In this seminar, we will discuss private federated learning. We will firstly provide new optimization error bounds for differential private federated learning with Laplacian Smoothing (DP-Fed-LS) and heterogeneous data.

Current neural networks can be easily attacked by small artificially chosen noise called adversarial examples.

In this talk, I will first introduce the mirror symmetry for Calabi-Yau threefolds, which describes the genus zero structures of the Gromow-Witten theory.

For Attendees' Attention: This lecture will be held on-site at LT-K and online via zoom.

Abstract

We consider the problem of minimizing an objective function without any derivative information. Such optimization is called zeroth-order, derivative-free, or black-box optimization.

The remarkable empirical performance of Generative Adversarial Networks (GANs) in generating high-quality samples have attracted enormous attention in the past few years. In this talk, we discuss how well can GANs approximate and learn high-dimensional distributions.