no code implementations • 15 Feb 2022 • Hassan Hafez-Kolahi, Behrad Moniri, Shohreh Kasaei
We consider the frequentist problem of minimax excess risk as a zero-sum game between the algorithm designer and the world.
no code implementations • 10 May 2021 • Hassan Hafez-Kolahi, Behrad Moniri, Shohreh Kasaei, Mahdieh Soleymani Baghshah
For the upper bound, the optimization is further constrained to use $R$ bits from the training set, a setting which relates MER to information-theoretic bounds on the generalization gap in frequentist learning.
no code implementations • NeurIPS 2020 • Hassan Hafez-Kolahi, Zeinab Golgooni, Shohreh Kasaei, Mahdieh Soleymani
This approach provides an insight into learning algorithms by considering the mutual information between the model and the training set.
no code implementations • 20 Sep 2019 • Hassan Hafez-Kolahi, Shohreh Kasaei, Mahdiyeh Soleymani-Baghshah
In this paper, the constraint on the entropy $H(X)$ of the input variable $X$ is studied as a simplicity assumption.
no code implementations • 7 Apr 2019 • Hassan Hafez-Kolahi, Shohreh Kasaei
Information Theory (IT) has been used in Machine Learning (ML) from early days of this field.