Opendata, web and dolomites

time-data SIGNED

Time-Data Trade-Offs in Resource-Constrained Information and Inference Systems

Total Cost €

0

EC-Contrib. €

0

Partnership

0

Views

0

 time-data project word cloud

Explore the words cloud of the time-data project. It provides you a very rough idea of what is the project "time-data" about.

science    false    algorithms    communications    imaging    area    input    prototype    establishing    power    samples    models    poses    running    theory    characterizing    geometric    materials    tools    massive    sampling    circuit    expanding    resource    systematically    dogma    generate    obtain    mathematical    captured    data    time    conversion    scientific    limited    building    basic    sizes    shown    trade    confront    technological    supports    universal    energy    discovery    feasibility    offs    framework    analogous    fundamental    hardware    analog    acquisition    off    computational    algorithm    domains    rigorous    optimality    relative    perspective    optimize    demonstrates    too    broad    size    numerical    engineering    primal    crucially    tandem    interdisciplinary    dual    slowly    infancy    accelerating    flexibility    computation    traded    solutions    foundations    estimators    goals    treat    precision    unified    medical    specialized    hence    learning    substantial    statistical    govern   

Project "time-data" data sheet

The following table provides information about the project.

Coordinator
ECOLE POLYTECHNIQUE FEDERALE DE LAUSANNE 

Organization address
address: BATIMENT CE 3316 STATION 1
city: LAUSANNE
postcode: 1015
website: www.epfl.ch

contact info
title: n.a.
name: n.a.
surname: n.a.
function: n.a.
email: n.a.
telephone: n.a.
fax: n.a.

 Coordinator Country Switzerland [CH]
 Total cost 1˙931˙574 €
 EC max contribution 1˙931˙574 € (100%)
 Programme 1. H2020-EU.1.1. (EXCELLENT SCIENCE - European Research Council (ERC))
 Code Call ERC-2016-COG
 Funding Scheme ERC-COG
 Starting year 2017
 Duration (year-month-day) from 2017-09-01   to  2022-08-31

 Partnership

Take a look of project's partnership.

# participants  country  role  EC contrib. [€] 
1    ECOLE POLYTECHNIQUE FEDERALE DE LAUSANNE CH (LAUSANNE) coordinator 1˙931˙574.00

Map

 Project objective

Massive data poses a fundamental challenge to learning algorithms, which is captured by the following computational dogma: The running time of an algorithm increases with the size of its input data. The available computational power, however, is growing slowly relative to data sizes. Hence, large-scale problems of interest require increasingly more time to solve. Our recent research demonstrates that this dogma is false in general, and supports an emerging perspective: Data should be treated as a resource that can be traded off with other resources such as running time. For data acquisition and communications, we have also shown related sampling, energy, and circuit area trade-offs. A detailed understanding of time-data and other analogous trade-offs, however, requires interdisciplinary studies that are currently in their infancy even for basic system models. Existing approaches are too specialized, and crucially, they only aim at establishing a trade-off, but not characterizing its optimality or its technological feasibility. TIME-DATA will confront these challenges by building unified mathematical foundations on how we generate data via sampling, how we set up learning objectives that govern our fundamental goals, and how we optimize these goals to obtain numerical solutions. We will demonstrate our rigorous theory with task-specific, end-to-end trade-offs (e.g., samples, power, computation, and statistical precision) in broad domains, by not only building prototype analog-to-information conversion hardware, but also accelerating scientific and medical imaging, and engineering new tools of discovery in materials science. Our goal of systematically understanding and expanding on this emerging perspective is ambitious: Our mathematical sampling framework, in tandem with new universal primal-dual algorithms and geometric estimators, are expected to change the way we treat data in information systems, promising substantial flexibility in the use of limited resources.

