More about HKUST
15 May 2020
Seminar, Lecture, Talk
MATH_PhD Student Seminar - Eigenvector distribution for spiked model with or without missing condition
In random matrix theory, one of the central topics is the limiting behavior of eigenvalues and eigenvectors of random matrices under fixed-rank perturbations. A famous model, raised by Johnstone, is the so-called spiked covariance matrix model.
15 May 2020
Seminar, Lecture, Talk
MATH_PhD Student Seminar - High-order finite difference gas-kinetic scheme for the Euler and Navier-Stokes equations
With the two-stage fourth-order temporal evolution of the gas distribution function and Weighted Essential Non-Oscillatory (WENO) reconstruction, a high-order finite difference gas-kinetic scheme is proposed.
15 May 2020
Seminar, Lecture, Talk
MATH_PhD Student Seminar - Bidirectional Generative Modeling Using Adversarial Gradient Estimation
We consider the general $f$-divergence formulation of bidirectional generative modeling, which includes VAE and BiGAN as special cases. We present a new optimization method for this formulation, where the gradient is computed using an adversarially learned discriminator.
15 May 2020
Seminar, Lecture, Talk
MATH_PhD Student Seminar - Local behavior of positive solutions of higher order conformally invariant equations with a singular set
We study some properties of singular positive solutions to the conformally invariant equations. We prove an asymptotic blow rate estimate for positive solutions near the singular set with some conditions about the Minkowski dimension of the set.
15 May 2020
Seminar, Lecture, Talk
MATH_PhD Student Seminar - Black-Box Adversarial Attack
Current neural network-based classifiers are susceptible to adversarial examples even in the black-box setting, where the attacker could only query the output of the network. We present a new method for black-box adversarial attack.
14 May 2020
Seminar, Lecture, Talk
MATH_PhD Student Seminar - Exploring Private Federated Learning with Laplacian Smoothing
Federated learning aims to protect data privacy by collaboratively learning a model without sharing private data among users. However, an adversary may still be able to infer the private training data by attacking the released model.
14 May 2020
Seminar, Lecture, Talk
MATH_PhD Student Seminar - Towards Adversarial Robustness by Natural Training Using Deep Stable ODE Networks
In this seminar I will talk about a provably stable architecture for Neural Ordinary Differential Equations (ODEs) which achieves non-trivial adversarial robustness under white-box adversarial attacks even when the network is trained naturally.
14 May 2020
Seminar, Lecture, Talk
MATH_PhD Student Seminar - Detect conformation change by template matching in cryo-em images
Cryo-EM detects protein conformations froze in solution, and thus provides a promising way to characterize these conformational changes. In order to detect the conformational change, we developed a new algorithm to obtain multiple conformations and their populations from Cryo-EM datasets.
For more past events from across the School of Science, please visit here.