Scholar
Michael E. Sander
Google Scholar ID: COqAqcMAAAAJ
Google DeepMind
Citations & Impact
Citations
897
H-index
8
i10-index
8
Publications
13
Co-authors
15
list available
Publications
Resume (English only)
Academic Achievements
- Joint Learning of Energy-based Models and their Partition Function, ICML 2025
- Loss Functions and Operators Generated by f-Divergences, ICML 2025
- Towards Understanding the Universality of Transformers for Next-Token Prediction, ICLR 2025
- PhD Manuscript: Deeper Learning: Residual Networks, Neural Differential Equations and Transformers, in Theory and Action
- How do Transformers perform In-Context Autoregressive Learning?, ICML 2024
- Implicit regularization of deep residual networks towards neural ODEs, ICLR 2024 (Spotlight)
- Fast, Differentiable and Sparse Top-k: a Convex Analysis Perspective, ICML 2023
- Do Residual Neural Networks discretize Neural Ordinary Differential Equations?, NeurIPS 2022
- Vision Transformers provably learn spatial structure, NeurIPS 2022
- Sinkformers: Transformers with Doubly Stochastic Attention, AISTATS 2022
- Momentum Residual Neural Networks, ICML 2021