 Publications

year authors and title journal last update
List of publications.
2019 A. Yurtsever, S. Sra, V. Cevher
Conditional Gradient Methods via Stochastic Path-Integrated Differential Estimator
published pages: 7282-7291, ISSN: , DOI:
Proceedings of IEEE International Conference on Machine Learning (ICML)’2019 Once a year in PMLR 97 2020-04-01
2019 Locatello, Francesco; Yurtsever, Alp; Fercoq, Olivier; Cevher, Volkan
Stochastic Frank-Wolfe for Composite Convex Minimization
published pages: , ISSN: , DOI:
Proceedings of Conference on Neural Information Processing Systems (NeurIPS)’2019 once a year 2020-04-01
2019 M.F. Sahin, A. Eftekhari, A. Alacaoglu, F. Latorre, V. Cevher
An Inexact Augmented Lagrangian Framework for Nonconvex Optimization with Nonlinear Constraints
published pages: , ISSN: , DOI:
Proceedings of Conference on Neural Information Processing Systems (NeurIPS)’2019 once a yeaer 2020-04-01
2020 F. Latorre, P. Rolland, V. Cevher
Lipschitz constant estimation for Neural Networks via sparse polynomial optimization
published pages: , ISSN: , DOI:
Proceedings of International Conference on Learning Representations (ICLR)’2020 once a year 2020-04-01
2019 O. Fercoq, A. Alacaoglu, I. Necoara, V. Cevher
Almost surely constrained convex optimization
published pages: 1910-1919, ISSN: , DOI:
Proceedings of EEE International Conference on Machine Learning (ICML)’2019 Once a year in PMLR 97 2020-04-01
2019 Joel A. Tropp, Alp Yurtsever, Madeleine Udell, Volkan Cevher
Streaming Low-Rank Matrix Approximation with an Application to Scientific Simulation
published pages: A2430-A2463, ISSN: 1064-8275, DOI: 10.1137/18m1201068
SIAM Journal on Scientific Computing 41/4 2020-04-01
2020 T. Sanchez, B. Gözcü, R. van Heeswijk, A Eftekhari, E. Ilıcak, T. Cukur, V. Cevher
Scalable Learning-Based Sampling Optimization For Compressive Dynamic MRI
published pages: , ISSN: , DOI:
Proceedings of International Conference on Acoustics, Speech, and Signal Processing (ICASSP)’2020 once a year 2020-04-01
2020 J. Lin, V. Cevher
Convergences of Regularized Algorithms and Stochastic Gradient Methods with Random Projections
published pages: 1−44, ISSN: 1533-7928, DOI:
The Journal of Machine Learning Research (JMLR) Volume 21 2020-04-01
2019 Y-P. Hsieh, C. Liu, V. Cevher,
Finding Mixed Nash Equilibria of Generative Adversarial Networks
published pages: 2810-2819, ISSN: , DOI:
Proceedings of IEEE International Conference on Machine Learning (ICML)’2019 Once a year in PMLR 97 2020-04-01
2019 A. Yurtsever, O. Fercoq, V. Cevher
A Conditional Gradient-Based Augmented Lagrangian Framework
published pages: 7272-7281, ISSN: , DOI:
Proceedings of IEEE International Conference on Machine Learning (ICML)’2019 Once a year in PMLR 97 2020-04-01
2019 Quoc Tran-Dinh, Ahmet Alacaoglu, Olivier Fercoq, Volkan Cevher
An adaptive primal-dual framework for nonsmooth convex minimization
published pages: , ISSN: 1867-2949, DOI: 10.1007/s12532-019-00173-3
Mathematical Programming Computation 2020-04-01
2019 A. Kavis, K.Y. Levy, F. Bach, V. Cevher
UniXGrad: A Universal, Adaptive Algorithm with Optimal Guarantees for Constrained Optimization
published pages: , ISSN: , DOI:
Proceeding of Conference on Neural Information Processing Systems (NeurIPS)’2019 once a year 2020-04-01
2019 F. Latorre, A. Eftekhari, V. Cevher
Fast and Provable ADMM for Learning with Generative Priors
published pages: , ISSN: , DOI:
Proceedings of Conference on NeuralInformation Processing Systems (NeurIPS)’2019 once a year 2020-04-01
2017 Alacaoglu Ahmet, Quoc Tran-Dinh, Olivier Fercoq, Volkan Cevher
Smooth Primal-Dual Coordinate Descent Algorithms for Nonsmooth Convex Optimization
published pages: , ISSN: , DOI:
