Learning Confident Classifiers in the Presence of Label Noise

no code implementations • 2 Jan 2023 • Asma Ahmed Hashmi, Aigerim Zhumabayeva, Nikita Kotelevskii, Artem Agafonov, Mohammad Yaqub, Maxim Panov, Martin Takáč

We evaluate the proposed method on a series of classification tasks such as noisy versions of MNIST, CIFAR-10, Fashion-MNIST datasets as well as CIFAR-10N, which is real-world dataset with noisy human annotations.

Image Segmentation Medical Image Segmentation +2

FLECS-CGD: A Federated Learning Second-Order Framework via Compression and Sketching with Compressed Gradient Differences

no code implementations • 18 Oct 2022 • Artem Agafonov, Brahim Erraji, Martin Takáč

In the recent paper FLECS (Agafonov et al, FLECS: A Federated Learning Second-Order Framework via Compression and Sketching), the second-order framework FLECS was proposed for the Federated Learning problem.

Federated Learning Stochastic Optimization

Inexact Tensor Methods and Their Application to Stochastic Convex Optimization

no code implementations • 31 Dec 2020 • Artem Agafonov, Dmitry Kamzolov, Pavel Dvurechensky, Alexander Gasnikov

We propose general non-accelerated and accelerated tensor methods under inexact information on the derivatives of the objective, analyze their convergence rate.

Optimization and Control