Probabilistic Modeling and Inference
Probabilistic Modeling, Bayesian Inference, Uncertainty Estimation
Dr. Shinichi Nakajima leads the Independent Research Group Probabilistic Modeling and Inference. His aim is to develop novel probabilistic models and inference methods for multimodal, heterogeneous, and complex structured data analysis. In particular he wants to provide machine learning tools that can incorporate multiple aspects of data samples observed under different circumstances, in efficient and theoretically grounded ways. This includes:
- Developing novel probabilistic models with efficient inference methods
- Exploring novel applications of probabilistic models
- Establishing uncertainty estimation methods for deep probabilistic models
Solution Simplex Clustering for Heterogeneous Federated Learning
Detecting and Mitigating Mode-Collapse for Flow-based Sampling of Lattice Field Theories
Physics-Informed Bayesian Optimization of Variational Quantum Circuits
Tackling Data Heterogeneity in Federated Learning
A persistent challenge in Federated Learning (FL) lies in handling statistical heterogeneity—namely, if the clients’ distributions are different from each other. Shinichi Nakajima, BIFOLD research Grouplead and his team propose FLOCO (Federated Learning over Connected Modes), to tackle those issues.
Photo recap: BIFOLD New Year's reception
At its New Year's reception BIFOLD welcomed a series of distinguished guests and friends from Berlin's AI community.
Photo recap: All Hands Meeting 2023
On October 9 and 10, 2023, BIFOLD welcomed the other Geman AI centers (ScaDS.AI Dresden/Leipzig, Lamarr Institute, Tübingen AI Center, MCML, and the DFKI) in Berlin. The annual meeting featured guests, partners, visitors, and researchers from all over Germany.
Research Junior Group Lead
Doctoral Researcher
Doctoral Researcher
Doctoral Researcher
Doctoral Researcher
Doctoral Researcher