Youssef Mroueh  Youssef Mroueh photo         

contact information

Research Staff Member
Thomas J. Watson Research Center, Yorktown Heights, NY USA
  

links



2020

Decentralized Parallel Algorithm for Training Generative Adversarial Nets
Liu, M., Mroueh, Y., Zhang, W., Cui, X., Yang, T. and Das, P
NeurIPS, 2020

Unbalanced Sobolev Descent
Youssef Mroueh, Mattia Rigotti
arXiv preprint arXiv:2009.14148, 2020
Abstract   reproducing kernel hilbert space, sobolev space, conservation of mass, artificial neural network, applied mathematics, reaction step, particle, advection, computer science, target distribution

Fast Mixing of Multi-Scale Langevin Dynamics under the Manifold Hypothesis
Adam Block, Youssef Mroueh, Alexander Rakhlin, Jerret Ross
arXiv preprint arXiv:2006.11166, 2020
Abstract   langevin dynamics, intrinsic dimension, markov chain monte carlo, exponential function, manifold, statistical physics, image quality, sampling, computer science, image generation

Generative Modeling with Denoising Auto-Encoders and Langevin Sampling
Adam Block, Youssef Mroueh, Alexander Rakhlin
arXiv preprint arXiv:2002.00107, 2020
Abstract   sampling, population, score, gaussian, convergence, algorithm, noise reduction, mathematics, auto encoders, generative modeling

Active learning of deep surrogates for PDEs: Application to metasurface design
Raphael Pestourie, Youssef Mroueh, Thanh V. Nguyen, Payel Das, Steven G. Johnson
arXiv preprint arXiv:2008.12649, 2020
Abstract   surrogate model, engineering optimization, active learning, computer engineering, order of magnitude, computer science, optical wavelength

Kernel Stein Generative Modeling
Wei-Cheng Chang, Chun-Liang Li, Youssef Mroueh, Yiming Yang
arXiv preprint arXiv:2007.03074, 2020
Abstract   gradient descent, bayesian inference, score, inference, kullback leibler divergence, kernel, estimator, mnist database, algorithm, computer science

Transforming source distribution to target distribution using Sobolev descent
Mroueh Youssef, Sercu Tom
2020
Abstract   executable, computer program, artificial neural network, morphing, product distribution, computational science, sampling, computer science, sobolev space, target distribution

Nano-Material Configuration Design with Deep Surrogate Langevin Dynamics
Thanh V. Nguyen, Youssef Mroueh, Samuel Hoffman, Payel Das, Pierre Dognin, Giuseppe Romano, Chinmay Hegde
ICLR 2020 Workshop on Integration of Deep Neural Models and Differential Equations
langevin dynamics, configuration design, classical mechanics, nanomaterials, computer science

Learning Implicit Text Generation via Feature Matching
Inkit Padhi, Pierre Dognin, Ke Bai, Cicero Nogueira dos Santos, Vijil Chenthamarakshan, Youssef Mroueh, Payel Das
2020

Towards Better Understanding of Adaptive Gradient Algorithms in Generative Adversarial Nets
Mingrui Liu, Youssef Mroueh, Jerret Ross, Wei Zhang, Xiaodong Cui, Payel Das, Tianbao Yang
International Conference on Learning Representations (ICLR), 2020

Improving Efficiency in Large-Scale Decentralized Distributed Training
Wei Zhang, Xiaodong Cui, Abdullah Kayi, Mingrui Liu, Ulrich Finkler, Brian Kingsbury, George Saon, Youssef Mroueh, Alper Buyuktosunoglu, Payel Das, David Kung, Michael Picheny
ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP, Lecture Session)


2019

Improved Mutual Information Estimation
Youssef Mroueh, Igor Melnyk, Pierre Dognin, Jerret Ross, Tom Sercu
2019
mutual information, data mining, computer science

Surrogate-Based Constrained Langevin Sampling With Applications to Optimal Material Configuration Design
Thanh V Nguyen, Youssef Mroueh, Samuel C. Hoffman, Payel Das, Pierre Dognin, Giuseppe Romano, Chinmay Hegde
2019
sampling, configuration design, mathematical optimization, computer science

