Max sliced Wasserstein (Max-SW) distance has been widely known as a solu...
Data-free Knowledge Distillation (DFKD) has attracted attention recently...
Knowledge distillation (KD) is an efficient approach to transfer the
kno...
Data augmentation is one of the most successful techniques to improve th...
We introduce a conditional compression problem and propose a fast framew...
Trojan attacks on deep neural networks are both dangerous and surreptiti...
Layer-wise model fusion via optimal transport, named OTFusion, applies s...
In this paper we present a novel method for estimating the parameters of...
Mini-batch optimal transport (m-OT) has been widely used recently to dea...
This study aims to propose effective modeling and approach for designing...
Bayesian optimization (BO) is an efficient method for optimizing expensi...
Interpretability allows the domain-expert to directly evaluate the model...
In this note, we derive the closed form formulae for moments of Student'...
Many real-world functions are defined over both categorical and
category...
In this paper we consider the problem of finding stable maxima of expens...