• Learning curves of kernel methods

    Group meeting, July 2020

  • Loss Landscape and Performance in Deep Learning

    Talk given at Emory, June 2020

  • Spectrum Dependent Learning Curves in Kernel Regression and Wide Neural Networks

  • Kernel methods and the curse of dimensionality

    Talk given in Courant Institute, NY, March 2020

  • Loss Landscape and Generalization in Deep Learning

    Talk given in Les Houches (https://sites.google.com/view/leshouches2020)

  • Loss Landscape and Performance in Deep Learning

    Talk given in ICTS, Bangalore, January 2020

  • Asymptotic learning curves of kernel methods

  • Crans-Montana 2019 retreat

    Overview on DL. Typical applications and open problems. Comparison with classical inference. Our contribution.

  • A jamming transition from under- to over-parametrizationaffects loss landscape and generalization

    HEP-AI talk on "A jamming transition from under- to over-parametrizationaffects loss landscape and generalization", arxivs: 1809.09349, 1810.09665