The AI Innovation Institute (AI3) will host a seminar featuring Professor Meir Feder from Tel-Aviv University on Monday, November 10. The event, titled “Information-Theoretic Framework for Understanding Modern Machine-Learning,” will take place at 12:30 pm in the New Computer Science Building, Room 120.
According to the announcement, Information Theory considers learning as universal prediction under log loss and is defined through regret bounds. While traditional results focused on small model classes and provided uniform regret, this new framework offers non-uniform, model-dependent bounds that use an effective concept of architecture-based model complexity.
Professor Feder holds the Jokel Chair in Information Theory at Tel-Aviv University’s School of Electrical and Computer Engineering. His accolades include the IEEE Information Theory Society best paper award and the Padovani lectureship. In addition to his academic work, he has founded five companies, including Peach Networks and Amimon.
Recently, Professor Feder co-founded Run:ai, a company specializing in virtualization and orchestration platforms for AI infrastructure. Nvidia later acquired Run:ai to support its GPU cloud operations. For his technological contributions at Amimon, he received the 2020 Scientific and Engineering Award from the Academy of Motion Picture Arts and Sciences and was recognized as the principal inventor of technology that won the 73rd Engineering Emmy Award from the Television Academy.
