Robust Generalization despite Distribution Shift via Minimum Discriminating Information

Chattez avec Graph Search

Posez n’importe quelle question sur les cours, conférences, exercices, recherches, actualités, etc. de l’EPFL ou essayez les exemples de questions ci-dessous.

AVERTISSEMENT : Le chatbot Graph n'est pas programmé pour fournir des réponses explicites ou catégoriques à vos questions. Il transforme plutôt vos questions en demandes API qui sont distribuées aux différents services informatiques officiellement administrés par l'EPFL. Son but est uniquement de collecter et de recommander des références pertinentes à des contenus que vous pouvez explorer pour vous aider à répondre à vos questions.

There is a bias in the inference pipeline of most diffusion models. This bias arises from a signal leak whose distribution deviates from the noise distribution, creating a discrepancy between training and inference processes. We demonstrate that this signa ...

Visual perception is indispensable for many real-world applications. However, perception models deployed in the real world will encounter numerous and unpredictable distribution shifts, for example, changes in geographic locations, motion blur, and adverse ...

Interactions are ubiquitous in our world, spanning from social interactions between human individuals to physical interactions between robots and objects to mechanistic interactions among different components of an intelligent system. Despite their prevale ...

Discovering new materials is essential but challenging, time-consuming, and expensive. In many cases, simulations can be useful for estimating material properties. For many of the most interesting properties, however, simulations are infeasible because of ...

This paper addresses intra-client and inter-client covariate shifts in federated learning (FL) with a focus on the overall generalization performance. To handle covariate shifts, we formulate a new global model training paradigm and propose Federated Impor ...

We propose a method for adapting neural networks to distribution shifts at test-time. In contrast to training-time robustness mechanisms that attempt to anticipate and counter the shift, we create a closed-loop system and make use of test-time feedback sig ...

Machine learning (ML) models for molecules and materials commonly rely on a decomposition of the global target quantity into local, atom-centered contributions. This approach is convenient from a computational perspective, enabling large-scale ML-driven si ...

Despite their incredible performance, it is well reported that deep neural networks tend to be overoptimistic about their prediction confidence. Finding effective and efficient calibration methods for neural networks is therefore an important endeavour tow ...

The increasing availability of sensing techniques provides a great opportunity for engineers to design state estimation methods, which are optimal for the system under observation and the observed noise patterns. However, these patterns often do not fulfil ...

Learning-based outlier (mismatched correspondence) rejection for robust 3D registration generally formulates the outlier removal as an inlier/outlier classification problem. The core for this to be successful is to learn the discriminative inlier/outlier f ...

Outliers in discrete choice response data may result from misclassification and misreporting of the response variable and from choice behaviour that is inconsistent with modelling assumptions (e.g. random utility maximisation). In the presence of outliers, ...

Higher-order asymptotics provide accurate approximations for use in parametric statistical modelling. In this thesis, we investigate using higher-order approximations in two-specific settings, with a particular emphasis on the tangent exponential model. ...

The HST treasury programme BUFFALO provides extended wide-field imaging of the six Hubble Frontier Fields galaxy clusters. Here we present the combined strong and weak-lensing analysis of Abell 370, a massive cluster at z = 0.375. From the reconstructed to ...

Robust Generalization despite Distribution Shift via Minimum Discriminating Information

Chattez avec Graph Search

Exploiting the Signal-Leak Bias in Diffusion Models

Making Computer Vision Models Robust and Adaptive

Learning Robust and Adaptive Representations: from Interactions, for Interactions

Toward data-driven materials design: From atoms to pilot plants

Federated Learning under Covariate Shifts with Generalization Guarantees

Rapid Network Adaptation: Learning to Adapt Neural Networks Using Test-Time Feedback

Robustness of Local Predictions in Atomistic Machine Learning Models

Expectation consistency for calibration of neural networks

Regularization for distributionally robust state estimation and prediction

Robust Outlier Rejection for 3D Registration with Variational Bayes

Robust discrete choice models with t-distributed kernel errors

Higher Order Asymptotics: Applications to Satellite Conjunction and Boundary Problems

Beyond the ultradeep frontier fields and legacy observations (BUFFALO): a high-resolution strong plus weak-lensing view of Abell 370