Generalization Bounds for Stochastic Gradient Descent via Localized $\varepsilon$-Covers.
Sejun ParkUmut SimsekliMurat A. ErdogduPublished in: NeurIPS (2022)
Keyphrases
- stochastic gradient descent
- vc dimension
- least squares
- matrix factorization
- loss function
- upper bound
- data dependent
- sample size
- lower bound
- random forests
- support vector machine
- inductive inference
- sample complexity
- generalization ability
- worst case
- multiple kernel learning
- importance sampling
- learning problems
- model selection
- recommender systems
- learning algorithm