Are you an EPFL student looking for a semester project?
Work with us on data science and visualisation projects, and deploy your project as an app on top of Graph Search.
This lecture covers time-data trade-offs, variance reduction, and the role of convexity in mathematical models for data analysis. It delves into the challenges of estimation, prediction, and decision-making in regression models, emphasizing sparse representations and combinatorial approaches. The instructor discusses the impact of sparsity on overcomplete matrices and presents a computational dogma related to the running time of learning algorithms.