# Christopher Beckham

> Christopher Beckham is a machine learning researcher with more than a decade of experience across classical methods, deep learning, and generative modeling. His work emphasises theoretical clarity paired with practical execution, especially in domains where standard assumptions about data or ground truth break down. He has a strong interest in evaluation, metric design, and reproducibility, and prioritises understanding model behavior over headline performance alone. He has led and contributed to end-to-end ML systems in industrial settings. He is particularly drawn to problems that reward rigour, skepticism, and careful empirical validation.

## Key pages

- [Home](https://beckham.nz/): biography, positions, and post index
- [CV](https://beckham.nz/cv/): full employment and education history
- [Blog](https://beckham.nz/blog): technical writing on machine learning topics

## Education

- PhD, Polytechnique Montréal (2019–2024)
- MASc, Polytechnique Montréal (2016–2017)
- BCMS(Hons), University of Waikato (2012–2015)

## Research interests

- Model-based optimisation (generative models for inverse problems)
- Generative models
- Reproducibility in ML
- ML engineering and experimental design

## External profiles

- [Google Scholar](https://scholar.google.com/citations?user=PpD3zNYAAAAJ): publications
- [GitHub](https://github.com/christopher-beckham): code and open-source work