Can Machines Learn the True Probabilities?

Jinsook Kim
Proceedings of the 41st International Conference on Machine Learning, PMLR 235:23781-23804, 2024.

Abstract

When there exists uncertainty, AI machines are designed to make decisions so as to reach the best expected outcomes. Expectations are based on true facts about the objective environment the machines interact with, and those facts can be encoded into AI models in the form of true objective probability functions. Accordingly, AI models involve probabilistic machine learning in which the probabilities should be objectively interpreted. We prove under some basic assumptions when machines can learn the true objective probabilities, if any, and when machines cannot learn them.

Cite this Paper

BibTeX
@InProceedings{pmlr-v235-kim24a, title = {Can Machines Learn the True Probabilities?}, author = {Kim, Jinsook}, booktitle = {Proceedings of the 41st International Conference on Machine Learning}, pages = {23781--23804}, year = {2024}, editor = {Salakhutdinov, Ruslan and Kolter, Zico and Heller, Katherine and Weller, Adrian and Oliver, Nuria and Scarlett, Jonathan and Berkenkamp, Felix}, volume = {235}, series = {Proceedings of Machine Learning Research}, month = {21--27 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v235/main/assets/kim24a/kim24a.pdf}, url = {https://proceedings.mlr.press/v235/kim24a.html}, abstract = {When there exists uncertainty, AI machines are designed to make decisions so as to reach the best expected outcomes. Expectations are based on true facts about the objective environment the machines interact with, and those facts can be encoded into AI models in the form of true objective probability functions. Accordingly, AI models involve probabilistic machine learning in which the probabilities should be objectively interpreted. We prove under some basic assumptions when machines can learn the true objective probabilities, if any, and when machines cannot learn them.} }
Endnote
%0 Conference Paper %T Can Machines Learn the True Probabilities? %A Jinsook Kim %B Proceedings of the 41st International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2024 %E Ruslan Salakhutdinov %E Zico Kolter %E Katherine Heller %E Adrian Weller %E Nuria Oliver %E Jonathan Scarlett %E Felix Berkenkamp %F pmlr-v235-kim24a %I PMLR %P 23781--23804 %U https://proceedings.mlr.press/v235/kim24a.html %V 235 %X When there exists uncertainty, AI machines are designed to make decisions so as to reach the best expected outcomes. Expectations are based on true facts about the objective environment the machines interact with, and those facts can be encoded into AI models in the form of true objective probability functions. Accordingly, AI models involve probabilistic machine learning in which the probabilities should be objectively interpreted. We prove under some basic assumptions when machines can learn the true objective probabilities, if any, and when machines cannot learn them.
APA
Kim, J.. (2024). Can Machines Learn the True Probabilities?. Proceedings of the 41st International Conference on Machine Learning, in Proceedings of Machine Learning Research 235:23781-23804 Available from https://proceedings.mlr.press/v235/kim24a.html.

Related Material