3 papers
cs.LG2025
Revisiting Knowledge Distillation: The Hidden Role of Dataset Size
Giulia Lanzillotta, Felix Sarnthein, Gil Kur +2
The concept of knowledge distillation (KD) describes the training of a student model from a teacher model and is a widely adopted technique in deep learning. However, it is still n…
cs.LG2025
Fixed-Point RNNs: Interpolating from Diagonal to Dense
Sajad Movahedi, Felix Sarnthein, Nicola Muca Cirone +1
Linear recurrent neural networks (RNNs) and state-space models (SSMs) such as Mamba have become promising alternatives to softmax-attention as sequence mixing layers in Transformer…
cs.LG2023
Random Teachers are Good Teachers
Felix Sarnthein, Gregor Bachmann, Sotiris Anagnostidis +1
In this work, we investigate the implicit regularization induced by teacher-student learning dynamics in self-distillation. To isolate its effect, we describe a simple experiment w…