Concept

Gaussian function

Related publications (280)

Entropy and mutual information in models of deep neural networks

Nicolas Macris, Florent Gérard Krzakala, Lenka Zdeborová, Jean François Emmanuel Barbier, Clément Dominique Luneau

We examine a class of stochastic deep learning models with a tractable method to compute information-theoretic quantities. Our contributions are three-fold: (i) we show how entropies and mutual informations can be derived from heuristic statistical physics ...

IOP PUBLISHING LTD2019

Adversarially Robust Optimization with Gaussian Processes

Volkan Cevher, Jonathan Mark Scarlett, Ilija Bogunovic

In this paper, we consider the problem of Gaussian process (GP) optimization with an added robustness requirement: The returned point may be perturbed by an adversary, and we require the function value to remain as high as possible even after this perturba ...

2018

Adversarially Robust Optimization with Gaussian Processes

Volkan Cevher, Jonathan Mark Scarlett, Ilija Bogunovic

NEURAL INFORMATION PROCESSING SYSTEMS (NIPS)2018

Learning Proximal Operators with Gaussian Processes

Colin Neil Jones, Georgios Stathopoulos, Xuan Truong Nghiem

Several distributed-optimization setups involve a group of agents coordinated by a central entity (coordinator), altogether operating in a collaborative framework. In such environments, it is often common that the agents solve proximal minimization problem ...

IEEE2018

Probing non-Gaussian stochastic gravitational wave backgrounds with LISA

Daniel Garcia Figueroa, Valerie Fiona Domcke

The stochastic gravitational wave background (SGWB) contains a wealth of information on astrophysical and cosmological processes. A major challenge of upcoming years will be to extract the information contained in this background and to disentangle the con ...

IOP PUBLISHING LTD2018

Benchmarking of Objective Quality Metrics for Colorless Point Clouds

Touradj Ebrahimi, Evangelos Alexiou

Recent advances in depth sensing and display technologies, along with the significant growth of interest for augmented and virtual reality applications, lay the foundation for the rapid evolution of applications that provide immersive experiences. In such ...

IEEE2018

Investigating Depth Domain Adaptation for Efficient Human Pose Estimation

Jean-Marc Odobez, Olivier Canévet, Michael Villamizar

Convolutional Neural Networks (CNN) are the leading models for human body landmark detection from RGB vision data. However, as such models require high computational load, an alternative is to rely on depth images which, due to their more simple nature, ca ...

2018

Real-Time Optimization of Uncertain Process Systems via Modifier Adaptation and Gaussian Processes

Dominique Bonvin, Colin Neil Jones, Timm Faulwasser, Harsh Ambarishkumar Shukla

In the context of static real-time optimization, the use of measurements allows dealing with uncertainty in the form of plant-model mismatch and disturbances. Modifier adaptation (MA) is a measurement-based scheme that uses first-order corrections to the m ...

IEEE2018

Stochastic vs. sensitivity-based integral parameter and nuclear data adjustments

Andreas Pautz, Mathieu Hursin, Dimitri Rochman, Daniel Jerôme Siefman

Developments in data assimilation theory allow to adjust integral parameters and cross sections with stochastic sampling. This work investigates how two stochastic methods, MOCABA and BMC, perform relative to a sensitivity-based methodology called GLLS. St ...

SPRINGER HEIDELBERG2018

Machine-learning the configurational energy of multicomponent crystalline solids

Anirudh Raju Natarajan

Machine learning tools such as neural networks and Gaussian process regression are increasingly being implemented in the development of atomistic potentials. Here, we develop a formalism to leverage such non-linear interpolation tools in describing propert ...

Springer Nature2018

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.