Tianqi Chen

Tianqi Chen

PhD student in Statistics at UT-Austin; A Deep Learning enthusiast :)

Publications

Learning to Jump: Thinning and Thickening Latent Counts for Generative Modeling

Published in Proceedings of Machine Learning Research, 2023

We propose a binomial/Poisson-based hierarchical variational autoencoding framework that are well suited for modeling non-standard non-negative distributions that exhibit sparsity, skewedness, heavy-tailedness and/or heterogeneity.

Recommended citation: T. Chen and M. Zhou. Learning to Jump: Thinning and Thickening Latent Counts for Generative Modeling. In Proceedings of the 40th International Conference on Machine Learning (ICML), pages 5367–5382. PMLR, 2023 https://proceedings.mlr.press/v202/chen23ap.html

ASK: Adversarial Soft k-Nearest Neighbor Attack and Defense

Published in IEEE Access, 2022

In this work, we first introduce an information-theoretic surrogate loss for DkNN-based classification, based upon which we then propose an attack algorithm and a defense algorithm achieve SOTA adversarial results on DkNN-based models.

Recommended citation: R. Wang, T. Chen, P. Yao, S. Liu, I. Rajapakse, and A. O. Hero. Ask: Adversarial soft k-nearest neighbor attack and defense. IEEE Access, 10:103074–103088, 2022. https://ieeexplore.ieee.org/document/9902964

Immuno-mimetic Deep Neural Networks (Immuno-Net)

Published in The 2021 ICML Workshop on Computational Biology, 2021

In this paper we introduce a different type of biomimetic model, one that borrows concepts from the immune system, for designing robust deep neural networks.

Recommended citation: R. Wang, T. Chen, S. Lindsly, C. Stansbury, I. Rajapakse, and A. Hero. Immuno-mimetic deep neural networks (immuno-net). arXiv preprint arXiv:2107.02842, 2021. https://icml-compbio.github.io/2021/papers/WCBICML2021_paper_34.pdf