Stochastic Gradient Descent-Ascent and Consensus Optimization for Smooth Games: Convergence Analysis under Expected Co-coercivity.
Nicolas LoizouHugo BerardGauthier GidelIoannis MitliagkasSimon Lacoste-JulienPublished in: CoRR (2021)
Keyphrases
- stochastic gradient descent
- convergence analysis
- global convergence
- step size
- least squares
- convergence rate
- matrix factorization
- loss function
- random forests
- optimality conditions
- regularization parameter
- convergence speed
- global optimum
- multiple kernel learning
- machine learning
- particle swarm
- weight vector
- optimization methods
- nonlinear programming
- online algorithms
- approximation methods
- upper bound
- pairwise