Today

  • What Algorithms can Transformers Learn? A Study in Length Generalization

    CMSA Room G10 CMSA, 20 Garden Street, Cambridge, MA, United States

    New Technologies in Mathematics Seminar Speaker: Preetum Nakkiran, Apple Title: What Algorithms can Transformers Learn? A Study in Length Generalization Abstract: Large language models exhibit many surprising “out-of-distribution” generalization abilities, yet also struggle to solve certain simple tasks like decimal addition. To clarify the scope of Transformers' out-of-distribution generalization, we isolate this behavior in a […]

  • Computers and mathematics in partial differential equations: New developments and challenges

    CMSA Room G10 CMSA, 20 Garden Street, Cambridge, MA, United States

    https://youtu.be/JB2WqmpmTgk New Technologies in Mathematics Seminar Speaker: Javier Gomez Serrano, Brown University Title: Computers and mathematics in partial differential equations: new developments and challenges Abstract: In this talk I will address the interaction between traditional and more modern mathematics and how computers have helped over the last decade providing rigorous (computer-assisted) proofs in the context […]

  • LILO: Learning Interpretable Libraries by Compressing and Documenting Code

    CMSA Room G10 CMSA, 20 Garden Street, Cambridge, MA, United States

    https://youtu.be/ZDMRN0Iyp28 New Technologies in Mathematics Seminar Speaker: Gabe Grand, MIT CSAIL and Dept. of EE&CS Title: LILO: Learning Interpretable Libraries by Compressing and Documenting Code Abstract: While large language models (LLMs) now excel at code generation, a key aspect of software development is the art of refactoring: consolidating code into libraries of reusable and readable programs. […]

  • Solving olympiad geometry without human demonstrations

    Virtual

    https://youtu.be/eZbYSOpga2U New Technologies in Mathematics Seminar Speaker: Trieu H. Trinh, Google Deepmind and NYU Dept. of Computer Science Title: Solving olympiad geometry without human demonstrations Abstract: Proving mathematical theorems at the olympiad level represents a notable milestone in human-level automated reasoning, owing to their reputed difficulty among the world’s best talents in pre-university mathematics. Current […]

  • Mathematics and Machine Learning Program

    CMSA Room G10 CMSA, 20 Garden Street, Cambridge, MA, United States

    Mathematics and Machine Learning Program Dates: September 3 - November 1, 2024 Location: Harvard CMSA, 20 Garden Street, Cambridge, MA 0213 Machine learning and AI are increasingly important tools in all fields of research. Recent milestones in machine learning for mathematics include data-driven discovery of theorems in knot theory and representation theory, the discovery and […]