Bernhard Schölkopf

research

∙ 08/03/2022

Flow Annealed Importance Sampling Bootstrap

Normalizing flows are tractable density models that can approximate comp...

Laurence Illing Midgley, et al. ∙

research

∙ 07/25/2022

Homomorphism Autoencoder – Learning Group Structured Representations from Observed Transitions

How can we acquire world models that veridically represent the outside w...

Hamza Keurti, et al. ∙

research

∙ 07/22/2022

Discrete Key-Value Bottleneck

Deep neural networks perform well on prediction and classification tasks...

Frederik Träuble, et al. ∙

research

∙ 07/20/2022

Structural Causal 3D Reconstruction

This paper considers the problem of unsupervised 3D object reconstructio...

Weiyang Liu, et al. ∙

research

∙ 07/19/2022

Assaying Out-Of-Distribution Generalization in Transfer Learning

Since out-of-distribution generalization is a generally ill-posed proble...

Florian Wenzel, et al. ∙

research

∙ 07/13/2022

Probing the Robustness of Independent Mechanism Analysis for Representation Learning

One aim of representation learning is to recover the original latent cod...

Joanna Sliwa, et al. ∙

research

∙ 07/11/2022

Functional Generalized Empirical Likelihood Estimation for Conditional Moment Restrictions

Important problems in causal inference, economics, and, more generally, ...

Heiner Kremer, et al. ∙

research

∙ 06/22/2022

Variational Causal Dynamics: Discovering Modular World Models from Interventions

Latent world models allow agents to reason about complex environments wi...

Anson Lei, et al. ∙

research

∙ 06/17/2022

AutoML Two-Sample Test

Two-sample tests are important in statistics and machine learning, both ...

Jonas M. Kübler, et al. ∙

research

∙ 06/07/2022

Sampling without Replacement Leads to Faster Rates in Finite-Sum Minimax Optimization

We analyze the convergence rates of stochastic gradient algorithms for s...

Aniket Das, et al. ∙

research

∙ 06/06/2022

Embrace the Gap: VAEs Perform Independent Mechanism Analysis

Variational autoencoders (VAEs) are a popular framework for modeling com...

Patrik Reizinger, et al. ∙

research

∙ 06/04/2022

Causal Discovery in Heterogeneous Environments Under the Sparse Mechanism Shift Hypothesis

Machine learning approaches commonly rely on the assumption of independe...

Ronan Perry, et al. ∙

research

∙ 06/03/2022

BaCaDI: Bayesian Causal Discovery with Unknown Interventions

Learning causal structures from observation and experimentation is a cen...

Alexander Hägele, et al. ∙

research

∙ 05/25/2022

Amortized Inference for Causal Structure Learning

Learning causal structure poses a combinatorial search problem that typi...

Lars Lorch, et al. ∙

research

∙ 05/04/2022

Original or Translated? A Causal Analysis of the Impact of Translationese on Machine Translation Performance

Human-translated text displays distinct features from naturally written ...

Jingwei Ni, et al. ∙

research

∙ 04/07/2022

Half-sibling regression meets exoplanet imaging: PSF modeling and subtraction using a flexible, domain knowledge-driven, causal framework

High-contrast imaging of exoplanets hinges on powerful post-processing m...

Timothy D. Gebhard, et al. ∙

research

∙ 04/01/2022

From Statistical to Causal Learning

We describe basic ideas underlying research to build and understand arti...

Bernhard Schölkopf, et al. ∙

research

∙ 03/29/2022

Causal de Finetti: On the Identification of Invariant Causal Structure in Exchangeable Data

Learning invariant causal structure often relies on conditional independ...

Siyuan Guo, et al. ∙

research

∙ 03/14/2022

Phenomenology of Double Descent in Finite-Width Neural Networks

`Double descent' delineates the generalization behaviour of models depen...

Sidak Pal Singh, et al. ∙

research

∙ 03/09/2022

Leveling Down in Computer Vision: Pareto Inefficiencies in Fair Deep Classifiers

Algorithmic fairness is frequently motivated in terms of a trade-off in ...

Dominik Zietlow, et al. ∙

research

∙ 03/08/2022

Score matching enables causal discovery of nonlinear additive noise models

This paper demonstrates how to recover causal graphs from the score of t...

Paul Rolland, et al. ∙

research

∙ 03/03/2022

Interventions, Where and How? Experimental Design for Causal Models at Scale

Causal discovery from observational and interventional data is challengi...

Panagiotis Tigas, et al. ∙

research

∙ 02/28/2022

Logical Fallacy Detection

Reasoning is central to human intelligence. However, fallacious argument...

Zhijing Jin, et al. ∙

research

∙ 02/14/2022

On Pitfalls of Identifiability in Unsupervised Learning. A Note on: "Desiderata for Representation Learning: A Causal Perspective"

Model identifiability is a desirable property in the context of unsuperv...

Shubhangi Ghosh, et al. ∙

research

∙ 02/02/2022

Causal Inference Through the Structural Causal Marginal Problem

We introduce an approach to counterfactual inference based on merging in...

