Recent
Publications
|
- Somnath Dake, S Senthamarai Kannan, K V Subrahmanyam
Torus Quotients of Flag Varieties - a Computational Approach Based on Lattice Basis, 2022, (submitted)
- Bharat Adsul, Milind Sohoni, K V Subrahmanyam
Geometric Complexity Theory- Lie Algerbaic Methods for Projective Limits of Stable Points, 2022
- Sandesh Kamath, Amit Deshpande, K V Subrahmanyam, Vineeth Balasubramanian
Universalization of Any Adversarial Attack using Very Few Test Examples , (Accepted) CODS-COMAD, Bangalore, 2021
- Sandesh Kamath, Amit Deshpande, K V Subrahmanyam, Vineeth Balasubramanian
Can we have it all? On the trade-off between spatial and adversarial robustness of neural networks , (Accepted), NeurIPS 2021
- Sandesh Kamath, Amit Deshpande, K V Subrahmanyam
Invariance versus Robustness of Neural Networks, arxiv.org/abs/2002.11318, 2020
- Sarjick Bakshi, Senthamarai Kannan, K V Subrahmanyam
Torus quotients of Richardson varieties in the Grassmannian,; Communications in
Algebra, 2019;
- Sarjick Bakshi, Senthamarai Kannan, K V Subrahmanyam
Smooth torus quotients of Schubert varieties in the Grassmannian (preprint under review)
- Muthuvel Murugan, K V Subrahmanyam
SO(2) equivariance in neural networks using Fourier nonlinearity, 30th British Machine Vision Conference, 2019, Cardiff;
- Sandesh Kamath, Amit Deshpande, K V Subrahmanyam
On adversarial robustness of small versus large batch training,ICML 2019 Workshop " On Understanding and Improving Generalization in Deep Learning", Long Beach, California, 2019;
- Sandesh Kamath, Amit Deshpande, K V Subrahmanyam
Better generalization with adaptive adversarial training,ICML 2019 Workshop " On Understanding and Improving Generalization in Deep Learning",Long Beach, California, 2019;
|
