On the information bottleneck theory of deep learning

Andrew M. Saxe, Andrea Banino, Danijar Hafner, Máté Lengyel, Surya Ganguli
Paper From BibTeX import
Journal of Statistical Mechanics: Theory and Experiment 2019, pp. 124020, 2019

Notes

Their caveats about the descriptive reach of the IB principle in deep learning temper the scope under which riva2026task applies its bottleneck-style reasoning.

References

No references yet.