Hassan Hafez-Kolahi — accepted AI-conference papers

2021

Rate-Distortion Analysis of Minimum Excess Risk in Bayesian Learning

Hassan Hafez-Kolahi, Behrad Moniri, Shohreh Kasaei, Mahdieh Soleymani Baghshah

ICML 2021oral

In parametric Bayesian learning, a prior is assumed on the parameter $W$ which determines the distribution of samples. In this setting, Minimum Excess Risk (MER) is defined as the difference between the minimum expected loss achievable when learning from data and the minimum expected loss that could…

Cited by 12 Source ↗PDF ↗Scholar ↗

2020

Conditioning and Processing: Techniques to Improve Information-Theoretic Generalization Bounds

Hassan Hafez-Kolahi, Zeinab Golgooni, Shohreh Kasaei, Mahdieh Soleymani

NeurIPS 2020poster

Obtaining generalization bounds for learning algorithms is one of the main subjects studied in theoretical machine learning. In recent years, information-theoretic bounds on generalization have gained the attention of researchers. This approach provides an insight into learning algorithms by conside…

Cited by 54 Source ↗PDF ↗Scholar ↗