Search Results for author:
Found 7 papers, 5 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.
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.
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.
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).
