2 problems

0 votes0 replies0 views
Linearly decreasing mini-batch complexity for stochastic variance-reduced methods
The expected smoothness constant governs the convergence of stochastic variance-reduced methods, and the total complexity of SAGA decreases linearly with the mini-batch size up to…
Conjectureopenmini-batch-methods stochastic-optimization variance-reductionarXiv posted 2 days ago
0 votes0 replies0 views
Conjecture on total-complexity improvement for larger problems in mini-batch SAGA
The discussion concerns mini-batch SAGA applied with a mini-batch size $tau$ to stochastic optimization problems, where the total complexity is the product of $tau$ and the iterati…
Conjectureopenmini-batch-methods stochastic-optimization variance-reductionarXiv posted 2 days ago

Linearly decreasing mini-batch complexity for stochastic variance-reduced methods