Proceedings of the Conference on Neural Information Processing Systems (NIPS 2017), once a year 2019-05-23
2018 Rabeeh Karimi Mahabadi, Cosimo Aprile, Volkan Cevher
Real-time DCT Learning-based Reconstruction of Neural Signals
published pages: , ISSN: , DOI:
Proceeding of the European Signal Processing Conference (EUSIPCO 2018) once a year 2019-05-23
2019 Yen-Huan Li, Volkan Cevher
Convergence of the Exponentiated Gradient Method with Armijo Line Search
published pages: 588-607, ISSN: 0022-3239, DOI: 10.1007/s10957-018-1428-9
Journal of Optimization Theory and Applications 181/2 2019-05-23
2018 Cosimo Aprile, Alessandro Cevrero, Pier Andrea Francese, Christian Menolfi, Matthias Braendli, Marcel Kossel, Thomas Morf, Lukas Kull, Ilter Oezkaya, Yusuf Leblebici, Volkan Cevher, Thomas Toifl
An Eight-Lane 7-Gb/s/pin Source Synchronous Single-Ended RX With Equalization and Far-End Crosstalk Cancellation for Backplane Channels
published pages: 861-872, ISSN: 0018-9200, DOI: 10.1109/jssc.2017.2783679
IEEE Journal of Solid-State Circuits 53/3 2019-05-23
2018 Volkan Cevher, Bằng Công Vũ
On the linear convergence of the stochastic gradient method with constant step-size
published pages: , ISSN: 1862-4472, DOI: 10.1007/s11590-018-1331-1
Optimization Letters 2019-05-23
2018 Hsieh, Ya-Ping; Cevher, Volkan
Dimension-free Information Concentration via Exp-Concavity
published pages: , ISSN: , DOI:
Proceedings of the conference of Algorithmic Learning Theory (ALT) once a year 2019-05-23
2018 Cosimo Aprile, Kerim Ture, Luca Baldassarre, Mahsa Shoaran, Gurkan Yilmaz, Franco Maloberti, Catherine Dehollain, Yusuf Leblebici, Volkan Cevher
Adaptive Learning-Based Compressive Sampling for Low-power Wireless Implants
published pages: 3929-3941, ISSN: 1549-8328, DOI: 10.1109/tcsi.2018.2853983
IEEE Transactions on Circuits and Systems I: Regular Papers 65/11 2019-05-23
2018 Cosimo Aprile, Wüthrich, Johannes, Baldassarre, Luca , Leblebici, Yusuf, Cevher, Volkan
An area and power efficient on-the-fly LBCS transformation for implantable neuronal signal acquisition systems
published pages: , ISSN: , DOI:
Proceedings of the ACM International Conference on Computing Frontiers 2018 once a year 2019-05-23
2018 Jonathan Scarlett, Volkan Cevher
Near-Optimal Noisy Group Testing via Separate Decoding of Items
published pages: , ISSN: , DOI:
Proceedings of the IEEE International Symposium on Information Theory (ISIT) once a year 2019-05-23
2018 Hsieh, Ya-Ping; Kavis, Ali; Rolland, Paul; Cevher, Volkan
Mirrored Langevin Dynamics
published pages: , ISSN: , DOI:
Conference on Neural Information Processing Systems 2018 once a year 2019-05-23
2018 Ya-Ping Hsieh, Yu-Chun Kao, Rabeeh Karimi Mahabadi, Alp Yurtsever, Anastasios Kyrillidis, Volkan Cevher
A Non-Euclidean Gradient Descent Framework for Non-Convex Matrix Factorization
published pages: 5917-5926, ISSN: 1053-587X, DOI: 10.1109/tsp.2018.2870353
IEEE Transactions on Signal Processing 66/22 2019-05-23
2018 Rolland, Paul; Scarlett, Jonathan; Bogunovic, Ilija; Cevher, Volkan
High-Dimensional Bayesian Optimization via Additive Models with Overlapping Groups
published pages: , ISSN: , DOI:
Proceedings of the International Conference on Artificial Intelligence and Statistics (AISTATS) once a year 2019-05-23
2018 Baran Gozcu, Rabeeh Karimi Mahabadi, Yen-Huan Li, Efe Ilicak, Tolga Cukur, Jonathan Scarlett, Volkan Cevher
Learning-Based Compressive MRI
published pages: 1394-1406, ISSN: 0278-0062, DOI: 10.1109/tmi.2018.2832540
IEEE Transactions on Medical Imaging 37/6 2019-05-27
2018 Bogunovic, Ilija ; Scarlett, Jonathan ; Jegelka, Stefanie ; Cevher, Volkan
Adversarially Robust Optimization with Gaussian Processes
published pages: , ISSN: , DOI:
