REVIEW 1 cited by
Unpacking Information Bottlenecks: Unifying Information-Theoretic Objectives in Deep Learning
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original abstract
The Information Bottleneck principle offers both a mechanism to explain how deep neural networks train and generalize, as well as a regularized objective with which to train models. However, multiple competing objectives are proposed in the literature, and the information-theoretic quantities used in these objectives are difficult to compute for large deep neural networks, which in turn limits their use as a training objective. In this work, we review these quantities and compare and unify previously proposed objectives, which allows us to develop surrogate objectives more friendly to optimization without relying on cumbersome tools such as density estimation. We find that these surrogate objectives allow us to apply the information bottleneck to modern neural network architectures. We demonstrate our insights on MNIST, CIFAR-10 and Imagenette with modern DNN architectures (ResNets).
Forward citations
Cited by 1 Pith paper
-
Revisiting DRUP-based Interpolants with CaDiCaL 2.0
A new DRUP-based interpolation framework for CaDiCaL 2.0, integrated into Avy, outperforms the Glucose-based baseline on HWMCC'19 and HWMCC'20 benchmarks.
Discussion (0). Continue with ORCID to comment.