Distributed Inference Over Networks Under Subspace Constraints

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.

The application of kernel-based Machine Learning (ML) techniques to discrete choice modelling using large datasets often faces challenges due to memory requirements and the considerable number of parameters involved in these models. This complexity hampers ...

Sharing data across institutions for genome-wide association studies (GWAS) would enhance the discovery of genetic variation linked to health and disease1,2. However, existing data-sharing regulations limit the scope of such collaborations3. Although crypt ...

A de facto standard approach in solving computer vision tasks is to use a common high-resolution camera and choose its placement on an agent based on human intuition. On the other hand, extremely simple and well-designed visual sensors found throughout nat ...

We develop a model-free approach to optimally control stochastic, Markovian systems subject to a reach-avoid constraint. Specifically, the state trajectory must remain within a safe set while reaching a target set within a finite time horizon. Due to the t ...

Deep learning has shown remarkable potential for industrial applications, particularly in predictive maintenance and condition monitoring. A key challenge in this domain is prognostics, specifically predicting the Remaining Useful Life (RUL) of assets - a ...

Machine learning and artificial intelligence methods have achieved remarkable success, matching and even surpassing human capabilities in various complex tasks. However, many demonstrations have generally neglected a critical part of the intelligence that ...

In the field of choice modeling, the availability of ever-larger datasets has the potential to significantly expand our understanding of human behavior, but this prospect is limited by the poor scalability of discrete choice models (DCMs): as sample sizes ...

The analysis of the acceleration behavior of gradient-based eigensolvers with preconditioning presents a substantial theoretical challenge. In this work, we present a novel framework for preconditioning on Riemannian manifolds and introduce a metric, the l ...

Within the context of contemporary machine learning problems, efficiency of optimization process depends on the properties of the model and the nature of the data available, which poses a significant problem as the complexity of either increases ad infinit ...

Decentralized learning (DL) is an emerging approach that enables nodes to collaboratively train a machine learning model without sharing raw data. In many application domains, such as healthcare, this approach faces challenges due to the high level of hete ...

Collaborative learning algorithms, such as distributed SGD (or D-SGD), are prone to faulty machines that may deviate from their prescribed algorithm because of software or hardware bugs, poisoned data or malicious behaviors. While many solutions have been ...

The variational approach is a cornerstone of computational physics, considering both conventional and quantum computing computational platforms. The variational quantum eigensolver algorithm aims to prepare the ground state of a Hamiltonian exploiting para ...

Non-convex constrained optimization problems have become a powerful framework for modeling a wide range of machine learning problems, with applications in k-means clustering, large- scale semidefinite programs (SDPs), and various other tasks. As the perfor ...

An integer linear program is a problem of the form max{c^T x : Ax=b, x >= 0, x integer}, where A is in Z^(n x m), b in Z^m, and c in Z^n. Solving an integer linear program is NP-hard in general, but there are several assumptions for which it becomes fixed ...

In this manuscript, we investigate the problem of how two-layer neural networks learn features from data, and improve over the kernel regime, after being trained with a single gradient descent step. Leveraging the insight from (Ba et al., 2022), we model t ...

Distributed systems designers typically strive to improve performance and preserve availability despite failures or attacks; but, when strong consistency is also needed, they encounter fundamental limitations. The bottleneck is in replica coordination, whi ...

While momentum-based accelerated variants of stochastic gradient descent (SGD) are widely used when training machine learning models, there is little theoretical understanding on the generalization error of such methods. In this work, we first show that th ...

In this thesis we present and analyze approximation algorithms for three different clustering problems. The formulations of these problems are motivated by fairness and explainability considerations, two issues that have recently received attention in the ...

In this thesis, we study two closely related directions: robustness and generalization in modern deep learning. Deep learning models based on empirical risk minimization are known to be often non-robust to small, worst-case perturbations known as adversari ...

This paper presents a novel distributed approach for solving AC power flow (PF) problems. The optimization problem is reformulated into a distributed form using a communication structure corresponding to a hypergraph, by which complex relationships between ...

Distributed Inference Over Networks Under Subspace Constraints

Chattez avec Graph Search

Scalable kernel logistic regression with Nyström approximation: Theoretical analysis and application to discrete choice modelling

Secure and federated genome-wide association studies for biobank-scale datasets

How Far Can a 1-Pixel Camera Go? Solving Vision Tasks Using Photoreceptors and Computationally Designed Visual Morphology

A learning-based approach to stochastic optimal control under reach-avoid constraint

Overcoming Distribution Shifts and Imbalance Challenges in Representation Learning for Deep Regression Models

Sequential Reasoning with Socially Caused Beliefs

Stochastic adaptive resampling for the estimation of discrete choice models

Riemannian acceleration with preconditioning for symmetric eigenvalue problems

Universal and adaptive methods for robust stochastic optimization

Fair Decentralized Learning

Robust Collaborative Learning with Linear Gradient Overhead

Phenomenological theory of variational quantum ground-state preparation

Augmented Lagrangian Methods for Provable and Scalable Machine Learning

Results on Sparse Integer Programming and Geometric Independent Sets

Asymptotics of feature learning in two-layer networks after one gradient-step

Building Strongly-Consistent Systems Resilient to Failures, Partitions, and Slowdowns

On the Generalization of Stochastic Gradient Descent with Momentum

Fairness and Explainability in Clustering Problems

Understanding generalization and robustness in modern deep learning

Hypergraph-Based Fast Distributed AC Power Flow Optimization