Luigi Gresele, et al. ∙

research

∙ 01/31/2022

Compositional Multi-Object Reinforcement Learning with Linear Relation Networks

Although reinforcement learning has seen remarkable progress over the la...

Davide Mambelli, et al. ∙

research

∙ 01/15/2022

Physical Derivatives: Computing policy gradients by physical forward-propagation

Model-free and model-based reinforcement learning are two ends of a spec...

Arash Mehrjou, et al. ∙

research

∙ 12/21/2021

On the Adversarial Robustness of Causal Algorithmic Recourse

Algorithmic recourse seeks to provide actionable recommendations for ind...

Ricardo Dominguez-Olmedo, et al. ∙

research

∙ 12/10/2021

Learning soft interventions in complex equilibrium systems

Complex systems often contain feedback loops that can be described as cy...

Michel Besserve, et al. ∙

research

∙ 11/27/2021

Towards Principled Disentanglement for Domain Generalization

A fundamental challenge for machine learning models is generalizing to o...

Hanlin Zhang, et al. ∙

research

∙ 11/25/2021

Group equivariant neural posterior estimation

Simulation-based inference with conditional neural density estimators is...

Maximilian Dax, et al. ∙

research

∙ 10/29/2021

Resampling Base Distributions of Normalizing Flows

Normalizing flows are a popular class of models for approximating probab...

Vincent Stimper, et al. ∙

research

∙ 10/29/2021

Cause-effect inference through spectral independence in linear dynamical systems: theoretical foundations

Distinguishing between cause and effect using time series observational ...

Michel Besserve, et al. ∙

research

∙ 10/29/2021

GalilAI: Out-of-Task Distribution Detection using Causal Active Experimentation for Safe Transfer RL

Out-of-distribution (OOD) detection is a well-studied topic in supervise...

Sumedh A. Sontakke, et al. ∙

research

∙ 10/27/2021

Iterative Teaching by Label Synthesis

In this paper, we consider the problem of iterative machine teaching, wh...

Weiyang Liu, et al. ∙

research

∙ 10/13/2021

Unsupervised Object Learning via Common Fate

Learning generative object models from unlabelled videos is a long stand...

Matthias Tangemann, et al. ∙

research

∙ 10/12/2021

Dynamic Inference with Neural Interpreters

Modern neural network architectures can leverage large amounts of data t...

Nasim Rahaman, et al. ∙

research

∙ 10/12/2021

Action-Sufficient State Representation Learning for Control with Structural Constraints

Perceived signals in real-world scenarios are usually high-dimensional a...

Biwei Huang, et al. ∙

research

∙ 10/11/2021

You Mostly Walk Alone: Analyzing Feature Attribution in Trajectory Prediction

Predicting the future trajectory of a moving agent can be easy when the ...

Osama Makansi, et al. ∙

research

∙ 10/07/2021

Boxhead: A Dataset for Learning Hierarchical Representations

Disentanglement is hypothesized to be beneficial towards a number of dow...

Yukun Chen, et al. ∙

research

∙ 09/13/2021

Direct Advantage Estimation

Credit assignment is one of the central problems in reinforcement learni...

Hsiao-Ru Pan, et al. ∙

research

∙ 09/06/2021

Learning Neural Causal Models with Active Interventions

Discovering causal structures from data is a challenging inference probl...

Nino Scherrer, et al. ∙

research

∙ 07/17/2021

Visual Representation Learning Does Not Generalize Strongly Within the Same Domain

An important component for generalization in machine learning is to unco...

Lukas Schott, et al. ∙

research

∙ 07/12/2021

Representation Learning for Out-Of-Distribution Generalization in Reinforcement Learning

Learning data representations that are useful for various downstream tas...

Andrea Dittadi, et al. ∙

research

∙ 07/12/2021

Source-Free Adaptation to Measurement Shift via Bottom-Up Feature Restoration

Source-free domain adaptation (SFDA) aims to adapt a model trained on la...

Cian Eastwood, et al. ∙

research

∙ 07/02/2021

Backward-Compatible Prediction Updates: A Probabilistic Approach

When machine learning systems meet real world applications, accuracy is ...

Frederik Träuble, et al. ∙

research

∙ 07/01/2021

Generalization and Robustness Implications in Object-Centric Learning

The idea behind object-centric representation learning is that natural s...

Andrea Dittadi, et al. ∙

research

∙ 06/30/2021

Interventional Assays for the Latent Space of Autoencoders

The encoders and decoders of autoencoders effectively project the input ...

Felix Leeb, et al. ∙

research

∙ 06/24/2021

Shallow Representation is Deep: Learning Uncertainty-aware and Worst-case Random Feature Dynamics

Random features is a powerful universal function approximator that inher...

Diego Agudelo-España, et al. ∙

research

∙ 06/23/2021

Real-time gravitational-wave science with neural posterior estimation

We demonstrate unprecedented accuracy for rapid gravitational-wave param...

Maximilian Dax, et al. ∙

Bernhard Schölkopf

Featured Co-authors