Volgen
Anastasia Koloskova
Anastasia Koloskova
PhD student, EPFL
Geverifieerd e-mailadres voor epfl.ch
Titel
Geciteerd door
Geciteerd door
Jaar
Decentralized stochastic optimization and gossip algorithms with compressed communication
A Koloskova, SU Stich, M Jaggi
ICML 2019 - Proceedings of the 36th International Conference on Machine Learning, 2019
3222019
A unified theory of decentralized sgd with changing topology and local updates
A Koloskova, N Loizou, S Boreiri, M Jaggi, SU Stich
ICML 2020, 2020
2092020
Decentralized deep learning with arbitrary communication compression
A Koloskova, T Lin, SU Stich, M Jaggi
ICLR 2020, 2019
1422019
A linearly convergent algorithm for decentralized optimization: Sending less bits for free!
D Kovalev, A Koloskova, M Jaggi, P Richtarik, S Stich
International Conference on Artificial Intelligence and Statistics, 4087-4095, 2021
412021
Consensus control for decentralized deep learning
L Kong, T Lin, A Koloskova, M Jaggi, SU Stich
ICML 2021, 2021
302021
An improved analysis of gradient tracking for decentralized machine learning
A Koloskova, T Lin, SU Stich
Advances in Neural Information Processing Systems 34, 11422-11435, 2021
202021
Decentralized local stochastic extra-gradient for variational inequalities
A Beznosikov, P Dvurechensky, A Koloskova, V Samokhin, SU Stich, ...
arXiv preprint arXiv:2106.08315, 2021
182021
Efficient greedy coordinate descent for composite problems
SP Karimireddy, A Koloskova, SU Stich, M Jaggi
The 22nd International Conference on Artificial Intelligence and Statistics …, 2019
182019
Relaysum for decentralized deep learning on heterogeneous data
T Vogels, L He, A Koloskova, SP Karimireddy, T Lin, SU Stich, M Jaggi
Advances in Neural Information Processing Systems 34, 28004-28015, 2021
172021
Sharper convergence guarantees for asynchronous sgd for distributed and federated learning
A Koloskova, SU Stich, M Jaggi
arXiv preprint arXiv:2206.08307, 2022
52022
Data-heterogeneity-aware Mixing for Decentralized Learning
Y Dandi, A Koloskova, M Jaggi, SU Stich
arXiv preprint arXiv:2204.06477, 2022
22022
Het systeem kan de bewerking nu niet uitvoeren. Probeer het later opnieuw.
Artikelen 1–11