Search Results for author:
Found 23 papers, 7 papers with code
Posterior concentrations of fully-connected Bayesian neural networks with general priors on the weights
Bayesian approaches for training deep neural networks (BNNs) have received significant interest and have been effectively utilized in a wide range of applications.
Improving Performance of Semi-Supervised Learning by Adversarial Attacks
Semi-supervised learning (SSL) algorithm is a setup built upon a realistic assumption that access to a large amount of labeled data is tough.
Enhancing Adversarial Robustness in Low-Label Regime via Adaptively Weighted Regularization and Knowledge Distillation
For example, our algorithm with only 8\% labeled data is comparable to supervised adversarial training algorithms that use all labeled data, both in terms of standard and robust accuracies on CIFAR-10.
A Bayesian sparse factor model with adaptive posterior concentration
In this paper, we propose a new Bayesian inference method for a high-dimensional sparse factor model that allows both the factor dimensionality and the sparse structure of the loading matrix to be inferred.
Masked Bayesian Neural Networks : Theoretical Guarantee and its Posterior Inference
Bayesian approaches for learning deep neural networks (BNN) have been received much attention and successfully applied to various applications.
Covariate balancing using the integral probability metric for causal inference
However, the existing weighting methods have desirable theoretical properties only when a certain model, either the propensity score or outcome regression model, is correctly specified.
Within-group fairness: A guidance for more sound between-group fairness
We introduce a new concept of fairness so-called within-group fairness which requires that AI models should be fair for those in a same sensitive group as well as those in different sensitive groups.
ODIM: an efficient method to detect outliers via inlier-memorization effect of deep generative models
This study aims to solve the unsupervised outlier detection problem where training data contain outliers, but any label information about inliers and outliers is not given.
Improving Adversarial Robustness by Putting More Regularizations on Less Robust Samples
Adversarial training, which is to enhance robustness against adversarial attacks, has received much attention because it is easy to generate human-imperceptible perturbations of data to deceive a given deep neural network.
Masked Bayesian Neural Networks : Computation and Optimality
As data size and computing power increase, the architectures of deep neural networks (DNNs) have been getting more complex and huge, and thus there is a growing need to simplify such complex and huge DNNs.
Learning fair representation with a parametric integral probability metric
That is, we derive theoretical relations between the fairness of representation and the fairness of the prediction model built on the top of the representation (i. e., using the representation as the input).
SLIDE: a surrogate fairness constraint to ensure fairness consistency
As they have a vital effect on social decision makings, AI algorithms should be not only accurate and but also fair.
$L_q$ regularization for Fairness AI robust to sampling bias
To ensure fairness on test data, we develop computationally efficient learning algorithms robust to sampling bias.
INN: A Method Identifying Clean-annotated Samples via Consistency Effect in Deep Neural Networks
By carrying out various experiments, we demonstrate that the INN method resolves the shortcomings in the memorization effect successfully and thus is helpful to construct more accurate deep prediction models with training data with noisy labels.
A likelihood approach to nonparametric estimation of a singular distribution using deep generative models
In the considered model, a usual likelihood approach can fail to estimate the target distribution consistently due to the singularity.
Kernel-convoluted Deep Neural Networks with Data Augmentation
The Mixup method (Zhang et al. 2018), which uses linearly interpolated data, has emerged as an effective data augmentation tool to improve generalization performance and the robustness to adversarial examples.
Nonconvex sparse regularization for deep neural networks and its optimality
Recent theoretical studies proved that deep neural network (DNN) estimators obtained by minimizing empirical risk with a certain sparsity constraint can attain optimal convergence rates for regression and classification problems.
Understanding and Improving Virtual Adversarial Training
In semi-supervised learning, virtual adversarial training (VAT) approach is one of the most attractive method due to its intuitional simplicity and powerful performances.
Smooth function approximation by deep neural networks with general activation functions
Based on our approximation error analysis, we derive the minimax optimality of the deep neural network estimators with the general activation functions in both regression and classification problems.
Primal path algorithm for compositional data analysis
To reflect these characteristics, a specific regularized regression model with linear constraints is commonly used.
Fast convergence rates of deep neural networks for classification
In addition, we consider a DNN classifier learned by minimizing the cross-entropy, and show that the DNN classifier achieves a fast convergence rate under the condition that the conditional class probabilities of most data are sufficiently close to either 1 or zero.
On variation of gradients of deep neural networks
We provide a theoretical explanation of the role of the number of nodes at each layer in deep neural networks.
Fast adversarial training for semi-supervised learning
The proposed method generates bad samples of high-quality by use of the adversarial training used in VAT.
