Machine Learning Researcher & PhD Candidate at University of Mannheim
Mannheim
Joined January 2016
- Tweets65
- Following85
- Followers58
- Likes186
Pinned Tweet
🚀Exciting news! Our paper "Mitigating Information Loss in Tree-Based Reinforcement Learning via Direct Optimization" got accepted at #ICLR2025 ! 🎉🌳🤖
We introduce SYMPOL, a method that directly optimizes hard, axis-aligned decision trees with policy gradients! 🔥
🔽 Thread 👇
Sascha Marton retweeted
What’s in the Bottle? A Survey and Roadmap of Concept Bottleneck Models
CBMs are a rapidly growing direction in interpretable-by-design machine learning. However, the field has become increasingly fragmented.
Preprint Link:
researchgate.net/publication…
Sascha Marton retweeted
We took a quick look at the new PaperDecision results for ICLR 2026 and asked a simple question: do we really need LLMs for this task?
We did the same but with tabular data:
s-marton.github.io/TabICLR/
#ICLR2026
Sascha Marton retweeted
Super cool. We have built a similar tool, but based on tabular data. Let's see which of the two works best ;)
s-marton.github.io/TabICLR/
Sascha Marton retweeted
🚀 Preprint out: Concepts in Motion: Temporal Bottlenecks for Interpretable Video Classification
📄 Preprint: arxiv.org/pdf/2509.20899
💻 Code: github.com/patrick-knab/MoTI…
🌟 Spotlight at #ICLR2025!
Step by our poster #425 this Thu (Apr 24), 10:00–12:30 SGT — we’d love to chat if you’re around! 🇸🇬
📍 “Mitigating Information Loss in Tree-Based RL via Direct Optimization”
With SYMPOL, we directly optimize axis-aligned DTs using policy gradients! 🌳
Sascha Marton retweeted
Which LIME should I trust? Our new paper, accepted at XAI 2025 in Istanbul, answers this question!
LIME is a go-to for post-hoc explanations—but with so many variants, which one should you use? 🧵👇
📝 Paper: arxiv.org/abs/2503.24365v1
#XAI2025 #XAI #ML
Excited to see our paper on ReMeDe Trees featured! 🚀
We propose a novel recurrent decision tree architecture with an internal memory to capture dependencies in sequential data. 🌳🧠
Efficient, interpretable, and optimized via gradient descent.
Thanks @gm8xx8 for the shoutout! 🙌
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.
Sascha Marton retweeted
[LG] Decision Trees That Remember: Gradient-Based Learning of Recurrent Decision Trees with Memory
S Marton, M Schneider [University of Mannheim & Boehringer Ingelheim] (2025)
arxiv.org/abs/2502.04052
Want to dive deeper? 🤓
📄 Paper: openreview.net/forum?id=qpXc…
💻 Code: github.com/s-marton/SYMPOL
Integration with libraries like SB3 coming soon—follow for updates! 🚀
Excited to present SYMPOL @iclr_conf! See you in Singapore 🇸🇬🏝️
Let's discuss interpretable RL, symbolic policies & decision trees! Looking forward to meeting everyone there! 💬🔥
#ICLR2025 #ReinforcementLearning #SymbolicRL #InterpretableAI #DecisionTrees
Sascha Marton retweeted
Why do LLMs trained on over 90% English text perform so well in non-English languages?
We find that they learn to share highly abstract grammatical concept representations, even across unrelated languages!
New paper w/ @wendlerch and @amuuueller
Sascha Marton retweeted
PyTabKit 1.1 is out!
- Includes TabM and provides a scikit-learn interface
- some baseline NN parameter names are renamed (removed double-underscores)
- other small changes, see the readme.
