David Lopez-Paz

research

∙ 09/18/2023

Context is Environment

Two lines of work are taking the central stage in AI research. On the on...

0 Sharut Gupta, et al. ∙

research

∙ 05/26/2023

A Closer Look at In-Context Learning under Distribution Shifts

In-context learning, a capability that enables a model to learn from inp...

0 Kartik Ahuja, et al. ∙

research

∙ 12/20/2022

Recycling diverse models for out-of-distribution generalization

Foundation models are redefining how AI systems are built. Practitioners...

0 Alexandre Ramé, et al. ∙

research

∙ 11/03/2022

ImageNet-X: Understanding Model Mistakes with Factor of Variation Annotations

Deep learning vision systems are widely deployed across applications whe...

2 Badr Youbi Idrissi, et al. ∙

research

∙ 07/20/2022

Measuring and signing fairness as performance under multiple stakeholder distributions

As learning machines increase their influence on decisions concerning hu...

0 David Lopez-Paz, et al. ∙

research

∙ 05/23/2022

Throwing Away Data Improves Worst-Class Error in Imbalanced Classification

Class imbalances pervade classification problems, yet their treatment di...

0 Martin Arjovsky, et al. ∙

research

∙ 03/24/2022

Rich Feature Construction for the Optimization-Generalization Dilemma

There often is a dilemma between ease of optimization and robust out-of-...

0 Jianyu Zhang, et al. ∙

research

∙ 10/27/2021

Simple data balancing achieves competitive worst-group-accuracy

We study the problem of learning classifiers that perform well across (k...

0 Badr Youbi Idrissi, et al. ∙

research

∙ 07/13/2021

What classifiers know what they don't?

Being uncertain when facing the unknown is key to intelligent decision m...

0 Mohamed Ishmael Belghazi, et al. ∙

research

∙ 07/02/2020

In Search of Lost Domain Generalization

The goal of domain generalization algorithms is to predict well on distr...

0 Ishaan Gulrajani, et al. ∙

research

∙ 02/19/2020

Using Hindsight to Anchor Past Knowledge in Continual Learning

In continual learning, the learner faces a stream of data whose distribu...

0 Arslan Chaudhry, et al. ∙

research

∙ 07/05/2019

Invariant Risk Minimization

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

1 Martin Arjovsky, et al. ∙

research

∙ 03/09/2019

Interpolation Consistency Training for Semi-Supervised Learning

We introduce Interpolation Consistency Training (ICT), a simple and comp...

10 Vikas Verma, et al. ∙

research

∙ 02/22/2019

Learning about an exponential amount of conditional distributions

We introduce the Neural Conditioner (NC), a self-supervised machine able...

10 Mohamed Ishmael Belghazi, et al. ∙

research

∙ 11/02/2018

Frequentist uncertainty estimates for deep learning

We provide frequentist estimates of aleatoric and epistemic uncertainty ...

0 Natasa Tagasovska, et al. ∙

research

∙ 03/13/2018

SAM: Structural Agnostic Model, Causal Discovery and Penalized Adversarial Learning

We present the Structural Agnostic Model (SAM), a framework to estimate ...

0 Diviyan Kalainathan, et al. ∙

research

∙ 02/05/2018

Adversarial Vulnerability of Neural Networks Increases With Input Dimension

Over the past four years, neural networks have proven vulnerable to adve...

0 Carl-Johann Simon-Gabriel, et al. ∙

research

∙ 12/21/2017

Geometrical Insights for Implicit Generative Modeling

Learning algorithms for implicit generative models can optimize a variet...

0 Leon Bottou, et al. ∙

research

∙ 11/24/2017

Causal Generative Neural Networks

We introduce CGNN, a framework to learn functional causal models as gene...

0 Olivier Goudet, et al. ∙

research

∙ 10/25/2017

mixup: Beyond Empirical Risk Minimization

Large deep neural networks are powerful, but exhibit undesirable behavio...

0 Hongyi Zhang, et al. ∙

research

∙ 09/15/2017

Learning Functional Causal Models with Generative Neural Networks

We introduce a new approach to functional causal modeling from observati...

0 Olivier Goudet, et al. ∙

research

∙ 07/18/2017

Optimizing the Latent Space of Generative Networks

Generative Adversarial Networks (GANs) have been shown to be able to sam...

0 Piotr Bojanowski, et al. ∙

research

∙ 06/26/2017

Gradient Episodic Memory for Continual Learning

One major obstacle towards AI is the poor ability of models to solve new...

0 David Lopez-Paz, et al. ∙

research

∙ 02/23/2017

Causal Discovery Using Proxy Variables

Discovering causal relations is fundamental to reasoning and intelligenc...

0 Mateo Rojas-Carulla, et al. ∙

research

∙ 10/20/2016

Revisiting Classifier Two-Sample Tests

The goal of two-sample tests is to assess whether two samples, S_P ∼ P^n...

0 David Lopez-Paz, et al. ∙

research

∙ 07/12/2016

From Dependence to Causation

Machine learning is the science of discovering statistical dependencies ...

0 David Lopez-Paz, et al. ∙

research

∙ 05/26/2016

Discovering Causal Signals in Images

This paper establishes the existence of observable footprints that revea...

0 David Lopez-Paz, et al. ∙

research

∙ 02/09/2016

Minimax Lower Bounds for Realizable Transductive Classification

Transductive learning considers a training set of m labeled samples and ...

0 Ilya Tolstikhin, et al. ∙

research

∙ 11/11/2015

Unifying distillation and privileged information

Distillation (Hinton et al., 2015) and privileged information (Vapnik & ...

0 David Lopez-Paz, et al. ∙

research

∙ 08/12/2015

No Regret Bound for Extreme Bandits

Algorithms for hyperparameter optimization abound, all of which work wel...

0 Robert Nishihara, et al. ∙

research

∙ 02/09/2015

Towards a Learning Theory of Cause-Effect Inference

We pose causal inference as the problem of learning to classify probabil...

0 David Lopez-Paz, et al. ∙

research

∙ 02/01/2014

Randomized Nonlinear Component Analysis

Classical methods such as Principal Component Analysis (PCA) and Canonic...

0 David Lopez-Paz, et al. ∙

research

∙ 04/29/2013

The Randomized Dependence Coefficient

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

0 David Lopez-Paz, et al. ∙

research

∙ 02/16/2013

Gaussian Process Vine Copulas for Multivariate Dependence

Copulas allow to learn marginal distributions separately from the multiv...

0 David Lopez-Paz, et al. ∙

research

∙ 01/01/2013

Semi-Supervised Domain Adaptation with Non-Parametric Copulas

A new framework based on the theory of copulas is proposed to address se...

0 David Lopez-Paz, et al. ∙

David Lopez-Paz

Featured Co-authors