
Visual Representation Learning Does Not Generalize Strongly Within the Same Domain
An important component for generalization in machine learning is to unco...
read it

Representation Learning for OutOfDistribution Generalization in Reinforcement Learning
Learning data representations that are useful for various downstream tas...
read it

SourceFree Adaptation to Measurement Shift via BottomUp Feature Restoration
Sourcefree domain adaptation (SFDA) aims to adapt a model trained on la...
read it

BackwardCompatible Prediction Updates: A Probabilistic Approach
When machine learning systems meet real world applications, accuracy is ...
read it

Generalization and Robustness Implications in ObjectCentric Learning
The idea behind objectcentric representation learning is that natural s...
read it

Interventional Assays for the Latent Space of Autoencoders
The encoders and decoders of autoencoders effectively project the input ...
read it

Shallow Representation is Deep: Learning Uncertaintyaware and Worstcase Random Feature Dynamics
Random features is a powerful universal function approximator that inher...
read it

Realtime gravitationalwave science with neural posterior estimation
We demonstrate unprecedented accuracy for rapid gravitationalwave param...
read it

Algorithmic Recourse in Partially and Fully Confounded Settings Through Bounding Counterfactual Effects
Algorithmic recourse aims to provide actionable recommendations to indiv...
read it

Towards Total Recall in Industrial Anomaly Detection
Being able to spot defective parts is a critical component in largescal...
read it

Adversarial Robustness through the Lens of Causality
The adversarial vulnerability of deep neural networks has attracted sign...
read it

Independent mechanism analysis, a new concept?
Independent component analysis provides a principled framework for unsup...
read it

SelfSupervised Learning with Data Augmentations Provably Isolates Content from Style
Selfsupervised representation learning has shown remarkable success in ...
read it

The Inductive Bias of Quantum Kernels
It has been hypothesized that quantum computers may lend themselves well...
read it

Causal Influence Detection for Improving Efficiency in Reinforcement Learning
Many reinforcement learning (RL) environments consist of independent ent...
read it

DiBS: Differentiable Bayesian Structure Learning
Bayesian structure learning allows inferring Bayesian network structure ...
read it

Fast and Slow Learning of Recurrent Independent Mechanisms
Decomposing knowledge into interchangeable pieces promises a generalizat...
read it

Regret Bounds for GaussianProcess Optimization in Large Domains
The goal of this paper is to characterize GaussianProcess optimization ...
read it

Pyfectious: An individuallevel simulator to discover optimal containment polices for epidemic diseases
Simulating the spread of infectious diseases in human communities is cri...
read it

A priorbased approximate latent Riemannian metric
Stochastic generative models enable us to capture the geometric structur...
read it

Learning with Hyperspherical Uniformity
Due to the overparameterization nature, neural networks are a powerful ...
read it

Nonlinear Invariant Risk Minimization: A Causal Approach
Due to spurious correlations, machine learning systems often fail to gen...
read it

MultiSided Matching Markets with Consistent Preferences and Cooperative Partners
We introduce a variant of the threesided stable matching problem for a ...
read it

Towards Causal Representation Learning
The two fields of machine learning and graphical causality arose and dev...
read it

From Majorization to Interpolation: Distributionally Robust Learning using Kernel Smoothing
We study the function approximation aspect of distributionally robust op...
read it

Conditional Distributional Treatment Effect with Kernel Conditional Mean Embeddings and UStatistic Regression
We propose to analyse the conditional distributional treatment effect (C...
read it

Bayesian Quadrature on Riemannian Data Manifolds
Riemannian manifolds provide a principled way to model nonlinear geometr...
read it

An Optimal Witness Function for TwoSample Testing
We propose datadependent test statistics based on a onedimensional wit...
read it

TwoSided Matching Markets in the ELLIS 2020 PhD Program
The ELLIS PhD program is a European initiative that supports excellent y...
read it

SampleEfficient Reinforcement Learning via CounterfactualBased Data Augmentation
Reinforcement learning (RL) algorithms usually require a substantial amo...
read it

Assaying Largescale Testing Models to Interpret Covid19 Case Numbers. A Crosscountry Study
Largescale testing is considered key to assessing the state of the curr...
read it

PanCast: Listening to Bluetooth Beacons for Epidemic Risk Mitigation
During the ongoing COVID19 pandemic, there have been burgeoning efforts...
read it

On the Transfer of Disentangled Representations in Realistic Settings
Learning meaningful representations that disentangle the underlying stru...
read it

A Sober Look at the Unsupervised Learning of Disentangled Representations and their Evaluation
The idea behind the unsupervised learning of disentangled representation...
read it

Function Contrastive Learning of Transferable Representations
Fewshotlearning seeks to find models that are capable of fastadaptati...
read it

On the Fairness of Causal Algorithmic Recourse
While many recent works have studied the problem of algorithmic fairness...
read it

Physically constrained causal noise models for highcontrast imaging of exoplanets
The detection of exoplanets in highcontrast imaging (HCI) data hinges o...
read it

CausalWorld: A Robotic Manipulation Benchmark for Causal Structure and Transfer Learning
Despite recent successes of reinforcement learning (RL), it remains a ch...
read it

A survey of algorithmic recourse: definitions, formulations, solutions, and prospects
Machine learning is increasingly used to inform decisionmaking in sensi...
read it

Causal Curiosity: RL Agents Discovering Selfsupervised Experiments for Causal Representation Learning
Humans show an innate ability to learn the regularities of the world thr...
read it

Learning explanations that are hard to vary
In this paper, we investigate the principle that `good explanations are ...
read it

Realtime Prediction of COVID19 related Mortality using Electronic Health Records
Coronavirus Disease 2019 (COVID19) is an emerging respiratory disease c...
read it

Learning Dynamical Systems using Local Stability Priors
A coupled computational approach to simultaneously learn a vector field ...
read it

TriFinger: An OpenSource Robot for Learning Dexterity
Dexterous object manipulation remains an open problem in robotics, despi...
read it

Geometrically Enriched Latent Spaces
A common assumption in generative models is that the generator immerses ...
read it

A Commentary on the Unsupervised Learning of Disentangled Representations
The goal of the unsupervised learning of disentangled representations is...
read it

Causal analysis of Covid19 spread in Germany
In this work, we study the causal relations among German regions in term...
read it

Bloom Origami Assays: Practical Group Testing
We study the problem usually referred to as group testing in the context...
read it

S2RMs: Spatially Structured Recurrent Modules
Capturing the structure of a datagenerating process by means of appropr...
read it

Causal Feature Selection via Orthogonal Search
The problem of inferring the direct causal parents of a response variabl...
read it
Bernhard Schölkopf
is this you? claim profile
Director at Max Planck Institute for Intelligent Systems