Adaptation and Learning Over Networks Under Subspace Constraints-Part I: Stability Analysis

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.

Neural Networks (NNs), renowned for their universal approximation capabilities, have proven well-suited for parametrizing nonlinear control policies and modeling complex processes from available data. However, several NN architectures are physics-agnostic, ...

Emotion is an increasingly important concept in ethics, education, and engineering. It is also important for the intersection of these three domains: engineering ethics education. Despite extensive research being conducted independently in each field, ther ...

We present a general variational framework for the training of freeform nonlinearities in layered computational architectures subject to some slope constraints. The regularization that we add to the traditional training loss penalizes the second-order tota ...

First-generation students (FGS) are traditionally underrepresented in higher education, including engineering education. To ensure equity in access and success in engineering, and thereby ensure that we educate responsible engineers who come from a diversi ...

This paper offers a new algorithm to efficiently optimize scheduling decisions for dial-a-ride problems (DARPs), including problem variants considering electric and autonomous vehicles (e-ADARPs). The scheduling heuristic, based on linear programming theor ...

We introduce an algorithm to reconstruct a mesh from discrete samples of a shape's Signed Distance Function (SDF). A simple geometric reinterpretation of the SDF lets us formulate the problem through a point cloud, from which a surface can be extracted wit ...

Distributed learning is the key for enabling training of modern large-scale machine learning models, through parallelising the learning process. Collaborative learning is essential for learning from privacy-sensitive data that is distributed across various ...

In light of the challenges posed by climate change and the goals of the Paris Agreement, electricity generation is shifting to a more renewable and decentralized pattern, while the operation of systems like buildings is increasingly electrified. This calls ...

Modern optimization is tasked with handling applications of increasingly large scale, chiefly due to the massive amounts of widely available data and the ever-growing reach of Machine Learning. Consequently, this area of research is under steady pressure t ...

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 ...

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 the current era of big data, aggregation queries on high-dimensional datasets are frequently utilized to uncover hidden patterns, trends, and correlations critical for effective business decision-making. Data cubes facilitate such queries by employing p ...

Sample efficiency is a fundamental challenge in de novo molecular design. Ideally, molecular generative models should learn to satisfy a desired objective under minimal calls to oracles (computational property predictors). This problem becomes more apparen ...

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 ...

We consider the problem of learning to play a repeated contextual game with unknown reward and unknown constraints functions. Such games arise in applications where each agent’s action needs to belong to a feasible set, but the feasible set is a priori unk ...

The advent of comprehensive synaptic wiring diagrams of large neural circuits has created the field of connectomics and given rise to a number of open research questions. One such question is whether it is possible to reconstruct the information stored in ...

The scale and pervasiveness of the Internet make it a pillar of planetary communication, industry and economy, as well as a fundamental medium for public discourse and democratic engagement. In stark contrast with the Internet's decentralized infrastructur ...

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 ...

Modern machine learning (ML) models are capable of impressive performances. However, their prowess is not due only to the improvements in their architecture and training algorithms but also to a drastic increase in computational power used to train them.|S ...

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 ...

Adaptation and Learning Over Networks Under Subspace Constraints-Part I: Stability Analysis

Chat with Graph Search

Dependable learning and control through Neural ODEs

Emotions in Engineering Ethics Education: Systematic Review and Ways Forward

Controlled learning of pointwise nonlinearities in neural-network-like architectures

The Road Not Taken: How First-Generation Students Differ in Their Postgraduate Educational Paths

A ride time-oriented scheduling algorithm for dial-a-ride problems

Reach For the Arcs: Reconstructing Surfaces from SDFs via Tangent Points

Optimization Algorithms for Decentralized, Distributed and Collaborative Machine Learning

Quantifying the Unknown: Data-Driven Approaches and Applications in Energy Systems

Scalable constrained optimization

Understanding generalization and robustness in modern deep learning

Fairness and Explainability in Clustering Problems

Interactive-time Exploration, Querying, and Analysis of Large High-dimensional Datasets

Augmented Memory: Sample-Efficient Generative Molecular Design with Reinforcement Learning

Stochastic adaptive resampling for the estimation of discrete choice models

Multi-Agent Learning in Contextual Games under Unknown Constraints

Bayesian reconstruction of memories stored in neural networks from their connectivity

Planetary-Scale Byzantine Fault Tolerance

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

Byzantine-Resilient Learning Beyond Gradients: Distributing Evolutionary Search

Hypergraph-Based Fast Distributed AC Power Flow Optimization