Mariia Seleznova

According to our database, Mariia Seleznova authored at least 7 papers between 2018 and 2025.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2025

Revisiting Glorot Initialization for Long-Range Linear Recurrences.

Noga Bar, Mariia Seleznova, Yotam Alexander, Gitta Kutyniok, Raja Giryes

CoRR, May, 2025

GradPCA: Leveraging NTK Alignment for Reliable Out-of-Distribution Detection.

Mariia Seleznova, Hung-Hsu Chou, Claudio Mayrink Verdun, Gitta Kutyniok

CoRR, May, 2025

2023

Neural (Tangent Kernel) Collapse.

Mariia Seleznova, Dana Weitzner, Raja Giryes, Gitta Kutyniok, Hung-Hsu Chou

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

2022

Neural Tangent Kernel Beyond the Infinite-Width Limit: Effects of Depth and Initialization.

Mariia Seleznova, Gitta Kutyniok

Proceedings of the International Conference on Machine Learning, 2022

2021

Analyzing Finite Neural Networks: Can We Trust Neural Tangent Kernel Theory?

Mariia Seleznova, Gitta Kutyniok

Proceedings of the Mathematical and Scientific Machine Learning, 2021

2020

Guided Exploration of User Groups.

Mariia Seleznova, Behrooz Omidvar-Tehrani, Sihem Amer-Yahia, Eric Simon

Proc. VLDB Endow., 2020

2018

Towards Large-Scale Exploratory Search over Heterogeneous Sources.

Mariia Seleznova, Anton Belyy, Aleksei Sholokhov

CoRR, 2018