About
Blog
Pills
Software
Trainings
Seminar
⚲
Search results
We
identify
,
test
and
disseminate
established and emerging techniques in machine learning in order to provide practitioners with the best tools for their applications
What we do
Software
Open source libraries and paper implementations developed during our research and supporting our work.
Research feed
Read our paper pills: summaries of publications, talks or new software, with context and an explanation of the main ideas and key results.
Trainings
Our hands-on, one to three day workshops cover fundamental and advanced topics in machine learning.
Our blog
We publish introductory posts for beginners and paper digests for experienced people on a tight schedule.
Our areas of interest
Safety and reliability in ML systems
Efficient Machine Learning
Trustworthy and interpretable ML
Advances and fundamentals in ML
Our latest work
Training
Beyond Jupyter
Beyond Jupyter is a collection of self-study materials on software design, with a specific focus on machine learning applications, which demonstrates how sound software design can accelerate both development and experimentation.
Software
sbi: the simulation-based inference toolkit
sbi is a Python package for Bayesian parameter inference on simulators. It implements state-of-the-art algorithms and comes with …
Software
continuiti: Learning Function Operators with Neural Networks
continuiti is a Python package for machine learning on function operators. It implements various neural operator architectures (e.g., …
Blog
Can perceptual similarity metrics be used to compare adversarial attacks?
Adversarial attacks in computer vision are often bound in $\ell _{p}$ distance. This precludes comparing these techniques with …
Software
sensAI: The Python Library for Sensible AI
sensAI is a high-level AI toolkit with a specific focus on rapid experimentation for machine learning applications. It provides a unifying …
Research feed:
Paper pills
Sourcerer: Sample-based Maximum Entropy Source Distribution Estimation
Identifying the source distribution behind observed data is an ill-posed problem. Sourcerer [Vet24S] introduces a novel approach based on …
Variance Reduced Shapley Value Estimation for Trustworthy Data Valuation
VRDS, an effective method to reduce the variance of Data Shapley, based on a stratified sampling technique with precomputed coefficients.
Sequential Neural Score Estimation: Likelihood-Free Inference with Conditional Score Based Diffusion Models
In Simulation-based inference (SBI) conditional density estimators are used to approximate the posterior distribution from simulated data. …
BelNet: Basis-enhanced learning network
Operator learning trains a neural network to map functions to functions. An ideal operator learning framework should not require a …
See more...
