Search Results for author:
Found 7 papers, 1 papers with code
MM-GATBT: Enriching Multimodal Representation Using Graph Attention Network
While there have been advances in Natural Language Processing (NLP), their success is mainly gained by applying a self-attention mechanism into single or multi-modalities.
Randomized Algorithms for Comparison-based Search
This paper addresses the problem of finding the nearest neighbor (or one of the $R$-nearest neighbors) of a query object $q$ in a database of $n$ objects, when we can only use a comparison oracle.
Deep Switch Networks for Generating Discrete Data and Language
Unlike deconvolution networks which generate continuous-valued data and which consist of upsampling filters and reverse pooling layers, multilayer switch networks are composed of adaptive switches which model conditional distributions of discrete random variables.
Robust Classification Under $\ell_0$ Attack for the Gaussian Mixture Model
Under the assumption that data is distributed according to the Gaussian mixture model, our goal is to characterize the optimal robust classifier and the corresponding robust classification error as well as a variety of trade-offs between robustness, accuracy, and the adversary's budget.
Efficient and Robust Classification for Sparse Attacks
In the past two decades we have seen the popularity of neural networks increase in conjunction with their classification accuracy.
Binary Classification Under $\ell_0$ Attacks for General Noise Distribution
We introduce a classification method which employs a nonlinear component called truncation, and show in an asymptotic scenario, as long as the adversary is restricted to perturb no more than $\sqrt{d}$ data samples, we can almost achieve the optimal classification error in the absence of the adversary, i. e. we can completely neutralize adversary's effect.
Generalization Properties of Adversarial Training for $\ell_0$-Bounded Adversarial Attacks
In this paper, we focus on the $\ell_0$-bounded adversarial attacks, and aim to theoretically characterize the performance of adversarial training for an important class of truncated classifiers.
