Author

Marianna Pensky

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#machine learning Preprint Aug 2026

Component Type, Not Reconstruction Error, Predicts Attention Quantization Sensitivity

Many post-training quantization (PTQ) methods use layer-wise reconstruction, second-order proxy objectives, or activation-aware transformations to reduce quantization-induced error. Whether that error signal predicts the downstream functional impact of quantizing an individual attention projection has not been directly...

Kasun Dewage, Marianna Pensky, Suranadi De Silva · 0 citations

#artificial intelligence Preprint Aug 2026

Magnitude Profile Pruning: Calibration-Free Structured Attention Head Removal for Transformer Compression

Structured pruning of attention heads provides a hardware-friendly way to compress Transformer language models. However, existing methods for measuring head-level importance require calibration data, gradient computation, or Hessian estimation. These requirements add extra overhead and make the methods depend on the da...

Kasun Dewage, Marianna Pensky, Heranga K. Rathnasekara et al. · 0 citations