Search Results for author: Niki Kilbertus

Found 28 papers, 17 papers with code

Avoiding Discrimination through Causal Reasoning

no code implementations NeurIPS 2017 Niki Kilbertus, Mateo Rojas-Carulla, Giambattista Parascandolo, Moritz Hardt, Dominik Janzing, Bernhard Schölkopf

Going beyond observational criteria, we frame the problem of discrimination based on protected attributes in the language of causal reasoning.

Attribute Fairness

Learning Independent Causal Mechanisms

1 code implementation ICML 2018 Giambattista Parascandolo, Niki Kilbertus, Mateo Rojas-Carulla, Bernhard Schölkopf

The approach is unsupervised and based on a set of experts that compete for data generated by the mechanisms, driving specialization.

Transfer Learning

Blind Justice: Fairness with Encrypted Sensitive Attributes

1 code implementation ICML 2018 Niki Kilbertus, Adrià Gascón, Matt J. Kusner, Michael Veale, Krishna P. Gummadi, Adrian Weller

Recent work has explored how to train machine learning models which do not discriminate against any subgroup of the population as determined by sensitive attributes such as gender or race.

Fairness

Generalization in anti-causal learning

no code implementations3 Dec 2018 Niki Kilbertus, Giambattista Parascandolo, Bernhard Schölkopf

Anti-causal models are used to drive this search, but a causal model is required for validation.

BIG-bench Machine Learning

Fair Decisions Despite Imperfect Predictions

1 code implementation8 Feb 2019 Niki Kilbertus, Manuel Gomez-Rodriguez, Bernhard Schölkopf, Krikamol Muandet, Isabel Valera

In this paper, we show that in this selective labels setting, learning a predictor directly only from available labeled data is suboptimal in terms of both fairness and utility.

Causal Inference Decision Making +1

Convolutional neural networks: a magic bullet for gravitational-wave detection?

2 code implementations18 Apr 2019 Timothy D. Gebhard, Niki Kilbertus, Ian Harry, Bernhard Schölkopf

In the last few years, machine learning techniques, in particular convolutional neural networks, have been investigated as a method to replace or complement traditional matched filtering techniques that are used to detect the gravitational-wave signature of merging black holes.

Astronomy BIG-bench Machine Learning +1

The Sensitivity of Counterfactual Fairness to Unmeasured Confounding

1 code implementation1 Jul 2019 Niki Kilbertus, Philip J. Ball, Matt J. Kusner, Adrian Weller, Ricardo Silva

We demonstrate our new sensitivity analysis tools in real-world fairness scenarios to assess the bias arising from confounding.

counterfactual Fairness

A Class of Algorithms for General Instrumental Variable Models

1 code implementation NeurIPS 2020 Niki Kilbertus, Matt J. Kusner, Ricardo Silva

Causal treatment effect estimation is a key problem that arises in a variety of real-world settings, from personalized medicine to governmental policy making.

Beyond traditional assumptions in fair machine learning

no code implementations29 Jan 2021 Niki Kilbertus

Revisiting this limitation from a causal viewpoint we develop a more versatile conceptual framework, causal fairness criteria, and first algorithms to achieve them.

BIG-bench Machine Learning Decision Making +1

Beyond Predictions in Neural ODEs: Identification and Interventions

no code implementations23 Jun 2021 Hananeh Aliee, Fabian J. Theis, Niki Kilbertus

Spurred by tremendous success in pattern matching and prediction tasks, researchers increasingly resort to machine learning to aid original scientific discovery.

Time Series Time Series Analysis

On component interactions in two-stage recommender systems

no code implementations28 Jun 2021 Jiri Hron, Karl Krauth, Michael I. Jordan, Niki Kilbertus

Thanks to their scalability, two-stage recommenders are used by many of today's largest online platforms, including YouTube, LinkedIn, and Pinterest.

Recommendation Systems Vocal Bursts Valence Prediction

Stochastic Causal Programming for Bounding Treatment Effects

1 code implementation22 Feb 2022 Kirtan Padh, Jakob Zeitler, David Watson, Matt Kusner, Ricardo Silva, Niki Kilbertus

Causal effect estimation is important for many tasks in the natural and social sciences.

