Nonconvex optimization (IMAGE) University of California - San Diego Caption One of the foremost challenges in advancement of AI is to be able to learn in the presence of stochastic or adversarial agents. This requires nonconvex optimization. Credit UC San Diego Usage Restrictions none License Original content Disclaimer: AAAS and EurekAlert! are not responsible for the accuracy of news releases posted to EurekAlert! by contributing institutions or for the use of any information through the EurekAlert system.