Search Results for author:
Found 46 papers, 25 papers with code
Unified Uncertainty Calibration
To build robust, fair, and safe AI systems, we would like our classifiers to say ``I don't know'' when facing test examples that are difficult or fall outside of the training classes. The ubiquitous strategy to predict under uncertainty is the simplistic \emph{reject-or-classify} rule: abstain from prediction if epistemic uncertainty is high, classify otherwise. Unfortunately, this recipe does not allow different sources of uncertainty to communicate with each other, produces miscalibrated predictions, and it does not allow to correct for misspecifications in our uncertainty estimates.
Discovering environments with XRM
Successful out-of-distribution generalization requires environment annotations.
A Closer Look at In-Context Learning under Distribution Shifts
In-context learning, a capability that enables a model to learn from input examples on the fly without necessitating weight updates, is a defining characteristic of large language models.
Model Ratatouille: Recycling Diverse Models for Out-of-Distribution Generalization
In this paper, we thus propose model ratatouille, a new strategy to recycle the multiple fine-tunings of the same foundation model on diverse auxiliary tasks.
Ranked #14 on
Domain Generalization
on PACS
ImageNet-X: Understanding Model Mistakes with Factor of Variation Annotations
Equipped with ImageNet-X, we investigate 2, 200 current recognition models and study the types of mistakes as a function of model's (1) architecture, e. g. transformer vs. convolutional, (2) learning paradigm, e. g. supervised vs. self-supervised, and (3) training procedures, e. g., data augmentation.
Measuring and signing fairness as performance under multiple stakeholder distributions
By highlighting connections to the literature in domain generalization, we propose to measure fairness as the ability of the system to generalize under multiple stress tests -- distributions of examples with social relevance.
Why does Throwing Away Data Improve Worst-Group Error?
When facing data with imbalanced classes or groups, practitioners follow an intriguing strategy to achieve best results.
Rich Feature Construction for the Optimization-Generalization Dilemma
On the one hand, a rich representation provides a good initialization for the optimizer.
An Empirical Investigation of Domain Generalization with Empirical Risk Minimizers
Recent work demonstrates that deep neural networks trained using Empirical Risk Minimization (ERM) can generalize under distribution shift, outperforming specialized training algorithms for domain generalization.
Simple data balancing achieves competitive worst-group-accuracy
We study the problem of learning classifiers that perform well across (known or unknown) groups of data.
Ranked #1 on
Out-of-Distribution Generalization
on UrbanCars
What classifiers know what they don't know?
Adding new datasets, algorithms, measures, or metrics is a matter of a few lines of code-in so hoping that UIMNET becomes a stepping stone towards realistic, rigorous, and reproducible research in uncertainty estimation.
What classifiers know what they don't?
Adding new datasets, algorithms, measures, or metrics is a matter of a few lines of code-in so hoping that UIMNET becomes a stepping stone towards realistic, rigorous, and reproducible research in uncertainty estimation.
Linear unit-tests for invariance discovery
There is an increasing interest in algorithms to learn invariant correlations across training environments.
In Search of Lost Domain Generalization
As a first step, we realize that model selection is non-trivial for domain generalization tasks.
Ranked #42 on
Domain Generalization
on PACS
Permutation Equivariant Models for Compositional Generalization in Language
Humans understand novel sentences by composing meanings and roles of core language components.
Using Hindsight to Anchor Past Knowledge in Continual Learning
In continual learning, the learner faces a stream of data whose distribution changes over time.
Measuring causal influence with back-to-back regression: the linear case
Identifying causes from observations can be particularly challenging when i) potential factors are difficult to manipulate individually and ii) observations are complex and multi-dimensional.
Invariant Risk Minimization
We introduce Invariant Risk Minimization (IRM), a learning paradigm to estimate invariant correlations across multiple training distributions.
Adversarial Vulnerability of Neural Networks Increases with Input Dimension
Over the past four years, neural networks have been proven vulnerable to adversarial images: targeted but imperceptible image perturbations lead to drastically different predictions.
Interpolation Consistency Training for Semi-Supervised Learning
We introduce Interpolation Consistency Training (ICT), a simple and computation efficient algorithm for training Deep Neural Networks in the semi-supervised learning paradigm.
Learning about an exponential amount of conditional distributions
We introduce the Neural Conditioner (NC), a self-supervised machine able to learn about all the conditional distributions of a random vector $X$.
