Local limit theorems and strong approximations for Robbins-Monro procedures

The Robbins-Monro algorithm is a recursive, simulation-based stochastic procedure to approximate the zeros of a function that can be written as an expectation. It is known that under some technical assumptions, Gaussian limit theorems approximate the stochastic performance of the algorithm. Here, we...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Konakov, Valentin (VerfasserIn) , Mammen, Enno (VerfasserIn) , Huang, Lorick (VerfasserIn)
Dokumenttyp: Article (Journal)
Sprache:Englisch
Veröffentlicht: [01 Oct 2025]
In: Statistics
Year: 2025, Pages: 1-37
ISSN:1029-4910
DOI:10.1080/02331888.2025.2562301
Online-Zugang:Verlag, lizenzpflichtig, Volltext: https://doi.org/10.1080/02331888.2025.2562301
Volltext
Verfasserangaben:Valentin Konakov, Enno Mammen & Lorick Huang

MARC

LEADER 00000naa a22000002c 4500
001 195071067X
003 DE-627
005 20260130141749.0
007 cr uuu---uuuuu
008 260130s2025 xx |||||o 00| ||eng c
024 7 |a 10.1080/02331888.2025.2562301  |2 doi 
035 |a (DE-627)195071067X 
035 |a (DE-599)KXP195071067X 
040 |a DE-627  |b ger  |c DE-627  |e rda 
041 |a eng 
084 |a 27  |2 sdnb 
100 1 |a Konakov, Valentin  |e VerfasserIn  |0 (DE-588)1104703734  |0 (DE-627)86199339X  |0 (DE-576)471269190  |4 aut 
245 1 0 |a Local limit theorems and strong approximations for Robbins-Monro procedures  |c Valentin Konakov, Enno Mammen & Lorick Huang 
264 1 |c [01 Oct 2025] 
300 |a 37 
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 30.01.2026 
520 |a The Robbins-Monro algorithm is a recursive, simulation-based stochastic procedure to approximate the zeros of a function that can be written as an expectation. It is known that under some technical assumptions, Gaussian limit theorems approximate the stochastic performance of the algorithm. Here, we are interested in strong approximations for Robbins-Monro procedures. The main tool for getting them are local limit theorems, that is, studying the convergence of the density of the algorithm. The analysis relies on a version of parametrix techniques for Markov chains converging to diffusions. The main difficulty that arises here is the fact that the drift is unbounded. 
650 4 |a 62-08 
650 4 |a 65C20 
650 4 |a 68W20 
650 4 |a Robbins-Monro algorithm 
650 4 |a stochastic approximation 
700 1 |a Mammen, Enno  |d 1955-  |e VerfasserIn  |0 (DE-588)170668606  |0 (DE-627)060788658  |0 (DE-576)13153159X  |4 aut 
700 1 |a Huang, Lorick  |e VerfasserIn  |4 aut 
773 0 8 |i Enthalten in  |t Statistics  |d London [u.a.] : Taylor & Francis, 1985  |g (2025), Seite 1-37  |h Online-Ressource  |w (DE-627)325350310  |w (DE-600)2035635-3  |w (DE-576)099426684  |x 1029-4910  |7 nnas  |a Local limit theorems and strong approximations for Robbins-Monro procedures 
773 1 8 |g year:2025  |g pages:1-37  |g extent:37  |a Local limit theorems and strong approximations for Robbins-Monro procedures 
856 4 0 |u https://doi.org/10.1080/02331888.2025.2562301  |x Verlag  |x Resolving-System  |z lizenzpflichtig  |3 Volltext  |7 1 
951 |a AR 
992 |a 20260130 
993 |a Article 
994 |a 2025 
998 |g 170668606  |a Mammen, Enno  |m 170668606:Mammen, Enno  |d 110000  |d 110000  |d 110400  |e 110000PM170668606  |e 110000PM170668606  |e 110400PM170668606  |k 0/110000/  |k 0/110000/  |k 1/110000/110400/  |p 2 
999 |a KXP-PPN195071067X  |e 4866390387 
BIB |a Y 
SER |a journal 
JSO |a {"language":["eng"],"recId":"195071067X","note":["Gesehen am 30.01.2026"],"origin":[{"dateIssuedDisp":"[01 Oct 2025]","dateIssuedKey":"2025"}],"name":{"displayForm":["Valentin Konakov, Enno Mammen & Lorick Huang"]},"person":[{"given":"Valentin","role":"aut","display":"Konakov, Valentin","family":"Konakov"},{"role":"aut","given":"Enno","family":"Mammen","display":"Mammen, Enno"},{"given":"Lorick","role":"aut","display":"Huang, Lorick","family":"Huang"}],"id":{"doi":["10.1080/02331888.2025.2562301"],"eki":["195071067X"]},"type":{"bibl":"article-journal","media":"Online-Ressource"},"physDesc":[{"extent":"37 S."}],"relHost":[{"pubHistory":["Volume 16, 1 (1985)-"],"physDesc":[{"extent":"Online-Ressource"}],"title":[{"title":"Statistics","title_sort":"Statistics","subtitle":"a journal of theoretical and applied statistics"}],"type":{"media":"Online-Ressource","bibl":"periodical"},"id":{"zdb":["2035635-3"],"eki":["325350310"],"issn":["1029-4910"]},"origin":[{"publisherPlace":"London [u.a.] ; Berlin ; Newark, NJ [u.a.]","publisher":"Taylor & Francis ; Akademie-Verlag ; Gordon and Breach Publ. Group","dateIssuedDisp":"[1985]-"}],"part":{"pages":"1-37","extent":"37","year":"2025","text":"(2025), Seite 1-37"},"recId":"325350310","note":["Gesehen am 19.09.2022"],"language":["eng"],"disp":"Local limit theorems and strong approximations for Robbins-Monro proceduresStatistics"}],"title":[{"title_sort":"Local limit theorems and strong approximations for Robbins-Monro procedures","title":"Local limit theorems and strong approximations for Robbins-Monro procedures"}]} 
SRT |a KONAKOVVALLOCALLIMIT0120