An Information-Theoretic Perspective on Overfitting and Underfitting

October 12, 2020 ยท Declared Dead ยท ๐Ÿ› Australasian Conference on Artificial Intelligence

๐Ÿ‘ป CAUSE OF DEATH: Ghosted
No code link whatsoever

"No code URL or promise found in abstract"

Evidence collected by the PWNC Scanner

Authors Daniel Bashir, George D. Montanez, Sonia Sehra, Pedro Sandoval Segura, Julius Lauw arXiv ID 2010.06076 Category cs.LG: Machine Learning Cross-listed cs.AI, cs.IT, stat.ML Citations 54 Venue Australasian Conference on Artificial Intelligence Last Checked 5 months ago
Abstract
We present an information-theoretic framework for understanding overfitting and underfitting in machine learning and prove the formal undecidability of determining whether an arbitrary classification algorithm will overfit a dataset. Measuring algorithm capacity via the information transferred from datasets to models, we consider mismatches between algorithm capacities and datasets to provide a signature for when a model can overfit or underfit a dataset. We present results upper-bounding algorithm capacity, establish its relationship to quantities in the algorithmic search framework for machine learning, and relate our work to recent information-theoretic approaches to generalization.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

๐Ÿ“œ Similar Papers

In the same crypt โ€” Machine Learning

Died the same way โ€” ๐Ÿ‘ป Ghosted