Wasserstein Style Transfer
Youssef Mroueh
AISTATS, pp. 842-852, 2019
calculus, mathematics

Wasserstein Barycenter Model Ensembling
Pierre Dognin, Igor Melnyk, Youssef Mroueh, Jerret Ross, Tom Sercu
ICLR: International Conference on Learning Representations, 2019

Sobolev Independence Criterion
Youssef Mroueh, Tom Sercu, Mattia Rigotti, Inkit Padhi, Cicero Dos Santos
arXiv preprint arXiv:1910.14212, 2019
Abstract   feature selection, joint probability distribution, random variable, convex optimization, artificial neural network, interpretability, kernel, parameterized complexity, algorithm, computer science

Adversarial Semantic Alignment for Improved Image Captions
Pierre Dognin, Igor Melnyk, Youssef Mroueh, Jarret Ross and Tom Sercu
CVPR: Conference on Computer Vision and Pattern Recognition, 2019

Learning Implicit Generative Models by Matching Perceptual Features
Cicero Nogueira Dos Santos, Youssef Mroueh, Inkit Padhi, Pierre Dognin
2019 IEEE/CVF International Conference on Computer Vision (ICCV), pp. 4460-4469
Abstract   transfer of learning, kernel, feature extraction, kernel, artificial intelligence, generative grammar, method of moments, convergence, computer science, perception

Sobolev Descent
Youssef Mroueh, Tom Sercu, Anant Raj
The 22nd International Conference on Artificial Intelligence and Statistics, 2019
Abstract   sobolev space, regularization, convergence, artificial neural network, kernel, applied mathematics, parametrization, kinetic energy, mathematics, target distribution

Implicit Kernel Learning
Chun-Liang Li, Wei-Cheng Chang, Youssef Mroueh, Yiming Yang, Barnabas Poczos
arXiv preprint arXiv:1902.10214, 2019
Abstract   supervised learning, kernel, machine learning, data driven, inference, computer science, sampling, generative grammar, spectral power distribution, parametrization, artificial intelligence

Unsupervised Hierarchy Matching with Optimal Transport over Hyperbolic Spaces
David Alvarez-Melis, Youssef Mroueh, Tommi S. Jaakkola
AISTATS, pp. 1606-1617, 2019
hierarchy, theoretical computer science, computer science


2018

Regularized Finite Dimensional Kernel Sobolev Discrepancy
Youssef Mroueh
arXiv preprint arXiv:1805.06441, 2018
Abstract   sobolev space, approximation error, function space, kernel, feature vector, applied mathematics, computer science, statistical error

Improved Image Captioning with Adversarial Semantic Alignment
Pierre L. Dognin, Igor Melnyk, Youssef Mroueh, Jerret Ross, Tom Sercu
2018
Abstract   closed captioning, discriminator, pattern recognition, computer science, gumbel distribution, correlation, judgement, adversarial system, artificial intelligence, semantic alignment


2017

Semi-Supervised Learning with IPM-based GANs: an Empirical Study
Sercu, Tom and Mroueh, Youssef
NIPS 2017, workshop paper arXiv preprint arXiv:1712.02505

Sobolev GAN
Mroueh, Youssef and Li, Chun-Liang and Sercu, Tom and Raj, Anant and Cheng, Yu
Submitted to ICLR 2018,arXiv preprint arXiv:1711.04894, 2017

Exploring ROI size in deep learning based lipreading
Koumparoulis, Alexandros and Potamianos, Gerasimos and Mroueh, Youssef and Rennie, Steven J
AVSP 2017

Local group invariant representations via orbit embeddings. preprint
Raj, Anant and Kumar, Abhishek and Mroueh, Youssef and Fletcher, P Thomas and Scholkopf, B
AISTATS, 2017

Audio and visual modality combination in speech processing applications
Potamianos, Gerasimos and Marcheret, Etienne and Mroueh, Youssef and Goel, Vaibhava and Koumbaroulis, Alexandros and Vartholomaios, Argyrios and Thermos, Spyridon
The Handbook of Multimodal-Multisensor Interfaces, pp. 489--543, 2017

