 @default.
• W2890680551 cites W2107426741 @default.
• W2890680551 cites W2109408917 @default.
• W2890680551 cites W2110317531 @default.
• W2890680551 cites W2112530506 @default.
• W2890680551 cites W2115364117 @default.
• W2890680551 cites W2120596490 @default.
• W2890680551 cites W2122825543 @default.
• W2890680551 cites W2124704085 @default.
• W2890680551 cites W2126247482 @default.
• W2890680551 cites W2126430683 @default.
• W2890680551 cites W2128349740 @default.
• W2890680551 cites W2129018774 @default.
• W2890680551 cites W2130486630 @default.
• W2890680551 cites W2132166479 @default.
• W2890680551 cites W2134829400 @default.
• W2890680551 cites W2147227228 @default.
• W2890680551 cites W2148041662 @default.
• W2890680551 cites W2154776925 @default.
• W2890680551 cites W2155846194 @default.
• W2890680551 cites W2163757302 @default.
• W2890680551 cites W2177693422 @default.
• W2890680551 cites W2218302223 @default.
• W2890680551 cites W2233387570 @default.
• W2890680551 cites W2236721743 @default.
• W2890680551 cites W2248060815 @default.
• W2890680551 cites W2283967055 @default.
• W2890680551 cites W2296319761 @default.
• W2890680551 cites W2315878770 @default.
• W2890680551 cites W2346665266 @default.
• W2890680551 cites W2367397349 @default.
• W2890680551 cites W2396120831 @default.
• W2890680551 cites W2462906003 @default.
• W2890680551 cites W2493343568 @default.
• W2890680551 cites W2563227985 @default.
• W2890680551 cites W2582743722 @default.
• W2890680551 cites W2604231045 @default.
• W2890680551 cites W2735773097 @default.
• W2890680551 cites W2743731382 @default.
• W2890680551 cites W2753645534 @default.
• W2890680551 cites W2762002773 @default.
• W2890680551 cites W2762409054 @default.
• W2890680551 cites W2762658547 @default.
• W2890680551 cites W2801961936 @default.
• W2890680551 cites W2962714378 @default.

• next