Byzantine Machine Learning Made Easy By Resilient Averaging of Momentums

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.

Atomistic machine learning has revolutionized atomistic modeling. Traditionally, molecular dynamics simulations relied on classical force fields or electronic structure calculations like Density Functional Theory. Classical force fields are fast but less p ...

Recent years have witnessed a growing integration of automatic control into a wide range of cyber-physical systems, including electrical grids and autonomous transportation networks. These systems operate in uncertain and dynamic environments, exhibit comp ...

Federated Learning (FL) enables end-user devices to collaboratively train ML models without sharing raw data, thereby preserving data privacy. In FL, a central parameter server coordinates the learning process by iteratively aggregating the trained models ...

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 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 ...

Modern neuroscience research is generating increasingly large datasets, from recording thousands of neurons over long timescales to behavioral recordings of animals spanning weeks, months, or even years. Despite a great variety in recording setups and expe ...

The increasing availability of multimodal data from electronic health records (EHR) has paved the way for deep learning methods to improve diagnosis accuracy. However, deep learning models are data-driven, requiring large-scale datasets to achieve high gen ...

Driven by the need for more efficient and seamless integration of physical models and data, physics -informed neural networks (PINNs) have seen a surge of interest in recent years. However, ensuring the reliability of their convergence and accuracy remains ...

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 ...

Traditional example-based learning methods are often limited by static, expert-created content. Hence, they face challenges in scalability, engagement, and effectiveness, as some learners might struggle to relate to the examples or find them relevant. To a ...

Recent developments in neural architecture search (NAS) emphasize the significance of considering robust architectures against malicious data. However, there is a notable absence of benchmark evaluations and theoretical guarantees for searching these robus ...

In this thesis we explore the applications of projective geometry, a mathematical theory of the relation between 3D scenes and their 2D images, in modern learning-based computer vision systems. This is an interesting research question which contradicts the ...

Modern automobiles are equipped with advanced computing capabilities, allowing them to become powerful computing units capable of processing a large amount of data and training machine learning models. However, machine learning algorithms typically require ...

Recent advancements in deep learning have revolutionized 3D computer vision, enabling the extraction of intricate 3D information from 2D images and video sequences. This thesis explores the application of deep learning in three crucial challenges of 3D com ...

In the rapidly evolving landscape of machine learning research, neural networks stand out with their ever-expanding number of parameters and reliance on increasingly large datasets. The financial cost and computational resources required for the training p ...

We study a class of stochastic nonconvex optimization in the form of min(x is an element of X) F(x) := E-xi[f (phi(x, xi))], that is, F is a composition of a convex function f and a random function phi. Leveraging an (implicit) convex reformulation via a v ...

The capabilities of deep learning systems have advanced much faster than our ability to understand them. Whilst the gains from deep neural networks (DNNs) are significant, they are accompanied by a growing risk and gravity of a bad outcome. This is troubli ...

Current transformer-based skeletal action recognition models tend to focus on a limited set of joints and low-level motion patterns to predict action classes. This results in significant performance degradation under small skeleton perturbations or changin ...

Machine learning has provided a means to accelerate early-stage drug discovery by combining molecule generation and filtering steps in a single architecture that leverages the experience and design preferences of medicinal chemists. However, designing mach ...

Deep learning has emerged as a promising avenue for automatic mapping, demonstrating high efficacy in land cover categorization through various semantic segmentation models. Nonetheless, the practical deployment of these models encounters important challen ...

Byzantine Machine Learning Made Easy By Resilient Averaging of Momentums

Chat with Graph Search

Advancing understanding and practical performance of machine learning interatomic potentials

Optimal Control under Uncertainty: From Regret Minimization to Distributional Robustness

Practical Federated Learning without a Server

Optimization Algorithms for Decentralized, Distributed and Collaborative Machine Learning

Understanding generalization and robustness in modern deep learning

Robust machine learning for neuroscientific inference

CARER - ClinicAl Reasoning-Enhanced Representation for Temporal Health Risk Prediction

Residual-based attention in physics-informed neural networks

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

GELEX: Generative AI-Hybrid System for Example-Based Learning

Robust NAS under adversarial training: benchmark, theory, and beyond

Incorporating Projective Geometry into Deep Learning

Hierarchical Federated Learning in MEC Networks with Knowledge Distillation

Advancing Self-Supervised Deep Learning for 3D Scene Understanding

Random matrix methods for high-dimensional machine learning models

Efficient Algorithms for a Class of Stochastic Hidden Convex Optimization and Its Applications in Network Revenue Management

Safe Deep Neural Networks

MaskCLR: Attention-Guided Contrastive Learning for Robust Action Representation Learning

Machine learning-aided generative molecular design

Land Cover Mapping From Multiple Complementary Experts Under Heavy Class Imbalance