Global Convergence of Stochastic Gradient Hamiltonian Monte Carlo for Non-Convex Stochastic Optimization: Non-Asymptotic Performance Bounds and Momentum-Based Acceleration.
Xuefeng GaoMert GürbüzbalabanLingjiong ZhuPublished in: CoRR (2018)
Keyphrases
- monte carlo
- stochastic optimization
- global convergence
- stochastic gradient
- convergence rate
- step size
- learning rate
- global optimum
- convergence speed
- worst case
- optimization methods
- multistage
- upper bound
- importance sampling
- markov chain
- lower bound
- convex optimization
- objective function
- simulated annealing
- convex hull
- particle filter
- primal dual
- particle swarm optimization
- optimization problems
- robust optimization