Skip to main navigation
Skip to search
Skip to main content
KAUST PORTAL FOR RESEARCHERS AND STUDENTS Home
Help & FAQ
Home
Profiles
Research Units
Research output
Prizes
Equipment
Courses
Datasets
Student theses
Press / Media
Search by expertise, name or affiliation
Algorithm portfolio selection as a bandit problem with unbounded losses
Matteo Gagliolo,
Jürgen Schmidhuber
Research output
:
Contribution to journal
›
Article
›
peer-review
20
Scopus citations
Overview
Fingerprint
Fingerprint
Dive into the research topics of 'Algorithm portfolio selection as a bandit problem with unbounded losses'. Together they form a unique fingerprint.
Sort by
Weight
Alphabetically
Social Sciences
Algorithms
100%
Problem
75%
Performance
62%
Time
50%
Information
25%
Resource Allocation
25%
Guides
12%
Portfolio Selection
12%
Experiments
12%
Experts
12%
Training
12%
Training
12%
Awards
12%
Alternative
12%
Mathematics
Algorithm
75%
Bounds
37%
Sequences
25%
Selection
25%
Tradeoff
12%
Training Sequence
12%
General Method
12%
Computer Science
Computation Time
25%
Algorithm Performance
25%
Performance Model
25%
Problem Instance
25%
Training Sequence
12%
Online Approach
12%
Allocator
12%
Allocate Computation
12%
Domains
12%
Economics, Econometrics and Finance
Loss
25%
Allocation
25%
Portfolio Selection
12%