Heejune Sheen

Orcid: 0000-0003-3286-7859

According to our database1, Heejune Sheen authored at least 7 papers between 2020 and 2024.

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

Timeline

2020
2021
2022
2023
2024
0
1
2
3
4
5
2
2
1
2

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

On csauthors.net:

Bibliography

2024
Implicit Regularization of Gradient Flow on One-Layer Softmax Attention.
CoRR, 2024

Training Dynamics of Multi-Head Softmax Attention for In-Context Learning: Emergence, Convergence, and Optimality.
CoRR, 2024

Unveiling Induction Heads: Provable Training Dynamics and Feature Learning in Transformers.
Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024

Training Dynamics of Multi-Head Softmax Attention for In-Context Learning: Emergence, Convergence, and Optimality (extended abstract).
Proceedings of the Thirty Seventh Annual Conference on Learning Theory, June 30, 2024

2022
Tensor Kernel Recovery for Discrete Spatio-Temporal Hawkes Processes.
IEEE Trans. Signal Process., 2022

Exploiting aggregate sparsity in second-order cone relaxations for quadratic constrained quadratic programming problems.
Optim. Methods Softw., 2022

2020
Tensor Kernel Recovery for Spatio-Temporal Hawkes Processes.
CoRR, 2020


  Loading...