Worst-Case Convergence Time of ML Algorithms via Extreme Value Theory.
Saeid Tizpaz-NiariSriram SankaranarayananPublished in: CAIN (2024)
Keyphrases
- worst case
- extreme value theory
- error bounds
- lower bound
- computational cost
- learning algorithm
- average case
- computational efficiency
- orders of magnitude
- np hard
- computer vision
- significant improvement
- upper bound
- neural network
- computational complexity
- times faster
- recently developed
- greedy algorithm
- theoretical analysis
- running times
- theoretical guarantees
- stochastic approximation
- iterative algorithms
- theoretical justification
- convergence rate
- computationally efficient
- maximum likelihood
- optimal solution
- genetic algorithm
- machine learning