Hrayr Harutyunyan
Hrayr Harutyunyan
Research Scientist, Google Research
Verified email at - Homepage
Cited by
Cited by
Multitask learning and benchmarking with clinical time series data
H Harutyunyan, H Khachatrian, DC Kale, G Ver Steeg, A Galstyan
Scientific data 6 (1), 96, 2019
Mixhop: Higher-order graph convolutional architectures via sparsified neighborhood mixing
S Abu-El-Haija, B Perozzi, A Kapoor, N Alipourfard, K Lerman, ...
international conference on machine learning, 21-29, 2019
Improving generalization by controlling label-noise information in neural network weights
H Harutyunyan, K Reing, G Ver Steeg, A Galstyan
International Conference on Machine Learning, 4071-4081, 2020
Information-theoretic generalization bounds for black-box learning algorithms
H Harutyunyan, M Raginsky, G Ver Steeg, A Galstyan
Advances in Neural Information Processing Systems 34, 24670-24682, 2021
Estimating informativeness of samples with Smooth Unique Information
H Harutyunyan, A Achille, G Paolini, O Majumder, A Ravichandran, ...
International Conference on Learning Representations, 2021
Failure modes of domain generalization algorithms
T Galstyan, H Harutyunyan, H Khachatrian, GV Steeg, A Galstyan
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2022
Fast structure learning with modular regularization
G Ver Steeg, H Harutyunyan, D Moyer, A Galstyan
Advances in Neural Information Processing Systems 32, 2019
Supervision complexity and its role in knowledge distillation
H Harutyunyan, AS Rawat, AK Menon, S Kim, S Kumar
arXiv preprint arXiv:2301.12245, 2023
A meta-learning approach to predicting performance and data requirements
A Jain, G Swaminathan, P Favaro, H Yang, A Ravichandran, ...
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2023
Disentangled representations via synergy minimization
G Ver Steeg, R Brekelmans, H Harutyunyan, A Galstyan
2017 55th Annual Allerton Conference on Communication, Control, and …, 2017
Formal limitations of sample-wise information-theoretic generalization bounds
H Harutyunyan, G Ver Steeg, A Galstyan
2022 IEEE Information Theory Workshop (ITW), 440-445, 2022
Efficient covariance estimation from temporal data
H Harutyunyan, D Moyer, H Khachatrian, GV Steeg, A Galstyan
arXiv preprint arXiv:1905.13276, 2019
Identifying geopolitical event precursors using attention-based LSTMs
KSMT Hossain, H Harutyunyan, Y Ning, B Kennedy, N Ramakrishnan, ...
Frontiers in Artificial Intelligence 5, 893875, 2022
Identifying and disentangling spurious features in pretrained image representations
R Darbinyan, H Harutyunyan, AH Markosyan, H Khachatrian
arXiv preprint arXiv:2306.12673, 2023
On information captured by neural networks: connections with memorization and generalization
H Harutyunyan
arXiv preprint arXiv:2306.15918, 2023
The system can't perform the operation now. Try again later.
Articles 1–15