
In Search of Lost Domain Generalization
The goal of domain generalization algorithms is to predict well on distr...
read it

Using Hindsight to Anchor Past Knowledge in Continual Learning
In continual learning, the learner faces a stream of data whose distribu...
read it

Invariant Risk Minimization
We introduce Invariant Risk Minimization (IRM), a learning paradigm to e...
read it

Interpolation Consistency Training for SemiSupervised Learning
We introduce Interpolation Consistency Training (ICT), a simple and comp...
read it

Learning about an exponential amount of conditional distributions
We introduce the Neural Conditioner (NC), a selfsupervised machine able...
read it

Frequentist uncertainty estimates for deep learning
We provide frequentist estimates of aleatoric and epistemic uncertainty ...
read it

SAM: Structural Agnostic Model, Causal Discovery and Penalized Adversarial Learning
We present the Structural Agnostic Model (SAM), a framework to estimate ...
read it

Adversarial Vulnerability of Neural Networks Increases With Input Dimension
Over the past four years, neural networks have proven vulnerable to adve...
read it

Geometrical Insights for Implicit Generative Modeling
Learning algorithms for implicit generative models can optimize a variet...
read it

Causal Generative Neural Networks
We introduce CGNN, a framework to learn functional causal models as gene...
read it

mixup: Beyond Empirical Risk Minimization
Large deep neural networks are powerful, but exhibit undesirable behavio...
read it

Learning Functional Causal Models with Generative Neural Networks
We introduce a new approach to functional causal modeling from observati...
read it

Optimizing the Latent Space of Generative Networks
Generative Adversarial Networks (GANs) have been shown to be able to sam...
read it

Gradient Episodic Memory for Continual Learning
One major obstacle towards AI is the poor ability of models to solve new...
read it

Causal Discovery Using Proxy Variables
Discovering causal relations is fundamental to reasoning and intelligenc...
read it

Revisiting Classifier TwoSample Tests
The goal of twosample tests is to assess whether two samples, S_P ∼ P^n...
read it

From Dependence to Causation
Machine learning is the science of discovering statistical dependencies ...
read it

Discovering Causal Signals in Images
This paper establishes the existence of observable footprints that revea...
read it

Minimax Lower Bounds for Realizable Transductive Classification
Transductive learning considers a training set of m labeled samples and ...
read it

Unifying distillation and privileged information
Distillation (Hinton et al., 2015) and privileged information (Vapnik & ...
read it

No Regret Bound for Extreme Bandits
Algorithms for hyperparameter optimization abound, all of which work wel...
read it

Towards a Learning Theory of CauseEffect Inference
We pose causal inference as the problem of learning to classify probabil...
read it

Randomized Nonlinear Component Analysis
Classical methods such as Principal Component Analysis (PCA) and Canonic...
read it

The Randomized Dependence Coefficient
We introduce the Randomized Dependence Coefficient (RDC), a measure of n...
read it

Gaussian Process Vine Copulas for Multivariate Dependence
Copulas allow to learn marginal distributions separately from the multiv...
read it

SemiSupervised Domain Adaptation with NonParametric Copulas
A new framework based on the theory of copulas is proposed to address se...
read it