Publication

Stochastic distributed learning with gradient quantization and double-variance reduction

Related publications (62)

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.

Ultra low power design of hardware efficient CS-Based compression scheme in WBSN

David Atienza Alonso, Pierre Vandergheynst, Hossein Mamaghanian

Ultra-low power optimization is a challenging research topic in the de- sign of the sensor front-ends, especially in the area of Wireless Body Sensor Nodes (WBSN), where a limited amount of power and hardware resources are available. In this talk, I analyz ...

2014

Obstructions to regularity in the classical Monge problem

Maria Colombo

We provide counterexamples to regularity of optimal maps in the classical Monge problem under various assumptions on the initial data. Our construction is based on a variant of the counterexample in [10] to Lipschitz regularity of the monotone optimal map ...

2014

A global existence result for the semigeostrophic equations in three dimensional convex domains

Maria Colombo

Exploiting recent regularity estimates for the Monge-Ampère equation, under some suitable assumptions on the initial data we prove global-in-time existence of Eulerian distributional solutions to the semigeostrophic equations in 3-dimensional convex domain ...

2014

A Global Existence Result for the Semigeostrophic Equations in Three Dimensional Convex Domains

Maria Colombo

Exploiting recent regularity estimates for the Monge-Ampere equation, under some suitable assumptions on the initial data we prove global in-time existence of Eulerian distributional solutions to the semigeostrophic equations in 3-dimensional convex domain ...

2014

Lossy source coding via spatially coupled LDGM ensembles

Rüdiger Urbanke, Nicolas Macris, Vahid Aref, Marc Vuffray

We study a new encoding scheme for lossy source compression based on spatially coupled low-density generatormatrix codes. We develop a belief-propagation guided-decimation algorithm, and show that this algorithm allows to approach the optimal distortion of ...

Ieee2012

Approaches to Conditional Risk

Damir Filipovic

We present and compare two different approaches to conditional risk measures. One approach draws from convex analysis in vector spaces and presents risk measures as functions on Lp spaces, while the other approach utilizes module-based convex analysis wher ...

2012

Data compression on the sphere

Yves Wiaux, Jason Douglas McEwen

Large data-sets defined on the sphere arise in many fields. In particular, recent and forthcoming observations of the anisotropies of the cosmic microwave background (CMB) made on the celestial sphere contain approximately three and fifty mega-pixels respe ...

Indian Academy of Sciences2011

Performance analysis of VP8 image and video compression based on subjective evaluations

Touradj Ebrahimi, Francesca De Simone, Jong Seok Lee, Lutz Goldmann

Today, several alternatives for compression of digital pictures and video sequences exist to choose from. Beside internationally recognized standard solutions, open access options like the VP8 image and video compression have recently appeared and are gain ...

Spie-Int Soc Optical Engineering, Po Box 10, Bellingham, Wa 98227-0010 Usa2011

Polar Codes are Optimal for Lossy Source Coding

Rüdiger Urbanke, Satish Babu Korada

We consider lossy source compression of a binary symmetric source using polar codes and the low-complexity successive encoding algorithm. It was recently shown by Arikan that polar codes achieve the capacity of arbitrary symmetric binary-input discrete mem ...

Institute of Electrical and Electronics Engineers2010

Netscope: Practical Network Loss Tomography

Patrick Thiran, Xuan Hung Nguyen, Maciej Kurant, Denisa Gabriela Ghita

We present Netscope, a tomographic technique that infers the loss rates of network links from unicast end-to-end measurements. Netscope uses a novel combination of first- and second-order moments of end-to-end measurements to identify and characterize the ...

Ieee Service Center, 445 Hoes Lane, Po Box 1331, Piscataway, Nj 08855-1331 Usa2010