Follow
Alexandra Peste
Alexandra Peste
Verified email at ist.ac.at
Title
Cited by
Cited by
Year
Sparsity in deep learning: Pruning and growth for efficient inference and training in neural networks
T Hoefler, D Alistarh, T Ben-Nun, N Dryden, A Peste
The Journal of Machine Learning Research 22 (1), 10882-11005, 2021
5802021
AC/DC: Alternating Compressed/DeCompressed Training of Deep Neural Networks
A Peste, E Iofinova, A Vladu, D Alistarh
Advances in Neural Information Processing Systems 34, 8557-8570, 2021
522021
How Well Do Sparse ImageNet Models Transfer?
E Iofinova, A Peste, M Kurtz, D Alistarh
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2022
312022
SSSE: Efficiently Erasing Samples from Trained Machine Learning Models
A Peste, D Alistarh, CH Lampert
arXiv preprint arXiv:2107.03860, 2021
172021
CrAM: A Compression-Aware Minimizer
A Peste, A Vladu, E Kurtic, CH Lampert, D Alistarh
ICLR 2023, 2022
82022
Bias in Pruned Vision Models: In-Depth Analysis and Countermeasures
E Iofinova, A Peste, D Alistarh
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2023
42023
Accurate Neural Network Pruning Requires Rethinking Sparse Optimization
D Kuznedelev, E Kurtic, E Iofinova, E Frantar, A Peste, D Alistarh
arXiv preprint arXiv:2308.02060, 2023
32023
An Explanatory Analysis of the Geometry of Latent Variables Learned by Variational Auto-Encoders
A Peste, L Malagò, S Sârbu
NIPS, Bayesian Deep Learning Workshop, 2017
22017
Learning in Variational Autoencoders with Kullback-Leibler and Renyi Integral Bounds
S Sârbu, R Volpi, A Peşte, L Malagò
arXiv preprint arXiv:1807.01889, 2018
12018
ELSA: Partial Weight Freezing for Overhead-Free Sparse Network Deployment
P Halvachi, A Peste, D Alistarh, CH Lampert
arXiv preprint arXiv:2312.06872, 2023
2023
Knowledge Distillation Performs Partial Variance Reduction
M Safaryan, A Peste, D Alistarh
Advances in Neural Information Processing Systems (NeurIPS) 2023, 2023
2023
Efficiency and generalization of sparse neural networks
EA Peste
2023
The system can't perform the operation now. Try again later.
Articles 1–12