Predicting Cellular Responses to Novel Drug Perturbations at a Single-Cell Resolution

1 code implementation28 Apr 2022 Leon Hetzel, Simon Böhm, Niki Kilbertus, Stephan Günnemann, Mohammad Lotfollahi, Fabian Theis

Single-cell transcriptomics enabled the study of cellular heterogeneity in response to perturbations at the resolution of individual cells.

Drug Discovery Transfer Learning

Supervised Learning and Model Analysis with Compositional Data

1 code implementation15 May 2022 Shimeng Huang, Elisabeth Ailer, Niki Kilbertus, Niklas Pfister

We propose KernelBiome, a kernel-based nonparametric regression and classification framework for compositional data.

regression

Multi-disciplinary fairness considerations in machine learning for clinical trials

no code implementations18 May 2022 Isabel Chien, Nina Deliu, Richard E. Turner, Adrian Weller, Sofia S. Villar, Niki Kilbertus

While interest in the application of machine learning to improve healthcare has grown tremendously in recent years, a number of barriers prevent deployment in medical practice.

BIG-bench Machine Learning Fairness

Modeling Content Creator Incentives on Algorithm-Curated Platforms

no code implementations27 Jun 2022 Jiri Hron, Karl Krauth, Michael I. Jordan, Niki Kilbertus, Sarah Dean

To this end, we propose tools for numerically finding equilibria in exposure games, and illustrate results of an audit on the MovieLens and LastFM datasets.

Learning Counterfactually Invariant Predictors

1 code implementation20 Jul 2022 Francesco Quinzan, Cecilia Casolo, Krikamol Muandet, Yucen Luo, Niki Kilbertus

Notions of counterfactual invariance (CI) have proven essential for predictors that are fair, robust, and generalizable in the real world.

counterfactual Object Recognition

Sparsity in Continuous-Depth Neural Networks

1 code implementation26 Oct 2022 Hananeh Aliee, Till Richter, Mikhail Solonin, Ignacio Ibarra, Fabian Theis, Niki Kilbertus

Neural Ordinary Differential Equations (NODEs) have proven successful in learning dynamical systems in terms of accurately recovering the observed trajectories.

Discovering ordinary differential equations that govern time-series

no code implementations5 Nov 2022 Sören Becker, Michal Klein, Alexander Neitz, Giambattista Parascandolo, Niki Kilbertus

Natural laws are often described through differential equations yet finding a differential equation that describes the governing law underlying observed data is a challenging and still mostly manual task.

Time Series Time Series Analysis

Sequential Underspecified Instrument Selection for Cause-Effect Estimation

1 code implementation11 Feb 2023 Elisabeth Ailer, Jason Hartford, Niki Kilbertus

Instrumental variable (IV) methods are used to estimate causal effects in settings with unobserved confounding, where we cannot directly experiment on the treatment variable.

Predicting Ordinary Differential Equations with Transformers

no code implementations24 Jul 2023 Sören Becker, Michal Klein, Alexander Neitz, Giambattista Parascandolo, Niki Kilbertus

We develop a transformer-based sequence-to-sequence model that recovers scalar ordinary differential equations (ODEs) in symbolic form from irregularly sampled and noisy observations of a single solution trajectory.

ODEFormer: Symbolic Regression of Dynamical Systems with Transformers

1 code implementation9 Oct 2023 Stéphane d'Ascoli, Sören Becker, Alexander Mathis, Philippe Schwaller, Niki Kilbertus

We introduce ODEFormer, the first transformer able to infer multidimensional ordinary differential equation (ODE) systems in symbolic form from the observation of a single solution trajectory.

regression Symbolic Regression

Signature Kernel Conditional Independence Tests in Causal Discovery for Stochastic Processes

no code implementations28 Feb 2024 Georg Manten, Cecilia Casolo, Emilio Ferrucci, Søren Wengel Mogensen, Cristopher Salvi, Niki Kilbertus

Inferring the causal structure underlying stochastic dynamical systems from observational data holds great promise in domains ranging from science and health to finance.

Causal Discovery

Cannot find the paper you are looking for? You can Submit a new open access paper.