Explores the trade-off between complexity and risk in machine learning models, the benefits of overparametrization, and the implicit bias of optimization algorithms.
Explores optimization methods like gradient descent and subgradients for training machine learning models, including advanced techniques like Adam optimization.
Discusses Stochastic Gradient Descent and its application in non-convex optimization, focusing on convergence rates and challenges in machine learning.
Explores diverse regularization approaches, including the L0 quasi-norm and the Lasso method, discussing variable selection and efficient algorithms for optimization.