Theoretical characterization of uncertainty in high-dimensional linear classification

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

This paper studies the problem of learning computable functions in the limit by extending Gold's inductive inference framework to incorporate computational observations and restricted input sources. Complimentary to the traditional Input-Output Observation ...

Correctly representing convective precipitation remains a long-standing problem in climate models, due to its highly parameterized nature and unclear role of drivers interacting over a wide range of spatial scales. We analyze and compare simulations of Glo ...

The problem of identifying the best answer among a collection of items having real-valued distribution is well-understood. Despite its practical relevance for many applications, fewer works have studied its extension when multiple and potentially conflict ...

This thesis focuses on the development of advanced algorithmic techniques, primarily Markov Chain Monte Carlo (MCMC) methods, and message passing algorithms, to tackle high-dimensional optimization and inference problems. The algorithms used have a probabi ...

For Graph Neural Networks, oversmoothing denotes the homogenization of vertex embeddings as the number of layers increases. To better understand this phenomenon, we study community detection with a linearized Graph Convolutional Network on the Contextual S ...

Since the 80s, indoor radon, a radioactive noble gas, became a public health concern, with the WHO declaring it a carcinogen in 1987. Accurate radon measurement is crucial for estimating exposure and shaping policies to reduce lung cancer. Nowadays, the re ...

Denoising Diffusion Probabilistic Models (DDPMs) exhibit remarkable capabilities in image generation, with studies suggesting that they can generalize by composing latent factors learned from the training data. In this work, we go further and study DDPMs t ...

Partial differential equations can model diverse physical phenomena including heat diffusion, incompressible flows, and electrostatic potentials. Given a description of an object's boundary and interior, traditional methods solve such PDEs by densely meshi ...

It is widely believed that the success of deep networks lies in their ability to learn a meaningful representation of the features of the data. Yet, understanding when and how this feature learning improves performance remains a challenge. For example, it ...

Indonesia is located in a high-seismic-risk region with a significant number of non-engineered houses, which typically have a higher risk during earthquakes. Due to the wide variety of differences even among parameters within one building typology, it is d ...

Multi-view approaches to people-tracking have the potential to better handle occlusions than single-view ones in crowded scenes. They often rely on the tracking-by-detection paradigm, which involves detecting people first and then connecting the detections ...

Structured and grounded representation of text is typically formalized by closed information extraction, the problem of extracting an exhaustive set of (subject, relation, object) triplets that are consistent with a predefined set of entities and relations ...

New extensions and features to the remote laboratories currently used for undergraduate courses in automatic control laboratory at the School of Engineering of University of Applied Sciences and Arts Western Switzerland are presented. This paper shows how ...

Parental Training is a methodology where therapists teach caregivers how to train their kids in specific behaviors practicing. It can be used in verbal behavior acquisition for childrenwith autismmediated by the parents. In this paper, we are presenting an ...

This article introduces a new class of models for multiple networks. The core idea is to parameterize a distribution on labeled graphs in terms of a Frechet mean graph (which depends on a user-specified choice of metric or graph distance) and a parameter t ...

This paper presents a novel deep learning-based travel behaviour choice model. Our proposed Residual Logit (ResLogit) model formulation seamlessly integrates a Deep Neural Network (DNN) architecture into a multinomial logit model. Recently, DNN models such ...

Theoretical characterization of uncertainty in high-dimensional linear classification

Chat with Graph Search

Learning Algorithms in the Limit

A causal intercomparison framework unravels precipitation drivers in Global Storm-Resolving Models

Bandit Pareto Set Identification with Posterior Sampling

Advances in Algorithms for Sampling, Optimization and Inference in Disordered Systems

Optimal performance of Graph Convolutional Networks on the Contextual Stochastic Block Model

Assessment of methods for radon detection in buildings

Going beyond Compositions, DDPMs Can Produce Zero-Shot Interpolations

Solving Inverse PDE Problems using Grid-Free Monte Carlo Estimators

Learning sparse features can lead to overfitting in neural networks

Gaussian Process Regression for Seismic Fragility Assessment: Application to Non-Engineered Residential Buildings in Indonesia

Multi-view Tracking UsingWeakly Supervised Human Motion Prediction

GenIE: Generative Information Extraction

Interactive Lab Experimentation and Simulation Tools for Remote Laboratories

Supporting Therapists' Assessment in Parent-Mediated Training Through Autonomous Data Collection

Modeling Network Populations via Graph Distances

ResLogit: A residual neural network logit model for data-driven choice modelling