Talks

Some Virtual Talks

• Spectra of the Conjugate Kernel and Neural Tangent Kernel for linear-width neural networks.
  NeurIPS 2020.

• Tree convolution for probability distributions with unbounded support.
  RMMC Summer School (2022) on Free Probability, Random Matrices, and Applications, University of Wyoming, June 2022.

• High-dimensional Asymptotics of Feature Learning: How One Gradient Step Improves the Representation.
  NeurIPS 2022.

• Signal Propagation and Feature Learning in Neural Networks.
  The DIMACS Workshop on Modeling Randomness in Neural Network Training: Mathematical, Statistical, and Numerical Guarantees was held at Rutgers University on June 5-7, 2024