Sascha Marton
65 posts
@__smarton
Machine Learning Researcher & PhD Candidate at University of Mannheim
Decision Trees That Remember: Gradient-Based Learning of Recurrent Decision Trees with Memory paper: arxiv.org/abs/2502.04052 ReMeDe Trees is a decision tree architecture designed to handle sequential data by integrating an internal memory mechanism. It learns long-term dependencies through hard, axis-aligned decision rules optimized via gradient descent. Synthetic benchmark tests demonstrate its effectiveness in capturing temporal patterns.
What DL architecture to try on tabular data? TabM is our new answer. TabM is leading on the benchmarks, while being simple, practical, and scalable to large datasets. 🧵In tabular ML, there is one thing that most people trust... 1/10
