TY - GEN
T1 - Approximate Hypothesis Testing
AU - Le Gouic, Nicolas
AU - Graczyk, Robert
AU - Moser, Stefan
N1 - Publisher Copyright:
© 2025 IEEE.
PY - 2025/1/1
Y1 - 2025/1/1
N2 - We establish the sample complexity of Approximate Hypothesis Testing (AHT): Unlike in classical hypothesis testing, here we are only required to approximate the sample-generating distribution rather than determine it exactly.On finite hypothesis classes, we establish that the AHT sample complexity scales inversely with the multivariate Bhattacharyya distance (3) evaluated on a set of distributions considered to be the "most confusable"w.r.t. the desired approximation accuracy.
AB - We establish the sample complexity of Approximate Hypothesis Testing (AHT): Unlike in classical hypothesis testing, here we are only required to approximate the sample-generating distribution rather than determine it exactly.On finite hypothesis classes, we establish that the AHT sample complexity scales inversely with the multivariate Bhattacharyya distance (3) evaluated on a set of distributions considered to be the "most confusable"w.r.t. the desired approximation accuracy.
UR - https://www.scopus.com/pages/publications/105029043037
U2 - 10.1109/ITW62417.2025.11240528
DO - 10.1109/ITW62417.2025.11240528
M3 - Conference contribution
AN - SCOPUS:105029043037
T3 - 2025 IEEE Information Theory Workshop, ITW 2025
BT - 2025 IEEE Information Theory Workshop, ITW 2025
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2025 IEEE Information Theory Workshop, ITW 2025
Y2 - 29 September 2025 through 3 October 2025
ER -