Follow
Amartya Sanyal
Amartya Sanyal
Postdoctoral Fellow, ETH Zürich
Verified email at ai.ethz.ch - Homepage
Title
Cited by
Cited by
Year
Calibrating Deep Neural Networks using Focal Loss
J Mukhoti, V Kulharia, A Sanyal, S Golodetz, PHS Torr, PK Dokania
Advances in Neural Information Processing Systems (NeurIPS), December 2020, 2020
1722020
TAPAS: Tricks to Accelerate (encrypted) Prediction As a Service
A Sanyal, MJ Kusner, A Gascón, V Kanade
International Conference on Machine Learning 80, 4497--4506, 2018
1052018
Progressive skeletonization: Trimming more fat from a network at initialization
P de Jorge, A Sanyal, HS Behl, PHS Torr, G Rogez, PK Dokania
International Conference on Learning Representations, ICLR 2021, 2021
422021
Stable Rank Normalization for Improved Generalization in Neural Networks and GANs
A Sanyal, PHS Torr, PK Dokania
International Conference on Learning Representations, (Spotlight Paper) ICLR …, 2019
362019
How benign is benign overfitting?
A Sanyal, PK Dokania, V Kanade, PHS Torr
International Conference on Learning Representations, (Spotlight Paper) ICLR …, 2021
352021
Robustness via Deep Low-Rank Representations
A Sanyal, V Kanade, PHS Torr, PK Dokania
arXiv preprint arXiv:1804.07090, 2018
29*2018
Optimizing non-decomposable measures with deep networks
A Sanyal, P Kumar, P Kar, S Chawla, F Sebastiani
Machine Learning 107, 1597-1620, 2018
262018
Multiscale sequence modeling with a learned dictionary
B van Merriënboer, A Sanyal, H Larochelle, Y Bengio
ICML 2017 Workshop on Machine Learning in Speech and Language Processing, 2017
102017
How unfair is private learning ?
A Sanyal, Y Hu, F Yang
Conference on Uncertainty in Artificial Intelligence (Oral Paper) UAI, 2022
52022
Make Some Noise: Reliable and Efficient Single-Step Adversarial Training
P de Jorge, A Bibi, R Volpi, A Sanyal, PHS Torr, G Rogez, PK Dokania
Advances in Neural Information Processing Systems (NeurlPS), 2022, 2022
32022
How robust are pre-trained models to distribution shift?
Y Shi, I Daunhawer, JE Vogt, PHS Torr, A Sanyal
International Conference on Learning Representations (ICLR) 2023, 2022
22022
Catastrophic overfitting is a bug but also a feature
G Ortiz-Jiménez, P de Jorge, A Sanyal, A Bibi, PK Dokania, P Frossard, ...
ICML 2022 Workshop on New Frontiers in Adversarial Machine Learning, 2022
12022
A Hybrid Deep Architecture for Face Recognition in Real-Life Scenario
A Sanyal, U Bhattacharya, SK Parui
Computer Vision, Graphics, and Image Processing: ICVGIP 2016 Satellite …, 2017
12017
Certified defences hurt generalisation
P De Bartolomeis, J Clarysse, F Yang, A Sanyal
I Can't Believe It's Not Better Workshop: Understanding Deep Learning …, 2022
2022
Do you pay for Privacy in Online learning?
A Sanyal, G Ramponi
Conference on Learning Theory, 5633-5637, 2022
2022
A law of adversarial risk, interpolation, and label noise
D Paleka, A Sanyal
International Conference on Learning Representations (ICLR) 2023, 2022
2022
Identifying and exploiting structures for reliable deep learning
A Sanyal
arXiv preprint arXiv:2108.07083, 2021
2021
The system can't perform the operation now. Try again later.
Articles 1–17