Machine learning research

Hey, I'm Sascha.

I'm a Senior Machine Learning Engineer at NVIDIA, where my research focuses on tabular foundation models.

I'm part of the team behind Kumo Tabular and the open-source Structured Data Models library. I've always wanted to do research with impact. Research that people can use and build on. I enjoy working on ambitious ideas with people who are just as excited about them as I am. With tabular foundation models, there's still so much to figure out, and the chance to help shape what comes next is incredibly exciting.

My interest in tabular data began during my PhD at the University of Mannheim, where I developed methods for training decision trees and ensembles with gradient descent. I later joined TU Clausthal, where my research broadened to include tabular foundation models.

Tabular foundation modelsDeep learning for tabular dataDecision tree ensembles

Selected research & software

Research you can build on.

All publications ↗
AAAI 2024 (Oral)

GradTree

GradTree: Learning Axis-Aligned Decision Trees with Gradient Descent

A Python implementation for training hard, axis-aligned decision trees with gradient descent. The package includes preprocessing when categorical feature indices are supplied, a minimal example notebook, and code for reproducing the paper’s experiments.

ICLR 2025 (Spotlight)

SYMPOL

Mitigating Information Loss in Tree-Based Reinforcement Learning via Direct Optimization

Code for directly learning interpretable tree policies with PPO. The repository includes a decision-tree actor and neural-network critic, scripts for Gymnasium and vectorized gymnax environments, and experiment commands and hyperparameter configurations used in the paper.

Beyond research

Teaching & mentoring.

Besides research, I really enjoyed giving lectures, supervising students, and co-supervising PhD projects during my time in academia. Something I hadn't expected to enjoy quite that much. The research was fun, but the people made it special.

View my CV ↗

Get in touch.

For questions about my research or open-source projects, reach me at sascha.marton@gmail.com.