Adaptive SGD with Polyak stepsize and Line-search: Robust Convergence and Variance Reduction.
Xiaowen JiangSebastian U. StichPublished in: CoRR (2023)
Keyphrases
- line search
- step size
- convergence rate
- variance reduction
- convergence speed
- cost function
- faster convergence
- estimation error
- global convergence
- global optimum
- primal dual
- quadratic programming
- risk minimization
- conjugate gradient
- monte carlo
- differential evolution
- decision trees
- computational complexity
- particle swarm optimization
- importance sampling
- semi supervised
- supervised learning
- sample size
- wavelet coefficients
- markov chain