Seminar: Implicit Regularization of SGD in High-dimensional Linear Regression - видео

Speaker: Cong Fang Researcher at Peking University What will the talk cover? Stochastic Gradient Descent SGD is one of the most widely used algorithms in modern machine learning. In high-dimensional learning problems the number of SGD iterations is often smaller than the number of model parameters and the implicit regularization induced by the algorithm plays a key role in ensuring strong generalization performance. In this seminar we will: Analyze the generalization behavior of SGD across diff...
Источник видео: RuTube.ru (Обучение)