Home | Research | Groups | Tom Sterkenburg

Research Group Tom Sterkenburg


Link to website at LMU

Tom Sterkenburg

Dr.

Associated JRG Leader Epistemology in ML

Munich Center for Mathematical Philosophy

Tom Sterkenburg

leads the Emmy Noether Junior Research Group ‘From Bias to Knowledge: The Epistemology of Machine Learning’ at LMU Munich.

His group’s research is in the epistemological foundations of machine learning. The group uses the mathematical theory of machine learning to study epistemological questions around machine learning and its reliability, with a particular focus on the notion of inductive bias. The group also works on other topics where machine learning and the philosophy of science meet, including explanation and representation. Supported by DFG funding, the group investigates novel research directions that both complement and extend MCML’s scope while strengthening ties to the center.

Team members @MCML

PostDocs

Link to website

Timo Freiesleben

Dr.

Munich Center for Mathematical Philosophy

Publications @MCML

2024


[5]
S. Dandl, K. Blesch, T. Freiesleben, G. König, J. Kapar, B. Bischl and M. N. Wright.
CountARFactuals – Generating plausible model-agnostic counterfactual explanations with adversarial random forests.
xAI 2024 - 2nd World Conference on Explainable Artificial Intelligence. Valletta, Malta, Jul 17-19, 2024. DOI
Abstract

Counterfactual explanations elucidate algorithmic decisions by pointing to scenarios that would have led to an alternative, desired outcome. Giving insight into the model’s behavior, they hint users towards possible actions and give grounds for contesting decisions. As a crucial factor in achieving these goals, counterfactuals must be plausible, i.e., describing realistic alternative scenarios within the data manifold. This paper leverages a recently developed generative modeling technique – adversarial random forests (ARFs) – to efficiently generate plausible counterfactuals in a model-agnostic way. ARFs can serve as a plausibility measure or directly generate counterfactual explanations. Our ARF-based approach surpasses the limitations of existing methods that aim to generate plausible counterfactual explanations: It is easy to train and computationally highly efficient, handles continuous and categorical data naturally, and allows integrating additional desiderata such as sparsity in a straightforward manner.

MCML Authors
Link to website

Timo Freiesleben

Dr.

Munich Center for Mathematical Philosophy

Link to Profile Bernd Bischl

Bernd Bischl

Prof. Dr.

Statistical Learning and Data Science


2023


[4]
C. Molnar, T. Freiesleben, G. König, J. Herbinger, T. Reisinger, G. Casalicchio, M. N. Wright and B. Bischl.
Relating the Partial Dependence Plot and Permutation Feature Importance to the Data Generating Process.
xAI 2023 - 1st World Conference on eXplainable Artificial Intelligence. Lisbon, Portugal, Jul 26-28, 2023. DOI
Abstract

Scientists and practitioners increasingly rely on machine learning to model data and draw conclusions. Compared to statistical modeling approaches, machine learning makes fewer explicit assumptions about data structures, such as linearity. However, their model parameters usually cannot be easily related to the data generating process. To learn about the modeled relationships, partial dependence (PD) plots and permutation feature importance (PFI) are often used as interpretation methods. However, PD and PFI lack a theory that relates them to the data generating process. We formalize PD and PFI as statistical estimators of ground truth estimands rooted in the data generating process. We show that PD and PFI estimates deviate from this ground truth due to statistical biases, model variance and Monte Carlo approximation errors. To account for model variance in PD and PFI estimation, we propose the learner-PD and the learner-PFI based on model refits, and propose corrected variance and confidence interval estimators.

MCML Authors
Link to website

Timo Freiesleben

Dr.

Munich Center for Mathematical Philosophy

Link to website

Giuseppe Casalicchio

Dr.

Statistical Learning and Data Science

Link to Profile Bernd Bischl

Bernd Bischl

Prof. Dr.