Single-Model Uncertainties for Deep Learning
To estimate epistemic uncertainty, we propose Orthonormal Certificates (OCs), a collection of diverse non-constant functions that map all training samples to zero.
Manifold Mixup: Better Representations by Interpolating Hidden States
Deep neural networks excel at learning the training data, but often provide incorrect and confident predictions when evaluated on slightly different test examples.
Ranked #18 on
Image Classification
on OmniBenchmark
Structural Agnostic Modeling: Adversarial Learning of Causal Graphs
A new causal discovery method, Structural Agnostic Modeling (SAM), is presented in this paper.
First-order Adversarial Vulnerability of Neural Networks and Input Dimension
Over the past few years, neural networks were proven vulnerable to adversarial images: targeted but imperceptible image perturbations lead to drastically different predictions.
Geometrical Insights for Implicit Generative Modeling
Learning algorithms for implicit generative models can optimize a variety of criteria that measure how the data distribution differs from the implicit model distribution, including the Wasserstein distance, the Energy distance, and the Maximum Mean Discrepancy criterion.
Causal Generative Neural Networks
We present Causal Generative Neural Networks (CGNNs) to learn functional causal models from observational data.
mixup: Beyond Empirical Risk Minimization
We also find that mixup reduces the memorization of corrupt labels, increases the robustness to adversarial examples, and stabilizes the training of generative adversarial networks.
Ranked #1 on
Out-of-Distribution Generalization
on ImageNet-W
Learning Functional Causal Models with Generative Neural Networks
We introduce a new approach to functional causal modeling from observational data, called Causal Generative Neural Networks (CGNN).
Optimizing the Latent Space of Generative Networks
Generative Adversarial Networks (GANs) have achieved remarkable results in the task of generating realistic natural images.
Gradient Episodic Memory for Continual Learning
One major obstacle towards AI is the poor ability of models to solve new problems quicker, and without forgetting previously acquired knowledge.
Causal Discovery Using Proxy Variables
In this paper, we develop a framework to estimate the cause-effect relation between two static entities $x$ and $y$: for instance, an art masterpiece $x$ and its fraudulent copy $y$.
Patient-Driven Privacy Control through Generalized Distillation
In this paper, we present privacy distillation, a mechanism which allows patients to control the type and amount of information they wish to disclose to the healthcare providers for use in statistical models.
Revisiting Classifier Two-Sample Tests
The goal of this paper is to establish the properties, performance, and uses of C2ST.
From Dependence to Causation
Second, we build on this framework to interpret the problem of causal inference as the task of distribution classification, yielding a family of novel causal inference algorithms.
Discovering Causal Signals in Images
Our experiments demonstrate the existence of a relation between the direction of causality and the difference between objects and their contexts, and by the same token, the existence of observable signals that reveal the causal dispositions of objects.
Minimax Lower Bounds for Realizable Transductive Classification
Transductive learning considers a training set of $m$ labeled samples and a test set of $u$ unlabeled samples, with the goal of best labeling that particular test set.
Unifying distillation and privileged information
Distillation (Hinton et al., 2015) and privileged information (Vapnik & Izmailov, 2015) are two techniques that enable machines to learn from other machines.
No Regret Bound for Extreme Bandits
This work is naturally framed in the extreme bandit setting, which deals with sequentially choosing which distribution from a collection to sample in order to minimize (maximize) the single best cost (reward).
Towards a Learning Theory of Cause-Effect Inference
We pose causal inference as the problem of learning to classify probability distributions.
Non-linear Causal Inference using Gaussianity Measures
The problem of non-linear causal inference is addressed by performing an embedding in an expanded feature space, in which the relation between causes and effects can be assumed to be linear.
The Randomized Causation Coefficient
We are interested in learning causal relationships between pairs of random variables, purely from observational data.
Randomized Nonlinear Component Analysis
Although nonlinear variants of PCA and CCA have been proposed, these are computationally prohibitive in the large scale.
The Randomized Dependence Coefficient
We introduce the Randomized Dependence Coefficient (RDC), a measure of non-linear dependence between random variables of arbitrary dimension based on the Hirschfeld-Gebelein-R\'enyi Maximum Correlation Coefficient.
Semi-Supervised Domain Adaptation with Non-Parametric Copulas
A new framework based on the theory of copulas is proposed to address semi-supervised domain adaptation problems.
