← Search

Michael Hefenbrock

2 accepted papers

2025

Learning in Compact Spaces with Approximately Normalized Transformer

NeurIPS 2025poster

The successful training of deep neural networks requires addressing challenges such as overfitting, numerical instabilities leading to divergence, and increasing variance in the residual stream. A common solution is to apply regularization and normalization techniques that usually require tuning add…

Cited by 0SourceScholar
2024

Improving Deep Learning Optimization through Constrained Parameter Regularization

NeurIPS 2024poster

Regularization is a critical component in deep learning. The most commonly used approach, weight decay, applies a constant penalty coefficient uniformly across all parameters. This may be overly restrictive for some parameters, while insufficient for others. To address this, we present Constrained P…