The basic theory underlying machine learning and the process of generalizing from data
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.
A seminar course that will focus on the following phenomenon: many problems in machine learning are formally intractable (e.g., NP-hard). Nevertheless they are solved in practice by heuristics. Can we design algorithms with provable guarantees (running time, solution quality)?
Formally define and study various models that have been proposed for learning. The course will present and contrast the statistical, computational and online models for learning. We will present and rigorously analyze some of the most successful algorithms in machine learning that are extensively used today
Focuses on simplified proofs over what appears in the literature, and classical perspective of achieving a low test error for binary classification with IID data via standard (typically ReLU) feedforward networks
A broad overview of the theoretical foundations underlying common machine learning algorithms