Adversarial robustness is a research area that has recently received a l...
Semi-supervised learning (SSL) algorithm is a setup built upon a realist...
In this paper, we propose a new Bayesian inference method for a
high-dim...
Bayesian approaches for learning deep neural networks (BNN) have been
re...
Weighting methods in causal inference have been widely used to achieve a...
As they have a vital effect on social decision-making, AI algorithms not...
Identifying whether a given sample is an outlier or not is an important ...
Adversarial training, which is to enhance robustness against adversarial...
As data size and computing power increase, the architectures of deep neu...
As they have a vital effect on social decision makings, AI algorithms sh...
As they have a vital effect on social decision-making, AI algorithms sho...
In many classification problems, collecting massive clean-annotated data...
We investigate statistical properties of a likelihood approach to
nonpar...
The Mixup method (Zhang et al. 2018), which uses linearly interpolated d...
Recent theoretical studies proved that deep neural network (DNN) estimat...
In semi-supervised learning, virtual adversarial training (VAT) approach...
There has been a growing interest in expressivity of deep neural network...
Compositional data have two unique characteristics compared to typical
m...
We derive the fast convergence rates of a deep neural network (DNN)
clas...
We provide a theoretical explanation of the role of the number of nodes ...