TY - GEN
T1 - Real-Time Scheduling of Multistage IDK-Cascades
AU - Baruah, Sanjoy
N1 - Publisher Copyright:
© 2021 IEEE.
PY - 2021/6
Y1 - 2021/6
N2 - An IDK classifier is a software component that categorizes each input provided to it into one of a fixed set of 'classes,' or outputs an 'I don't know' (IDK) to indicate that it is unable to classify this input. An IDK-cascade is a linear arrangement of different IDK classifiers for the same classification problem, which are executed in sequence on a given input until one outputs an actual class (rather than IDK). Given a multistage computation that must be completed within a specified hard end-to-end deadline and a choice of classifiers, one deterministic and one an IDK-cascade, for each stage, the problem of determining which IDK-cascades to schedule in order to minimize the expected end-to-end response time while guaranteeing to meet the specified deadline is considered. Different variants of this problem are defined, and optimal algorithms for solving them are derived.
AB - An IDK classifier is a software component that categorizes each input provided to it into one of a fixed set of 'classes,' or outputs an 'I don't know' (IDK) to indicate that it is unable to classify this input. An IDK-cascade is a linear arrangement of different IDK classifiers for the same classification problem, which are executed in sequence on a given input until one outputs an actual class (rather than IDK). Given a multistage computation that must be completed within a specified hard end-to-end deadline and a choice of classifiers, one deterministic and one an IDK-cascade, for each stage, the problem of determining which IDK-cascades to schedule in order to minimize the expected end-to-end response time while guaranteeing to meet the specified deadline is considered. Different variants of this problem are defined, and optimal algorithms for solving them are derived.
KW - Classifiers
KW - Deep Learning
KW - End-to-end Deadline
KW - IDK-cascades
KW - Multistage Computation
UR - https://www.scopus.com/pages/publications/85112863829
U2 - 10.1109/ISORC52013.2021.00021
DO - 10.1109/ISORC52013.2021.00021
M3 - Conference contribution
AN - SCOPUS:85112863829
T3 - Proceedings - 2021 IEEE 24th International Symposium on Real-Time Distributed Computing, ISORC 2021
SP - 79
EP - 85
BT - Proceedings - 2021 IEEE 24th International Symposium on Real-Time Distributed Computing, ISORC 2021
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 24th IEEE International Symposium on Real-Time Distributed Computing, ISORC 2021
Y2 - 1 June 2021 through 3 June 2021
ER -