appliedAI — TransferLab

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

Trainings

Our hands-on, one to three day workshops cover fundamental and advanced topics in machine learning. We illustrate concepts with abundant real-world examples backed by rigorous theory.

Playbooks

Guided walkthroughs and industry-grade implementations of common tasks in machine learning

Reviews

In-depth analyses of the recently possible, as well as established techniques essential to the daily application of machine learning

Showcases

Visually rich, accessible explanations of novel concepts in machine learning, using open data

Software

Code libraries developed during our research and supporting our work, open sourced

Explore our work

Review Partner area

Data valuation techniques. Applications, advances and problems

The attribution of value to data points can help in data collection, active learning, gauging model robustness, improving model performance …

Data Valuation

May 15, 2021

Review Partner area

Calibration of Classifiers

We discuss the calibration of probabilistic classifiers, i.e. the question of whether the output vectors of such classifiers accurately …

Classifier Calibration

Apr 29, 2021

Software

pyDVL: the python Data Valuation Library

pyDVL strives to offer reference implementations of algorithms for data valuation with a common interface compatible with sklearn and a …

Data Valuation

Apr 3, 2021

Training

Calibration of modern classifiers

An introduction to the pitfalls of uncalibrated classifiers and modern techniques for (re)calibration.

Read our blog

Our take on ICLR 2022 - Part 1

ICLR is one of the most important and prestigious conferences in the ML community. It spans all ML topics, from embeddings to Graph neural …

May 10, 2022

Certified error rates for neural networks

Adversarial training has been shown to improve robustness of neural networks to certain classes of data perturbations. Despite constant …

Robustness in ML

Jan 14, 2022

Natural, Trust Region and Proximal Policy Optimization

We present an overview of the theory behind three popular and related algorithms for gradient based policy optimization: natural policy …

Efficient RL

Aug 10, 2021

Cross-validation: what does it estimate?

In Cross-validation: what does it estimate and how well does it do it? Bates et al. focus on cross validation for error estimation and show …

Error Estimation and Model Selection

Jun 11, 2021

What we are reading:
Paper pills

Denoising Diffusion and Score Based Generative Models

May 11, 2022

This pill gives a short overview of the development of diffusion models over the last 7 years. It contains several references useful for diving into this topic.

Diffusion Models

Progressive Distillation for Fast Sampling of Diffusion Models

May 11, 2022

The paper describes how the generation process of diffusion models can be sped up by using a slow teacher model for training a faster student - the latter performing fewer sampling steps. This distillation process can be iterated by using the previous student as teacher and the final student was shown to generate high-quality samples in the fraction of the original model’s time.

Diffusion Models

Comparing Distributions by Measuring Differences that Affect Decision Making

May 6, 2022

A new family of divergences for distributions is introduced, generalizing KL and others, together with an efficient estimator for it. A beautiful aspect of this family is that the divergence is based on a loss and thus can not only reflect how much distributions differ but also how much their difference affects a selected decision making scenario.

Score-Based Generative Modeling with Critically-Damped Langevin Diffusion

May 6, 2022

In this rather technical paper, a new dynamics is proposed for the sampling of diffusion models. Instead of sampling the de-noised image directly, an auxiliary velocity variable is sampled and deterministic dynamics are used to reconstruct the de-noised data. The approach outperforms previous state of the art in terms of sample quality.

Diffusion Models

Neural Collapse in deep classifiers during Terminal Phase of Training

May 5, 2022

Neural collapse refers to the observation that the last two layers of neural networks that were trained for a long time take a very simple, restricted and universal form - namely an equiangular tight frame. Papers referenced in this pill highlight the phenomenon and provide theoretical hints for why it happens.

Robustness in ML

What we do

Trainings

Our hands-on, one to three day workshops cover fundamental and advanced topics in machine learning. We illustrate concepts with abundant real-world examples backed by rigorous theory.

Playbooks

Guided walkthroughs and industry-grade implementations of common tasks in machine learning

Reviews

In-depth analyses of the recently possible, as well as established techniques essential to the daily application of machine learning

Showcases

Visually rich, accessible explanations of novel concepts in machine learning, using open data

Software

Code libraries developed during our research and supporting our work, open sourced

Explore our work

Data valuation techniques. Applications, advances and problems

The attribution of value to data points can help in data collection, active learning, gauging model robustness, improving model performance …

Calibration of Classifiers

We discuss the calibration of probabilistic classifiers, i.e. the question of whether the output vectors of such classifiers accurately …

pyDVL: the python Data Valuation Library

pyDVL strives to offer reference implementations of algorithms for data valuation with a common interface compatible with sklearn and a …

Calibration of modern classifiers

An introduction to the pitfalls of uncalibrated classifiers and modern techniques for (re)calibration.

Read our blog

Our take on ICLR 2022 - Part 1

ICLR is one of the most important and prestigious conferences in the ML community. It spans all ML topics, from embeddings to Graph neural …

Certified error rates for neural networks

Adversarial training has been shown to improve robustness of neural networks to certain classes of data perturbations. Despite constant …

Natural, Trust Region and Proximal Policy Optimization

We present an overview of the theory behind three popular and related algorithms for gradient based policy optimization: natural policy …

Cross-validation: what does it estimate?

In Cross-validation: what does it estimate and how well does it do it? Bates et al. focus on cross validation for error estimation and show …

What we are reading:Paper pills

This pill gives a short overview of the development of diffusion models over the last 7 years. It contains several references useful for diving into this topic.

Contact us

What we are reading:
Paper pills