Proceedings of the Conference on Neural Information Processing Systems (NIPS) once a year 2019-05-27
2018 Junhong Lin, Volkan Cevher
Optimal Distributed Learning with Multi-pass Stochastic Gradient Methods
published pages: , ISSN: , DOI:
Proceedings of the International Conference on Machine Learning (ICML 2018) once a year 2019-05-23
2018 Jonathan Scarlett, Volkan Cevher
Near-Optimal Noisy Group Testing via Separate Decoding of Items
published pages: 902-915, ISSN: 1932-4553, DOI: 10.1109/jstsp.2018.2844818
IEEE Journal of Selected Topics in Signal Processing 12/5 2019-05-27
2018 Junhong Lin, Alessandro Rudi, Lorenzo Rosasco, Volkan Cevher
Optimal rates for spectral algorithms with least-squares regression over Hilbert spaces
published pages: , ISSN: 1063-5203, DOI: 10.1016/j.acha.2018.09.009
Applied and Computational Harmonic Analysis 2019-05-23
2017 Mitrović, Slobodan; Bogunovic, Ilija; Norouzi-Fard, Ashkan; Tarnawski, Jakub; Cevher, Volkan
Streaming Robust Submodular Maximization: A Partitioned Thresholding Approach
published pages: , ISSN: , DOI:
Proceedings of the Conference on Neural Information Processing Systems (NIPS) once a year 2019-05-27
2018 Kangarshahi, Ehsan Asadi; Hsieh, Ya-Ping; Sahin, Mehmet Fatih; Cevher, Volkan
Let\'s be Honest: An Optimal No-Regret Framework for Zero-Sum Games
published pages: , ISSN: , DOI:
Proceedings of the 35th International Conference on Machine Learning once a year 2019-05-27
2018 Yurtsever, Alp; Fercoq, Olivier; Locatello, Francesco; Cevher, Volkan
A Conditional Gradient Framework for Composite Convex Minimization with Applications to Semidefinite Programming
published pages: , ISSN: , DOI:
Proceedings of the 35th International Conference on Machine Learning (ICML) once a year 2019-05-27
2018 Bogunovic, Ilija; Zhao, Junyao; Cevher, Volkan
Robust Maximization of Non-Submodular Objectives
published pages: , ISSN: , DOI:
Proceedings of the International Conference on Artificial Intelligence and Statistics (AISTATS) once a year 2019-05-23
2018 Levy, Kfir Y.; Yurtsever, Alp; Cevher, Volkan
Online Adaptive Methods, Universality and Acceleration
published pages: , ISSN: , DOI:
Proceedings of the Conference on Neural Information Processing Systems conference (NIPS 2018) once a year 2019-05-23
2018 Lin, Junhong; Cevher, Volkan
Optimal Convergence for Distributed Learning with Stochastic Gradient Methods and Spectral Algorithms
published pages: , ISSN: , DOI:
under review 2019-05-23
2019 Quang Van Nguyen, Sandip De, Junhong Lin, Volkan Cevher
Chemical machine learning with kernels: The impact of loss functions
published pages: e25872, ISSN: 0020-7608, DOI: 10.1002/qua.25872
International Journal of Quantum Chemistry 119/9 2019-06-06

Are you the coordinator (or a participant) of this project? Plaese send me more information about the "TIME-DATA" project.

For instance: the website url (it has not provided by EU-opendata yet), the logo, a more detailed description of the project (in plain text as a rtf file or a word file), some pictures (as picture files, not embedded into any word file), twitter account, linkedin page, etc.

Send me an  email (fabio@fabiodisconzi.com) and I put them in your project's page as son as possible.

Thanks. And then put a link of this page into your project's website.

The information about "TIME-DATA" are provided by the European Opendata Portal: CORDIS opendata.

More projects from the same programme (H2020-EU.1.1.)

PROGRESS (2019)

The Enemy of the Good: Towards a Theory of Moral Progress

Read More  

DISINTEGRATION (2019)

The Mass Politics of Disintegration

Read More  

KEYNESGROWTH (2020)

Economic Fluctuations, Productivity Growth and Stabilization Policies: A Keynesian Growth Perspective

Read More