Statistical Learning and Data Science


[3]
G. König, T. Freiesleben and M. Grosse-Wentrup.
Improvement-focused causal recourse (ICR).
AAAI 2023 - 37th Conference on Artificial Intelligence. Washington, DC, USA, Feb 07-14, 2023. DOI
Abstract

Algorithmic recourse recommendations, such as Karimi et al.’s (2021) causal recourse (CR), inform stakeholders of how to act to revert unfavorable decisions. However, there are actions that lead to acceptance (i.e., revert the model’s decision) but do not lead to improvement (i.e., may not revert the underlying real-world state). To recommend such actions is to recommend fooling the predictor. We introduce a novel method, Improvement-Focused Causal Recourse (ICR), which involves a conceptual shift: Firstly, we require ICR recommendations to guide toward improvement. Secondly, we do not tailor the recommendations to be accepted by a specific predictor. Instead, we leverage causal knowledge to design decision systems that predict accurately pre- and post-recourse. As a result, improvement guarantees translate into acceptance guarantees. We demonstrate that given correct causal knowledge ICR, in contrast to existing approaches, guides toward both acceptance and improvement.

MCML Authors
Link to website

Timo Freiesleben

Dr.

Munich Center for Mathematical Philosophy

Moritz Grosse-Wentrup

Moritz Grosse-Wentrup

Prof. Dr.

* Former Principal Investigator


2021


[2]
G. König, T. Freiesleben and M. Grosse-Wentrup.
A causal perspective on meaningful and robust algorithmic recourse.
ICML 2021 - Workshop on Algorithmic Recourse at the 38th International Conference on Machine Learning. Virtual, Jul 18-24, 2021. URL
Abstract

Algorithmic recourse explanations inform stakeholders on how to act to revert unfavorable predictions. However, in general ML models do not predict well in interventional distributions. Thus, an action that changes the prediction in the desired way may not lead to an improvement of the underlying target. Such recourse is neither meaningful nor robust to model refits. Extending the work of Karimi et al. (2021), we propose meaningful algorithmic recourse (MAR) that only recommends actions that improve both prediction and target. We justify this selection constraint by highlighting the differences between model audit and meaningful, actionable recourse explanations. Additionally, we introduce a relaxation of MAR called effective algorithmic recourse (EAR), which, under certain assumptions, yields meaningful recourse by only allowing interventions on causes of the target.

MCML Authors
Link to website

Timo Freiesleben

Dr.

Munich Center for Mathematical Philosophy

Moritz Grosse-Wentrup

Moritz Grosse-Wentrup

Prof. Dr.

* Former Principal Investigator


2020


[1]
C. Molnar, G. König, J. Herbinger, T. Freiesleben, S. Dandl, C. A. Scholbeck, G. Casalicchio, M. Grosse-Wentrup and B. Bischl.
General Pitfalls of Model-Agnostic Interpretation Methods for Machine Learning Models.
XXAI @ICML 2020 - Workshop on Extending Explainable AI Beyond Deep Models and Classifiers at the 37th International Conference on Machine Learning (ICML 2020). Virtual, Jul 12-18, 2020. DOI
Abstract

An increasing number of model-agnostic interpretation techniques for machine learning (ML) models such as partial dependence plots (PDP), permutation feature importance (PFI) and Shapley values provide insightful model interpretations, but can lead to wrong conclusions if applied incorrectly. We highlight many general pitfalls of ML model interpretation, such as using interpretation techniques in the wrong context, interpreting models that do not generalize well, ignoring feature dependencies, interactions, uncertainty estimates and issues in high-dimensional settings, or making unjustified causal interpretations, and illustrate them with examples. We focus on pitfalls for global methods that describe the average model behavior, but many pitfalls also apply to local methods that explain individual predictions. Our paper addresses ML practitioners by raising awareness of pitfalls and identifying solutions for correct model interpretation, but also addresses ML researchers by discussing open issues for further research.

MCML Authors
Link to website

Timo Freiesleben

Dr.

Munich Center for Mathematical Philosophy

Link to website

Giuseppe Casalicchio

Dr.

Statistical Learning and Data Science

Moritz Grosse-Wentrup

Moritz Grosse-Wentrup

Prof. Dr.

* Former Principal Investigator

Link to Profile Bernd Bischl

Bernd Bischl

Prof. Dr.

Statistical Learning and Data Science