Pages that link to "Item:Q5084492"
From MaRDI portal
The following pages link to A Diffusion Approximation Theory of Momentum Stochastic Gradient Descent in Nonconvex Optimization (Q5084492):
Displaying 10 items.
- On large batch training and sharp minima: a Fokker-Planck perspective (Q828491) (← links)
- On the diffusion approximation of nonconvex stochastic gradient descent (Q1734292) (← links)
- Uniform-in-time weak error analysis for stochastic gradient descent algorithms via diffusion approximation (Q1984706) (← links)
- Stochastic gradient Hamiltonian Monte Carlo for non-convex learning (Q2137760) (← links)
- Classical algebraic geometry. Abstracts from the workshop held June 20--26, 2021 (hybrid meeting) (Q2693010) (← links)
- On the influence of momentum acceleration on online learning (Q2834537) (← links)
- Global Convergence of Stochastic Gradient Hamiltonian Monte Carlo for Nonconvex Stochastic Optimization: Nonasymptotic Performance Bounds and Momentum-Based Acceleration (Q5058053) (← links)
- Convergence of the Momentum Method for Semialgebraic Functions with Locally Lipschitz Gradients (Q6071885) (← links)
- Convergence of the RMSProp deep learning method with penalty for nonconvex optimization (Q6078716) (← links)
- Switched diffusion processes for non-convex optimization and saddle points search (Q6089196) (← links)
