Equivalences between learning of data and probability distributions, and their applications
Algorithmic learning theory traditionally studies the learnability of effective infinite binary sequences (reals), while recent work by Vitányi and Chater has adapted this framework to the study of learnability of effective probability distributions from random data. We prove that for certain famil...
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Dokumenttyp: | Article (Journal) |
| Sprache: | Englisch |
| Veröffentlicht: |
1 August 2018
|
| In: |
Information and computation
Year: 2018, Jahrgang: 262, Pages: 123-140 |
| ISSN: | 1090-2651 |
| DOI: | 10.1016/j.ic.2018.08.001 |
| Online-Zugang: | Verlag, Volltext: https://doi.org/10.1016/j.ic.2018.08.001 Verlag: http://www.sciencedirect.com/science/article/pii/S0890540118301172 
|
| Verfasserangaben: | George Barmpalias, Nan Fang, Frank Stephan |
MARC
| LEADER | 00000caa a2200000 c 4500 | ||
|---|---|---|---|
| 001 | 1691541389 | ||
| 003 | DE-627 | ||
| 005 | 20220818004926.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 200304s2018 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1016/j.ic.2018.08.001 |2 doi | |
| 035 | |a (DE-627)1691541389 | ||
| 035 | |a (DE-599)KXP1691541389 | ||
| 035 | |a (OCoLC)1341309212 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rda | ||
| 041 | |a eng | ||
| 084 | |a 28 |2 sdnb | ||
| 100 | 1 | |a Barmpalias, George |e VerfasserIn |4 aut | |
| 245 | 1 | 0 | |a Equivalences between learning of data and probability distributions, and their applications |c George Barmpalias, Nan Fang, Frank Stephan |
| 264 | 1 | |c 1 August 2018 | |
| 300 | |a 18 | ||
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a Computermedien |b c |2 rdamedia | ||
| 338 | |a Online-Ressource |b cr |2 rdacarrier | ||
| 500 | |a Gesehen am 04.03.2020 | ||
| 520 | |a Algorithmic learning theory traditionally studies the learnability of effective infinite binary sequences (reals), while recent work by Vitányi and Chater has adapted this framework to the study of learnability of effective probability distributions from random data. We prove that for certain families of probability measures that are parametrized by reals, learnability of a subclass of probability measures is equivalent to learnability of the class of the corresponding real parameters. This equivalence allows to transfer results from classical algorithmic theory to learning theory of probability measures. We present a number of such applications, providing many new results regarding EX and BC learnability of classes of measures, thus drawing parallels between the two learning theories. | ||
| 700 | 1 | |a Fang, Nan |d 1991- |e VerfasserIn |0 (DE-588)1196037493 |0 (DE-627)1677911077 |4 aut | |
| 700 | 1 | |a Stephan, Frank |e VerfasserIn |0 (DE-588)1125914025 |0 (DE-627)880490810 |0 (DE-576)483630047 |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Information and computation |d Amsterdam : Elsevier, 1987 |g 262(2018), Seite 123-140 |h Online-Ressource |w (DE-627)26688170X |w (DE-600)1468010-5 |w (DE-576)10337308X |x 1090-2651 |7 nnas |a Equivalences between learning of data and probability distributions, and their applications |
| 773 | 1 | 8 | |g volume:262 |g year:2018 |g pages:123-140 |g extent:18 |a Equivalences between learning of data and probability distributions, and their applications |
| 856 | 4 | 0 | |u https://doi.org/10.1016/j.ic.2018.08.001 |x Verlag |x Resolving-System |3 Volltext |
| 856 | 4 | 0 | |u http://www.sciencedirect.com/science/article/pii/S0890540118301172 |x Verlag |
| 951 | |a AR | ||
| 992 | |a 20200304 | ||
| 993 | |a Article | ||
| 994 | |a 2018 | ||
| 998 | |g 1196037493 |a Fang, Nan |m 1196037493:Fang, Nan |d 110000 |d 110300 |e 110000PF1196037493 |e 110300PF1196037493 |k 0/110000/ |k 1/110000/110300/ |p 2 | ||
| 999 | |a KXP-PPN1691541389 |e 3603688791 | ||
| BIB | |a Y | ||
| SER | |a journal | ||
| JSO | |a {"person":[{"family":"Barmpalias","given":"George","display":"Barmpalias, George","roleDisplay":"VerfasserIn","role":"aut"},{"family":"Fang","given":"Nan","display":"Fang, Nan","roleDisplay":"VerfasserIn","role":"aut"},{"given":"Frank","family":"Stephan","role":"aut","roleDisplay":"VerfasserIn","display":"Stephan, Frank"}],"title":[{"title":"Equivalences between learning of data and probability distributions, and their applications","title_sort":"Equivalences between learning of data and probability distributions, and their applications"}],"type":{"bibl":"article-journal","media":"Online-Ressource"},"note":["Gesehen am 04.03.2020"],"language":["eng"],"recId":"1691541389","name":{"displayForm":["George Barmpalias, Nan Fang, Frank Stephan"]},"origin":[{"dateIssuedKey":"2018","dateIssuedDisp":"1 August 2018"}],"id":{"doi":["10.1016/j.ic.2018.08.001"],"eki":["1691541389"]},"physDesc":[{"extent":"18 S."}],"relHost":[{"title":[{"title_sort":"Information and computation","title":"Information and computation"}],"note":["Gesehen am 16.07.13"],"disp":"Equivalences between learning of data and probability distributions, and their applicationsInformation and computation","type":{"bibl":"periodical","media":"Online-Ressource"},"recId":"26688170X","language":["eng"],"pubHistory":["72.1987 - 209.2011; Vol. 210.2012 -"],"part":{"volume":"262","text":"262(2018), Seite 123-140","extent":"18","year":"2018","pages":"123-140"},"origin":[{"publisherPlace":"Amsterdam ; Orlando, Fla.","dateIssuedDisp":"1987-","dateIssuedKey":"1987","publisher":"Elsevier ; Academic Press"}],"id":{"issn":["1090-2651"],"zdb":["1468010-5"],"eki":["26688170X"]},"physDesc":[{"extent":"Online-Ressource"}]}]} | ||
| SRT | |a BARMPALIASEQUIVALENC1201 | ||