juliusberner

sde_sampler

Improved sampling via learned diffusions (ICLR2024) and an optimal control perspective on diffusion-based generative modeling (TMLR2024)

deep_kolmogorov

Numerically Solving Parametric Families of High-Dimensional Kolmogorov Partial Differential Equations via Deep Learning (NeurIPS 2020)

oberwolfach_workshop

Material for 'Mathematics of Deep Learning Workshop' (Invited Talk)

emotion_transformer

Contextual Emotion Detection in Text (DoubleDistilBert Model)

Deep-Multilevel-Kolmogorov-PDE-Solver

Solving stochastic differential equations and Kolmogorov equations by means of deep learning and Multilevel Monte Carlo simulation

homeserver

Ansible playbook for dockerized home-server

svm_tf_pytorch

Soft-margin SVM gradient-descent implementation in PyTorch and TensorFlow/Keras

neural_ode_julia

Using DiffEqFlux to learn underlying differential equations from data.

rpi_vpn_router

Ansible playbook to setup a VPN router using OpenWrt on a Raspberry Pi

ab134

Hey.

pgm_tutorial

A short introduction to probabilistic graphical models using jupyter slides

robust_kolmogorov

Robust SDE-Based Variational Formulations for Solving Linear PDEs via Deep Learning (ICML 2022)

ddn_tutorial

Tutorial on Deep Declarative Networks

science-GHOSTS

GHOSTS: Mathematical Capabilities of ChatGPT

theory2practice

Learning ReLU networks to high uniform accuracy is intractable (ICLR 2023)

NeuralCompression

A collection of tools for neural compression enthusiasts. Featuring my work on Bits-Back coding with diffusion models, see projects/bits_back_diffusion.

CoDA-NO

DPOT

Code for "DPOT: Auto-Regressive Denoising Operator Transformer for Large-Scale PDE Pre-Training"

nf_tutorial

A short tutorial on normalizing flows using jupyter slides

nn_inverse_stability

Illustrating the failure of inverse stability of the neural network realization map.

painter_classification

Painter classification - Model deployment on Render

regularity_relu_network

Towards a regularity theory for ReLU networks (construction of approximating networks, ReLU derivative at zero, theory)