π
π
The Cartographer
The Asymptotic Cost of Complexity
August 27, 2024 Β· Declared Dead Β· π arXiv.org
"No code URL or promise found in abstract"
Evidence collected by the PWNC Scanner
Authors
Martin W Cripps
arXiv ID
2408.14949
Category
econ.TH
Cross-listed
cs.IT
Citations
0
Venue
arXiv.org
Last Checked
3 months ago
Abstract
We propose a measure of learning efficiency for non-finite state spaces. We characterize the complexity of a learning problem by the metric entropy of its state space. We then describe how learning efficiency is determined by this measure of complexity. This is, then, applied to two models where agents learn high-dimensional states.
Community Contributions
Found the code? Know the venue? Think something is wrong? Let us know!
π Similar Papers
In the same crypt β econ.TH
R.I.P.
π»
Ghosted
Measuring the Completeness of Theories
R.I.P.
π»
Ghosted
Interactive coin offerings
R.I.P.
π»
Ghosted
Allocating marketing resources over social networks: A long-term analysis
R.I.P.
π»
Ghosted
Approximately Optimal Mechanism Design
R.I.P.
π»
Ghosted
A Social Network Analysis of Occupational Segregation
Died the same way β π» Ghosted
R.I.P.
π»
Ghosted
Neural Architecture Search with Reinforcement Learning
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