Recent advances in deep generative models have led to the development of...
Diffusion Probabilistic Field (DPF) models the distribution of continuou...
Depth separation – why a deeper network is more powerful than a shallowe...
In this work, we consider the stochastic optimal control problem in
cont...
In deep learning, often the training process finds an interpolator (a
so...
We consider the inverse acoustic obstacle problem for sound-soft star-sh...
Recently, researchers observed that gradient descent for deep neural net...
Monotonic linear interpolation (MLI) - on the line connecting a random
i...
Adversarial attacks pose safety and security concerns for deep learning
...
Owing to security implications of adversarial vulnerability, adversarial...
We propose a single time-scale actor-critic algorithm to solve the linea...
In this paper we study the training dynamics for gradient flow on
over-p...
Deep Neural Network classifiers are vulnerable to adversarial attack, wh...
Pedestrian trajectory prediction is a key technology in autopilot, which...
Recent studies unveil the vulnerabilities of deep ranking models, where ...
We propose a novel numerical method for high dimensional
Hamilton–Jacobi...
While over-parameterization is widely believed to be crucial for the suc...
Deep Neural Network (DNN) classifiers are vulnerable to adversarial atta...
We propose a new method to solve eigenvalue problems for linear and
semi...
For visual-semantic embedding, the existing methods normally treat the
r...
Residual Network (ResNet) is undoubtedly a milestone in deep learning. R...
Numerous empirical evidence has corroborated that the noise plays a cruc...