Maximizing the information learned from finite data selects a simple model
May 02, 2017 Β· Declared Dead Β· π Proceedings of the National Academy of Sciences of the United States of America
"No code URL or promise found in abstract"
Evidence collected by the PWNC Scanner
Authors
Henry H. Mattingly, Mark K. Transtrum, Michael C. Abbott, Benjamin B. Machta
arXiv ID
1705.01166
Category
physics.data-an
Cross-listed
cond-mat.stat-mech,
cs.IT,
math.ST,
stat.ML
Citations
51
Venue
Proceedings of the National Academy of Sciences of the United States of America
Last Checked
3 months ago
Abstract
We use the language of uninformative Bayesian prior choice to study the selection of appropriately simple effective models. We advocate for the prior which maximizes the mutual information between parameters and predictions, learning as much as possible from limited data. When many parameters are poorly constrained by the available data, we find that this prior puts weight only on boundaries of the parameter manifold. Thus it selects a lower-dimensional effective theory in a principled way, ignoring irrelevant parameter directions. In the limit where there is sufficient data to tightly constrain any number of parameters, this reduces to Jeffreys prior. But we argue that this limit is pathological when applied to the hyper-ribbon parameter manifolds generic in science, because it leads to dramatic dependence on effects invisible to experiment.
Community Contributions
Found the code? Know the venue? Think something is wrong? Let us know!
π Similar Papers
In the same crypt β physics.data-an
R.I.P.
π»
Ghosted
R.I.P.
π»
Ghosted
A deep convolutional neural network approach to single-particle recognition in cryo-electron microscopy
R.I.P.
π»
Ghosted
The Pandora Software Development Kit for Pattern Recognition
R.I.P.
π»
Ghosted
Emergence of Compositional Representations in Restricted Boltzmann Machines
R.I.P.
π»
Ghosted
Investigating echo state networks dynamics by means of recurrence analysis
R.I.P.
π»
Ghosted
Discovering state-parameter mappings in subsurface models using generative adversarial networks
Died the same way β π» Ghosted
R.I.P.
π»
Ghosted
Federated Learning: Strategies for Improving Communication Efficiency
R.I.P.
π»
Ghosted
In-Datacenter Performance Analysis of a Tensor Processing Unit
R.I.P.
π»
Ghosted
Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning
R.I.P.
π»
Ghosted