Projekteja vuodessa
Abstrakti
Machine learning can help personalized decision support by learning models to predict individual treatment effects (ITE). This work studies the reliability of prediction-based decision-making in a task of deciding which action a to take for a target unit after observing its covariates x~ and predicted outcomes p^(y~∣x~,a). An example case is personalized medicine and the decision of which treatment to give to a patient. A common problem when learning these models from observational data is imbalance, that is, difference in treated/control covariate distributions, which is known to increase the upper bound of the expected ITE estimation error. We propose to assess the decision-making reliability by estimating the ITE model’s Type S error rate, which is the probability of the model inferring the sign of the treatment effect wrong. Furthermore, we use the estimated reliability as a criterion for active learning, in order to collect new (possibly expensive) observations, instead of making a forced choice based on unreliable predictions. We demonstrate the effectiveness of this decision-making aware active learning in two decision-making tasks: in simulated data with binary outcomes and in a medical dataset with synthetic and continuous treatment outcomes.
Alkuperäiskieli | Englanti |
---|---|
Otsikko | 36th International Conference on Machine Learning, ICML 2019 |
Sivut | 10578-10587 |
Sivumäärä | 10 |
ISBN (elektroninen) | 9781510886988 |
Tila | Julkaistu - 2019 |
OKM-julkaisutyyppi | A4 Artikkeli konferenssijulkaisuussa |
Tapahtuma | International Conference on Machine Learning - Long Beach, Yhdysvallat Kesto: 9 kesäkuuta 2019 → 15 kesäkuuta 2019 Konferenssinumero: 36 |
Julkaisusarja
Nimi | Proceedings of Machine Learning Research |
---|---|
Kustantaja | PMLR |
Vuosikerta | 97 |
ISSN (elektroninen) | 1938-7228 |
Conference
Conference | International Conference on Machine Learning |
---|---|
Lyhennettä | ICML |
Maa/Alue | Yhdysvallat |
Kaupunki | Long Beach |
Ajanjakso | 09/06/2019 → 15/06/2019 |
Sormenjälki
Sukella tutkimusaiheisiin 'Active Learning for Decision-Making from Imbalanced Observational Data'. Ne muodostavat yhdessä ainutlaatuisen sormenjäljen.-
FCAI: Suomen tekoälykeskus
01/01/2019 → 31/12/2022
Projekti: Academy of Finland: Other research funding
-
Interaktiivinen koneoppiminen useista biodatalähteistä
Jälkö, J., Hegde, P., Kaski, S., Gadd, C., Jain, A., Hämäläinen, A., Siren, J., Shen, Z. & Trinh, T.
01/01/2019 → 31/08/2021
Projekti: Academy of Finland: Other research funding
-
Luotettava automatisoitu bayesilainen koneoppiminen
Vehtari, A., Ghosh, K., Dhaka, A., Koistinen, O., Magnusson, M. & Pavone, F.
01/01/2018 → 31/12/2019
Projekti: Academy of Finland: Other research funding