Fingerprint
Dive into the research topics where Inbar Seroussi is active. These topic labels come from the works of this person. Together they form a unique fingerprint.
- 1 Similar Profiles
Collaborations and top research areas from the last five years
Recent external collaboration on country/territory level. Dive into details by clicking on the dots or
-
From Kernels to Features: A Multi-Scale Adaptive Theory of Feature Learning
Rubin, N., Fischer, K., Lindner, J., Seroussi, I., Ringel, Z., Krämer, M. & Helias, M., 2025, In: Proceedings of Machine Learning Research. 267, p. 52225-52257 33 p.Research output: Contribution to journal › Conference article › peer-review
1 Scopus citations -
GROKKING AS A FIRST ORDER PHASE TRANSITION IN TWO LAYER NETWORKS
Rubin, N., Seroussi, I. & Ringel, Z., 2024.Research output: Contribution to conference › Paper › peer-review
11 Scopus citations -
Hitting the High-dimensional notes: an ODE for SGD learning dynamics on GLMs and multi-index models
Collins-Woodfin, E., Paquette, C., Paquette, E. & Seroussi, I., 1 Dec 2024, In: Information and Inference. 13, 4, iaae028.Research output: Contribution to journal › Article › peer-review
Open Access5 Scopus citations -
Spectral-bias and kernel-task alignment in physically informed neural networks
Seroussi, I., Miron, A. & Ringel, Z., 1 Sep 2024, In: Machine Learning: Science and Technology. 5, 3, 035048.Research output: Contribution to journal › Article › peer-review
Open Access2 Scopus citations -
The High Line: Exact Risk and Learning Rate Curves of Stochastic Adaptive Learning Rate Algorithms
Collins-Woodfin, E., Seroussi, I., Malaxechebarría, B. G., Mackenzie, A. W., Paquette, E. & Paquette, C., 2024, In: Advances in Neural Information Processing Systems. 37Research output: Contribution to journal › Conference article › peer-review