Highlights

NumGM postdoctoral position — application deadline passed

Byadmin 20 August 20269 October 2026

Application deadline passed: the stated deadline was 11 September 2026. TU Berlin invited applications for a Research Associate (PostDoc) in Numerically Efficient Learning of Generative Models and Beyond (NumGM). The position covers diffusion and geometric modelling, acceleration methods, transformers and scientific machine learning.

Application deadline: 11 September 2026 · Reference: II-319/26 · Earliest start: 1 September 2026 · Duration: up to three years

Official vacancy

Project details

Publications

Introduce thermal noise before discretizing, not afterwards!
Byadmin 22 July 2026

Workshop report · Oberwolfach Reports 23(1), 803–806 (2026). Incorporating thermal noise before discretising a continuum model.

Read More Introduce thermal noise before discretizing, not afterwards!
Publications

Curvature-Aware Optimization for High-Accuracy Physics-Informed Neural Networks
Byadmin 6 April 20269 October 2026

Published · Computer Methods in Applied Mechanics and Engineering 462, 119289 (2026). Efficient and robust optimization is essential for neural networks, enabling scientific machine learning models to converge rapidly to very high accuracy — faithfully capturing complex physical behavior governed by differential equations. In…

Read More Curvature-Aware Optimization for High-Accuracy Physics-Informed Neural Networks
Publications

Central Path Proximal Policy Optimization
Byadmin 31 May 202527 September 2026

Published · Exploration in AI Today Workshop at ICML 2025. In constrained Markov decision processes, enforcing constraints during training is often thought of as decreasing the final return. Recently, it was shown that constraints can be incorporated directly into the policy geometry,…

Read More Central Path Proximal Policy Optimization
Publications

Asymptotics of Multi-Scale McKean–Vlasov Diffusions with Super-Linear Kernels: a Lifted Semigroup Approach
Byadmin 24 April 202627 September 2026

In this work, we establish the small-noise asymptotic behaviour (namely, the functional law of large numbers and the large deviation principle) for multi-scale McKean–Vlasov diffusions with super-linear kernels. In this setting, the interaction depends on the laws of both the slow component…

Read More Asymptotics of Multi-Scale McKean–Vlasov Diffusions with Super-Linear Kernels: a Lifted Semigroup Approach
Publications

A Dynamical Systems Perspective on the Analysis of Neural Networks
Byadmin 7 July 202527 September 2026

In this chapter, we utilize dynamical systems to analyze several aspects of machine learning algorithms. As an expository contribution we demonstrate how to re-formulate a wide variety of challenges from deep neural networks, (stochastic) gradient descent, and related topics into dynamical statements.…

Read More A Dynamical Systems Perspective on the Analysis of Neural Networks
Publications

Non-Asymptotic Analysis of Projected Gradient Descent for Physics-Informed Neural Networks
Byadmin 12 May 20259 October 2026

Published · Scientific Machine Learning: Emerging Topics, SEMA SIMAI Springer Series (2026). In this work, we provide a non-asymptotic convergence analysis of projected gradient descent for physics-informed neural networks for the Poisson equation. Under suitable assumptions, we show that the optimization error can be…

Read More Non-Asymptotic Analysis of Projected Gradient Descent for Physics-Informed Neural Networks

Similar Posts