McGan: Mean and Covariance Feature Matching GAN
Mroueh, Youssef and Sercu, Tom and Goel, Vaibhava
ICML, 2017

Self-critical sequence training for image captioning
Rennie, Steven J and Marcheret, Etienne and Mroueh, Youssef and Ross, Jarret and Goel, Vaibhava
CVPR, 2017

Co-Occurring Directions Sketching for Approximate Matrix Multiply
Mroueh, Youssef and Marcheret, Etienne and Goel, Vaibhava
AISTATS, 2017

Fisher GAN
Mroueh, Youssef and Sercu, Tom
NIPS , 2017


2016

Co-Occuring Directions Sketching for Approximate Matrix Multiply
Youssef Mroueh, Etienne Marcheret, Vaibahava Goel
Artificial Intelligence and Statistics, pp. 567-575, 2016
matrix multiplication, computer science, mathematical analysis

Local Group Invariant Representations via Orbit Embeddings
Raj, Anant and Kumar, Abhishek and Mroueh, Youssef and Fletcher, P Thomas and others
arXiv preprint arXiv:1612.01988, 2016
Abstract

Asymmetrically Weighted CCA And Hierarchical Kernel Sentence Embedding For Multimodal Retrieval
Mroueh, Youssef and Marcheret, Etienne and Goel, Vaibhava
arXiv preprint arXiv:1511.06267, 2016


2015

Asymmetrically Weighted CCA And Hierarchical Kernel Sentence Embedding For Image & Text Retrieval
Youssef Mroueh, Etienne Marcheret, Vaibhava Goel
arXiv preprint arXiv:1511.06267, 2015
Abstract   kernel, embedding, weighting, sentence, model selection, canonical correlation, pattern recognition, vector space, computer science, artificial intelligence, text retrieval

Convex learning of multiple tasks and their structure
Ciliberto, Carlo and Mroueh, Youssef and Poggio, Tomaso and Rosasco, Lorenzo
International Conference on Machine Learning, pp. 1548--1557, 2015

Deep multimodal learning for audio-visual speech recognition
Mroueh, Youssef and Marcheret, Etienne and Goel, Vaibhava
Acoustics, Speech and Signal Processing (ICASSP), 2015 IEEE International Conference on, pp. 2130--2134

Learning with Group Invariant Features: A Kernel Perspective.
Mroueh, Youssef and Voinea, Stephen and Poggio, Tomaso A
Advances in Neural Information Processing Systems, pp. 1558--1566, 2015


2014

On efficiency and low sample complexity in phase retrieval
Mroueh, Youssef and Rosasco, Lorenzo
Information Theory (ISIT), 2014 IEEE International Symposium on, pp. 931--935



2013

q-ary Compressive Sensing
Mroueh, Youssef and Rosasco, Lorenzo
arXiv preprint arXiv:1302.5168, 2013

Quantization and greed are good: One bit phase retrieval, robustness and greedy refinements
Mroueh, Youssef and Rosasco, Lorenzo
arXiv preprint arXiv:1312.1830, 2013

Can a biologically-plausible hierarchy effectively replace face detection, alignment, and recognition pipelines?
Liao, Qianli and Leibo, Joel Z and Mroueh, Youssef and Poggio, Tomaso
arXiv preprint arXiv:1311.4082, 2013


2012

Multiclass learning with simplex coding
Mroueh, Youssef and Poggio, Tomaso and Rosasco, Lorenzo and Slotine, Jean-Jeacques
Advances in Neural Information Processing Systems, pp. 2789--2797, 2012


2011

Multi-category and taxonomy learning: A regularization approach
Mroueh, Youssef and Poggio, Tomaso and Rosasco, Lorenzo
NIPS Workshop on Challenges in Learning Hierarchical Models: Transfer Learning and Optimization, 2011

Regularization Predicts While Discovering Taxonomy
Mroueh, Youssef and Poggio, Tomaso and Rosasco, Lorenzo
CVPR workshop, 2011