A Deterministic Analysis for Learning Algorithms with Constant Learning Rates
1997
A novel deterministic approach to the convergence analysis of (stochastic) learning algorithms is presented. The link between the two is a new concept of time-average invariance (TAI) which is a property of deterministic signals but with applications to stochastic signals. It is then extended to the case of perturbed TAI signals.
Keywords:
- Online machine learning
- Machine learning
- Computational learning theory
- Stability (learning theory)
- Algorithm
- Ensemble learning
- Artificial intelligence
- Empirical risk minimization
- Wake-sleep algorithm
- Probably approximately correct learning
- Deterministic system (philosophy)
- Computer science
- Theoretical computer science
- Correction
- Source
- Cite
- Save
- Machine Reading By IdeaReader
8
References
0
Citations
NaN
KQI