Adaptive Stochastic Gradient Langevin Dynamics: Taming Convergence and Saddle Point Escape Time
–arXiv.org Artificial Intelligence
In this paper, we propose a new adaptive stochastic gradient Langevin dynamics (ASGLD) algorithmic framework and its two specialized versions, namely adaptive stochastic gradient (ASG) and adaptive gradient Langevin dynamics(AGLD), for non-convex optimization problems. All proposed algorithms can escape from saddle points with at most $O(\log d)$ iterations, which is nearly dimension-free. Further, we show that ASGLD and ASG converge to a local minimum with at most $O(\log d/\epsilon^4)$ iterations. Also, ASGLD with full gradients or ASGLD with a slowly linearly increasing batch size converge to a local minimum with iterations bounded by $O(\log d/\epsilon^2)$, which outperforms existing first-order methods.
arXiv.org Artificial Intelligence
May-23-2018
- Country:
- Asia
- Afghanistan > Parwan Province
- Charikar (0.04)
- Middle East > Jordan (0.04)
- Afghanistan > Parwan Province
- Europe > Romania
- Sud-Est Development Region > Constanța County > Constanța (0.04)
- North America > United States
- Iowa > Story County > Ames (0.04)
- Asia
- Genre:
- Research Report (0.82)