Multi-armed bandits – on range searching and on slowly-varying non-stationarity (Record no. 427156)
[ view plain ]
000 -LEADER | |
---|---|
fixed length control field | 01840nam a22002297a 4500 |
008 - FIXED-LENGTH DATA ELEMENTS--GENERAL INFORMATION | |
fixed length control field | 230317b |||||||| |||| 00| 0 eng d |
041 ## - LANGUAGE CODE | |
Language code of text/sound track or separate title | en. |
082 ## - DEWEY DECIMAL CLASSIFICATION NUMBER | |
Classification number | 600 |
Item number | RAM |
100 ## - MAIN ENTRY--PERSONAL NAME | |
Personal name | Ramakrishnan, K |
245 ## - TITLE STATEMENT | |
Title | Multi-armed bandits – on range searching and on slowly-varying non-stationarity |
260 ## - PUBLICATION, DISTRIBUTION, ETC. (IMPRINT) | |
Place of publication, distribution, etc | Bengaluru |
Name of publisher, distributor, etc | IISc |
Date of publication, distribution, etc | 2022 |
300 ## - PHYSICAL DESCRIPTION | |
Extent | 68p. |
Accompanying material | e-Thesis |
Other physical details | col. ill. ; |
Dimensions | 29.1 cm * 20.5 cm |
Size of unit | 1.367Mb |
500 ## - GENERAL NOTE | |
General note | Include bibliographical referrences and index |
502 ## - DISSERTATION NOTE | |
Dissertation note | MTech (Res); 2022; Computer science and automation |
520 ## - SUMMARY, ETC. | |
Summary, etc | Multi-Armed Bandits (MAB) is a popular framework for modelling sequential decision-making problems under uncertainty. This thesis is a compilation of two independent works on MABs. 1. In the first work, we study a multi-armed bandit (MAB) version of the range-searching problem. In its basic form, range searching considers as input a set of points (on the real line) and a collection of (real) intervals. Here, with each specified point, we have an associated weight, and the problem objective is to find a maximum-weight point within every given interval. The current work addresses range searching with stochastic weights: each point corresponds to an arm (that admits sample access), and the point’s weight is the (unknown) mean of the underlying distribution. In this MAB setup, we develop sample-efficient algorithms that find, with high probability, near-optimal arms within the given intervals, i.e., we obtain PAC (probably approximately correct) guarantees. We also provide an algorithm for a generalization wherein the weight of each point is a multi-dimensional vector. |
650 ## - SUBJECT ADDED ENTRY--TOPICAL TERM | |
Topical term or geographic name as entry element | Multi-Armed Bandits |
650 ## - SUBJECT ADDED ENTRY--TOPICAL TERM | |
Topical term or geographic name as entry element | Range Searching |
650 ## - SUBJECT ADDED ENTRY--TOPICAL TERM | |
Topical term or geographic name as entry element | stochastic weights |
700 ## - ADDED ENTRY--PERSONAL NAME | |
Personal name | Saladi, Rahul advised |
856 ## - ELECTRONIC LOCATION AND ACCESS | |
Uniform Resource Identifier | https://etd.iisc.ac.in/handle/2005/6043 |
942 ## - ADDED ENTRY ELEMENTS (KOHA) | |
Koha item type | Thesis |
Withdrawn status | Lost status | Source of classification or shelving scheme | Damaged status | Not for loan | Home library | Current library | Date acquired | Total Checkouts | Full call number | Barcode | Date last seen | Koha item type |
---|---|---|---|---|---|---|---|---|---|---|---|---|
Dewey Decimal Classification | JRD Tata Memorial Library | JRD Tata Memorial Library | 17/03/2023 | 600 RAM | ET00058 | 17/03/2023 | E-BOOKS |