Suraj Srinivas
Suraj Srinivas
Postdoctoral Research Fellow at Harvard University
Verified email at - Homepage
Cited by
Cited by
Data-free parameter pruning for deep neural networks
S Srinivas, RV Babu
British Machine Vision Conference (BMVC), 2015
A taxonomy of deep convolutional neural nets for computer vision
S Srinivas, RK Sarvadevabhatla, KR Mopuri, N Prabhu, SSS Kruthiventi, ...
Frontiers in Robotics and AI 2, 36, 2016
Full-gradient representation for neural network visualization
S Srinivas, F Fleuret
Neural Information Processing Systems (NeurIPS), 2019
Training sparse neural networks
S Srinivas, A Subramanya, R Venkatesh Babu
CVPR Embedded Vision Workshop, 138-145, 2017
Knowledge Transfer with Jacobian Matching
S Srinivas, F Fleuret
International Conference on Machine Learning (ICML), 2018
Which explanation should i choose? a function approximation perspective to characterizing post hoc explanations
T Han, S Srinivas, H Lakkaraju
Neural Information Processing Systems (NeurIPS), 2022
Estimating Confidence for Deep Neural Networks through Density modeling
A Subramanya, S Srinivas, RV Babu
2018 International Conference on Signal Processing and Communications (SPCOMá…, 2018
Certifying llm safety against adversarial prompting
A Kumar, C Agarwal, S Srinivas, S Feizi, H Lakkaraju
arXiv preprint arXiv:2309.02705, 2023
Learning the architecture of deep neural networks
S Srinivas, RV Babu
British Machine Vision Conference (BMVC), 2016
Generalized dropout
S Srinivas, RV Babu
Tech Report, 2016
Rethinking the Role of Gradient Based Attribution Methods for Model Interpretability
S Srinivas, F Fleuret
International Conference on Learning Representations (ICLR), 2021
Efficient Training of Low-Curvature Neural Networks
S Srinivas, K Matoba, H Lakkaraju, F Fleuret
Neural Information Processing Systems (NeurIPS), 2022
Data-efficient structured pruning via submodular optimization
M El Halabi, S Srinivas, S Lacoste-Julien
Neural Information Processing Systems (NeurIPS), 2022
Cyclical Pruning for Sparse Neural Networks
S Srinivas, A Kuzmin, M Nagel, M van Baalen, A Skliar, T Blankevoort
CVPR Workshop on Efficient Deep Learning for Computer Vision, 2022
Which models have perceptually-aligned gradients? an explanation via off-manifold robustness
S Srinivas, S Bordt, H Lakkaraju
Advances in neural information processing systems 36, 2024
Compensating for large in-plane rotations in natural images
L Boominathan, S Srinivas, RV Babu
Indian Conference on Computer Vision, Graphics and Image Processing (ICVGIP), 2016
Discriminative Feature Attributions: Bridging Post Hoc Explainability and Inherent Interpretability
U Bhalla, S Srinivas, H Lakkaraju
Advances in Neural Information Processing Systems 36, 2024
On minimizing the impact of dataset shifts on actionable explanations
AP Meyer, D Ley, S Srinivas, H Lakkaraju
Uncertainty in Artificial Intelligence, 1434-1444, 2023
Interpreting CLIP with Sparse Linear Concept Embeddings (SpLiCE)
U Bhalla, A Oesterling, S Srinivas, FP Calmon, H Lakkaraju
arXiv preprint arXiv:2402.10376, 2024
Consistent explanations in the face of model indeterminacy via ensembling
D Ley, L Tang, M Nazari, H Lin, S Srinivas, H Lakkaraju
arXiv preprint arXiv:2306.06193, 2023
The system can't perform the operation now. Try again later.
Articles 1–20