Inbar Seroussi

Orcid: 0000-0001-5209-5839

According to our database1, Inbar Seroussi authored at least 8 papers between 2021 and 2024.

Collaborative distances:
  • Dijkstra number2 of five.
  • Erdős number3 of four.

Timeline

2021
2022
2023
2024
0
1
2
3
4
1
3
1
1
2

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

On csauthors.net:

Bibliography

2024
Spectral-bias and kernel-task alignment in physically informed neural networks.
Mach. Learn. Sci. Technol., 2024

The High Line: Exact Risk and Learning Rate Curves of Stochastic Adaptive Learning Rate Algorithms.
Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024

Grokking as a First Order Phase Transition in Two Layer Networks.
Proceedings of the Twelfth International Conference on Learning Representations, 2024

2023
Droplets of Good Representations: Grokking as a First Order Phase Transition in Two Layer Networks.
CoRR, 2023

Hitting the High-Dimensional Notes: An ODE for SGD learning dynamics on GLMs and multi-index models.
CoRR, 2023

Speed Limits for Deep Learning.
CoRR, 2023

2022
Lower Bounds on the Generalization Error of Nonlinear Learning Models.
IEEE Trans. Inf. Theory, 2022

2021
Separation of scales and a thermodynamic description of feature learning in some CNNs.
CoRR, 2021


  Loading...