Publication

Quasi-Global Momentum: Accelerating Decentralized Deep Learning on Heterogeneous Data

Related publications (60)

Graph Chatbot

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.

Deep Domain Adaptation in Earth Observation

Devis Tuia, Benjamin Alexander Kellenberger, Nicolas Courty

When applied to new datasets, acquired at different time moments, with different sensors or under different acquisition conditions, deep learning models might fail spectacularly. This is because they have learned from the data distribution observed during ...

Wiley2021

Oblivious Sketching of High-Degree Polynomial Kernels

Mikhail Kapralov, Amir Zandieh

Kernel methods are fundamental tools in machine learning that allow detection of non-linear dependencies between data without explicitly constructing feature vectors in high dimensional spaces. A major disadvantage of kernel methods is their poor scalabili ...

ASSOC COMPUTING MACHINERY2020

Advancing Deep Learning for Earth Sciences: From Hybrid Modeling to Interpretability

Devis Tuia

Machine learning and deep learning in particular have made a huge impact in many fields of science and engineering. In the last decade, advanced deep learning methods have been developed and applied to remote sensing and geoscientific data problems extensi ...

2020

AIDE: Accelerating image‐based ecological surveys with interactive machine learning

Devis Tuia, Benjamin Alexander Kellenberger

Ecological surveys increasingly rely on large‐scale image datasets, typically terabytes of imagery for a single survey. The ability to collect this volume of data allows surveys of unprecedented scale, at the cost of expansive volumes of photo‐interpretati ...

2020

Amatoxins are ribosomally synthesized and post-translationally modified bicyclic octapeptides biosynthesized by the deadly basidiomycete fungus Amanita phalloides. Amongst this group, alpha-amanitin is the most widely known toxin and is currently under inv ...

EPFL2020

Exponential Collapse Of Social Beliefs Over Weakly-Connected Heterogeneous Networks

Ali H. Sayed, Augusto José Rabelo Almeida Santos

We consider a distributed social learning problem where a network of agents is interested in selecting one among a finite number of hypotheses. The data collected by the agents might be heterogeneous, meaning that different sub-networks might observe data ...

IEEE2019

Statistical Physics Methods for Community Detection

Chun Lam Chan

This thesis is devoted to information-theoretic aspects of community detection. The importance of community detection is due to the massive amount of scientific data today that describes relationships between items from a network, e.g., a social network. I ...

EPFL2019

Backpropagation-Friendly Eigendecomposition

Pascal Fua, Mathieu Salzmann, Zheng Dang, Wei Wang, Yinlin Hu

Eigendecomposition (ED) is widely used in deep networks. However, the backpropagation of its results tends to be numerically unstable, whether using ED directly or approximating it with the Power Iteration method, particularly when dealing with large matri ...

NEURAL INFORMATION PROCESSING SYSTEMS (NIPS)2019

Wet Markets and Food Safety: TripAdvisor for Improved Global Digital Surveillance

Sharada Prasanna Mohanty

Background: Wet markets are markets selling fresh meat and produce. Wet markets are critical for food security and sustainable development in their respective regions. Due to their cultural significance, they attract numerous visitors and consequently gene ...

2019

Multichromatic calibration method and device

Dragos Constantin

A Multichromatic Calibration (MC) method of at least a spectral sensor which is one of a list comprising at least a spectrometer, a multispectral sensor, a hyperspectral sensor, a spectral camera, a color camera. The method comprises a. generating a plural ...

2019