Efficient Variance-Reduced Learning Over Multi-Agent Networks

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.

Demographic fairness or equity is a crucial aspect of machine learning models, particularly in critical domains such as healthcare, where errors can have severe consequences. A fair model avoids making distinctions between groups with different sensitive o ...

A payment channel network is a blockchain-based overlay mechanism that allows parties to transact more efficiently than directly using the blockchain. These networks are composed of payment channels that carry transactions between pairs of users. Due to it ...

The unifying theme of this thesis are decision trees. Given a boolean function

f

and an input

x

, a decision tree computes the value

f(x)

by repeatedly querying bits of

x

. Our work is two-fold. On one hand, we investigate direct sums and other relat ...

Laser material processing (LMP) has revolutionized modern manufacturing, emerging as a cornerstone technology valued for its precision, speed, and versatility, especially in high-stakes sectors like aerospace, automotive, and medical device production. Des ...

Our understanding of the generalization capabilities of neural networks (NNs) is still incomplete. Prevailing explanations are based on implicit biases of gradient descent (GD) but they cannot account for the capabilities of models from gradient-free metho ...

This work studies the learning process over social networks under partial and random information sharing. In traditional social learning models, agents exchange full belief information with each other while trying to infer the true state of nature. We stud ...

Beliefs inform the behaviour of forward-thinking agents in complex environments. Recently, sequential Bayesian inference has emerged as a mechanism to study belief formation among agents adapting to dynamical conditions. However, we lack critical theory to ...

Reinforcement learning (RL) has shown promising results for real-time control systems, including the domain of plasma magnetic control. However, there are still significant drawbacks compared to traditional feedback control approaches for magnetic confinem ...

Accurate human trajectory prediction is crucial for applications such as autonomous vehicles, robotics, and surveillance systems. Yet, existing models often fail to fully leverage the non-verbal social cues human subconsciously communicate when navigating ...

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 this paper, we propose a novel approach that employs kinetic equations to describe the collective dynamics emerging from graph-mediated pairwise interactions in multi-agent systems. We formally show that for large graphs and specific classes of interact ...

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 ...

Extracting maximal information from experimental data requires access to the likelihood function, which however is never directly available for complex experiments like those performed at high energy colliders. Theoretical predictions are obtained in this ...

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 ...

The field of biometrics, and especially face recognition, has seen a wide-spread adoption the last few years, from access control on personal devices such as phones and laptops, to automated border controls such as in airports. The stakes are increasingly ...

Earth scientists study a variety of problems with remote sensing data, but they most often consider them in isolation from each other, which limits information flows across disciplines. In this work, we present METEOR, a meta-learning methodology for Earth ...

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 ...

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 ...

The increasing complexity of transformer models in artificial intelligence expands their computational costs, memory usage, and energy consumption. Hardware acceleration tackles the ensuing challenges by designing processors and accelerators tailored for t ...

Machine learning (ML) enables artificial intelligent (AI) agents to learn autonomously from data obtained from their environment to perform tasks. Modern ML systems have proven to be extremely effective, reaching or even exceeding human intelligence. Altho ...

Efficient Variance-Reduced Learning Over Multi-Agent Networks

Chat with Graph Search

Optimizing fairness and utility in healthcare machine learning models

Pricing for Routing and Flow-control in Payment Channel Networks

The Power of Decision Trees for Composition and Search Problems

Toward Autonomous Laser Manufacturing: Solving Key Challenges in Optimization, Monitoring, and Control

Neural Redshift: Random Networks are not Random Functions

Social Opinion Formation and Decision Making Under Communication Trends

Stochastic pairwise preference convergence in Bayesian agents

Towards practical reinforcement learning for tokamak magnetic control

Social-Transmotion: Promptable Human Trajectory Prediction

Optimization Algorithms for Decentralized, Distributed and Collaborative Machine Learning

Network-based kinetic models: Emergence of a statistical description of the graph topology

Understanding generalization and robustness in modern deep learning

Boosting likelihood learning with event reweighting

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

Performing and Detecting Backdoor Attacks on Face Recognition Algorithms

Meta-learning to address diverse Earth observation problems across resolutions

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

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

Accelerator-driven Data Arrangement to Minimize Transformers Run-time on Multi-core Architectures

Few-shot Learning for Efficient and Effective Machine Learning Model Adaptation