2 papers
cs.LG2025
Towards Continuous-Time Approximations for Stochastic Gradient Descent without Replacement
Stefan Perko
Gradient optimization algorithms using epochs, that is those based on stochastic gradient descent without replacement (SGDo), are predominantly used to train machine learning model…
math.PR2025
Modified Equations for Stochastic Optimization
Stefan Perko
In this thesis, we extend the recently introduced theory of stochastic modified equations (SMEs) for stochastic gradient optimization algorithms. In Ch. 3 we study time-inhomogeneo…