Decentralized Decision-Making Over Multi-Task Networks

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.

This paper introduces a new algorithm for consensus optimization in a multi-agent network, where all agents collaboratively find a minimizer for the sum of their private functions. All decentralized algorithms rely on communications between adjacent nodes. ...

Many important problems in contemporary machine learning involve solving highly non- convex problems in sampling, optimization, or games. The absence of convexity poses significant challenges to convergence analysis of most training algorithms, and in some ...

Progress in engineering systems is the result of the combined improvements of technology and design methods. It is often a cyclic process, stimulated by success and failure. When the innovation loop stalls in producing effective progress, a change in parad ...

Recent studies suggested that long-lived photooxidants (LLPO), which are reactive intermediates formed during irradiation of dissolved organic matter (DOM), may consist of phenoxyl radicals derived from phenolic moieties of the DOM. Besides the well-studie ...

This work presents and studies a distributed algorithm for solving optimization problems over networks where agents have individual costs to minimize subject to subspace constraints that require the minimizers across the network to lie in a low-dimensional ...

The moisture resistance of friction-welded wood joints can be improved by applying bio-based bonding additives. Several biomolecules including tannic acid, organosolv lignin from hardwood, kraft lignin from softwood, and derivates thereof, were investigate ...

Improving the energy sustainability of our cities involves the integration of multiple renewable energy technologies into existing energy infrastructure, stretching the capabilities of traditional energy systems to the limit. To consider the transition tak ...

Convolutional neural networks, as most artificial neural networks, are frequently viewed as methods different in essence from kernel-based methods. In this work we translate several classical convolutional neural networks into kernel-based counterparts. Ea ...

This work studies the robustness certification problem of neural network models, which aims to find certified adversary-free regions as large as possible around data points. In contrast to the existing approaches that seek regions bounded uniformly along a ...

To build biophysically detailed models of brain cells, circuits, and regions, a data-driven approach is increasingly being adopted. This helps to obtain a simulated activity that reproduces the experimentally recorded neural dynamics as faithfully as possi ...

The significant progress that has been made in recent years both in hardware implementations and in numerical computing has rendered real-time optimization-based control a viable option when it comes to advanced industrial applications. At the same time, t ...

Explainable Artificial Intelligence (XAI) plays a crucial role in enabling human understanding and trust in deep learning systems, often defined as determining which features are most important to a model's prediction. As models get larger, more ubiquitous ...

In recent years, Machine Learning based Computer Vision techniques made impressive progress. These algorithms proved particularly efficient for image classification or detection of isolated objects. From a probabilistic perspective, these methods can predi ...

When humans or animals perform an action that led to a desired outcome, they show a tendency to repeat it. The mechanisms underlying learning from past experience and adapting future behavior are still not fully understood. In this thesis, I study how huma ...

Agent-based simulations have been widely applied in many disciplines, by scientists and engineers alike. Scientists use agent-based simulations to tackle global problems, including alleviating poverty, reducing violence, and predicting the impact of pandem ...

We address multi-robot safe mission planning in uncertain dynamic environments. This problem arises in several applications including safety-critical exploration, surveillance, and emergency rescue missions. Computation of a multi-robot optimal control pol ...

One-way electric vehicle carsharing systems are receiving increasing attention due to their mobility, environmental, and societal benefits. One of the major issues faced by the operators of these systems is the optimization of the relocation operations of ...

We present a method to control individual high-voltage actuators in an array using microfabricated photoconductive switches and a light projection system, thus overcoming the challenges of on-chip control at high voltages. Such switching capabilities go be ...

The increasing popularity of parametric design tools goes hand in hand with the use of building performance simulation (BPS) tools from the early design phase. However, current methods require a significant computational time and a high number of parameter ...

Many medical image analysis tasks require complex learning strategies to reach a quality of image-based decision support that is sufficient in clinical practice. The analysis of medical texture in tomographic images, for example of lung tissue, is no excep ...

Decentralized Decision-Making Over Multi-Task Networks

Chattez avec Graph Search

Walkman: A Communication-Efficient Random-Walk Algorithm for Decentralized Optimization

Convergence without Convexity: Sampling, Optimization, and Games

Cyclical Progress in Design and Technology

Impact of chlorination and ozonation of dissolved organic matter on its photo-induced production of long-lived photooxidants and excited triplet states

Distributed Learning over Networks under Subspace Constraints

The influence of wood surface treatments with different biomolecules on dry and wet strength of linear friction welded joints

Modeling and Assessment of Urban Energy Systems

Revisiting Convolutional Neural Networks from the Viewpoint of Kernel-Based Methods

On Certifying Non-Uniform Bounds against Adversarial Attacks

Online interoperable resources for building hippocampal neuron models via the Hippocampus Hub

Distributed Optimization and Control using Operator Splitting Methods

The future of human-centric eXplainable Artificial Intelligence (XAI) is not post-hoc explanations

Mean-Field methods for Structured Deep-Learning in Computer Vision

One-shot learning and eligibility traces in sequential decision making

Generalizing Bulk-Synchronous Parallel Processing for Data Science: From Data to Threads and Agent-Based Simulations

Multi-robot task allocation for safe planning against stochastic hazard dynamics

An integrated optimization-simulation framework for vehicle and personnel relocations of electric carsharing systems with reservations

Photoconductive Switching Of A High-Voltage Actuator Array

Integrating urban energy simulation in a parametric environment: a Grasshopper interface for CitySim

Optimized Distributed Hyperparameter Search and Simulation for Lung Texture Classification in CT Using Hadoop