Information Theoretic Lower Bounds for Information Theoretic Upper Bounds
–arXiv.org Artificial Intelligence
We examine the relationship between the mutual information between the output model and the empirical sample and the generalization of the algorithm in the context of stochastic convex optimization. Despite increasing interest in information-theoretic generalization bounds, it is uncertain if these bounds can provide insight into the exceptional performance of various learning algorithms. Our study of stochastic convex optimization reveals that, for true risk minimization, dimension-dependent mutual information is necessary. This indicates that existing information-theoretic generalization bounds fall short in capturing the generalization capabilities of algorithms like SGD and regularized ERM, which have dimension-independent sample complexity.
arXiv.org Artificial Intelligence
Feb-9-2023
- Country:
- North America > United States
- California > Santa Clara County > Palo Alto (0.04)
- Europe > United Kingdom
- England > Cambridgeshire > Cambridge (0.04)
- Asia > Middle East
- Israel > Tel Aviv District > Tel Aviv (0.04)
- North America > United States
- Genre:
- Research Report (0.82)
- Technology: