1k citations · 2.1k across the 17 of their papers we have counts for
7 papers · 1 filter
Learning Commute-Time-Preserving World Models for Planning
Michael Hauri, Peter Buttaroni, Fabian A. Mikulasch +1
World models allow agents to plan in latent space by choosing a sequence of actions that most reduces the distance to a given goal state. Thus, planning can benefit from latent rep…
Predictive Self-Supervised Learning Provably Identifies Stochastic Signals under Nuisance
Fabian A. Mikulasch, Friedemann Zenke
Self-supervised learning (SSL) by predicting in latent space, without generating the input data itself, learns highly abstract, useful representations. Intuitively, this success is…
Understanding Self-Supervised Learning via Latent Distribution Matching
Fabian A Mikulasch, Friedemann Zenke
Self-supervised learning (SSL) excels at finding general-purpose latent representations from complex data, yet lacks a unifying theoretical framework that explains the diverse exis…
Dreamer-CDP: Improving Reconstruction-free World Models Via Continuous Deterministic Representation Prediction
Michael Hauri, Friedemann Zenke
Model-based reinforcement learning (MBRL) agents operating in high-dimensional observation spaces, such as Dreamer, rely on learning abstract representations for effective planning…
Implicit variance regularization in non-contrastive SSL
Manu Srinath Halvagal, Axel Laborieux, Friedemann Zenke
Non-contrastive SSL methods like BYOL and SimSiam rely on asymmetric predictor networks to avoid representational collapse without negative samples. Yet, how predictor networks fac…
Finding trainable sparse networks through Neural Tangent Transfer
Tianlin Liu, Friedemann Zenke
Deep neural networks have dramatically transformed machine learning, but their memory and energy demands are substantial. The requirements of real biological neural networks are ra…
Continual Learning Through Synaptic Intelligence
Friedemann Zenke, Ben Poole, Surya Ganguli
While deep learning has led to remarkable advances across diverse applications, it struggles in domains where the data distribution changes over the course of learning. In stark co…