Search Results for author: Youssef Mroueh

Found 55 papers, 15 papers with code

Auditing and Generating Synthetic Data with Controllable Trust Trade-offs

no code implementations21 Apr 2023 Brian Belgodere, Pierre Dognin, Adam Ivankay, Igor Melnyk, Youssef Mroueh, Aleksandra Mojsilovic, Jiri Navratil, Apoorva Nitsure, Inkit Padhi, Mattia Rigotti, Jerret Ross, Yair Schiff, Radhika Vedpathak, Richard A. Young

We present an auditing framework that offers a holistic assessment of synthetic datasets and AI models trained on them, centered around bias and discrimination prevention, fidelity to the real data, utility, robustness, and privacy preservation.

Model Selection Privacy Preserving

Effective Dynamics of Generative Adversarial Networks

no code implementations8 Dec 2022 Steven Durr, Youssef Mroueh, Yuhai Tu, Shenshen Wang

Generative adversarial networks (GANs) are a class of machine-learning models that use adversarial training to generate new samples with the same (potentially very complex) statistics as the training samples.


Learning with Stochastic Orders

1 code implementation27 May 2022 Carles Domingo-Enrich, Yair Schiff, Youssef Mroueh

Learning high-dimensional distributions is often done with explicit likelihood modeling or implicit modeling via minimizing integral probability metrics (IPMs).

Image Generation

Auditing Differential Privacy in High Dimensions with the Kernel Quantum Rényi Divergence

1 code implementation27 May 2022 Carles Domingo-Enrich, Youssef Mroueh

Differential privacy (DP) is the de facto standard for private data release and private machine learning.

Cycle Consistent Probability Divergences Across Different Spaces

no code implementations22 Nov 2021 Zhengxin Zhang, Youssef Mroueh, Ziv Goldfeld, Bharath K. Sriperumbudur

Discrepancy measures between probability distributions are at the core of statistical inference and machine learning.

Physics-enhanced deep surrogates for PDEs

no code implementations10 Nov 2021 Raphaël Pestourie, Youssef Mroueh, Chris Rackauckas, Payel Das, Steven G. Johnson

Many physics and engineering applications demand Partial Differential Equations (PDE) property evaluations that are traditionally computed with resource-intensive high-fidelity numerical solvers.

Active Learning

Tighter Sparse Approximation Bounds for ReLU Neural Networks

no code implementations ICLR 2022 Carles Domingo-Enrich, Youssef Mroueh

A well-known line of work (Barron, 1993; Breiman, 1993; Klusowski & Barron, 2018) provides bounds on the width $n$ of a ReLU two-layer neural network needed to approximate a function $f$ over the ball $\mathcal{B}_R(\mathbb{R}^d)$ up to error $\epsilon$, when the Fourier based quantity $C_f = \frac{1}{(2\pi)^{d/2}} \int_{\mathbb{R}^d} \|\xi\|^2 |\hat{f}(\xi)| \ d\xi$ is finite.

Large-Scale Chemical Language Representations Capture Molecular Structure and Properties

1 code implementation17 Jun 2021 Jerret Ross, Brian Belgodere, Vijil Chenthamarakshan, Inkit Padhi, Youssef Mroueh, Payel Das

Models based on machine learning can enable accurate and fast molecular property predictions, which is of interest in drug discovery and material design.

Drug Discovery Molecular Property Prediction +2

Separation Results between Fixed-Kernel and Feature-Learning Probability Metrics

no code implementations NeurIPS 2021 Carles Domingo-Enrich, Youssef Mroueh

Several works in implicit and explicit generative modeling empirically observed that feature-learning discriminators outperform fixed-kernel discriminators in terms of the sample quality of the models.

Optimizing Functionals on the Space of Probabilities with Input Convex Neural Networks

no code implementations1 Jun 2021 David Alvarez-Melis, Yair Schiff, Youssef Mroueh

Gradient flows are a powerful tool for optimizing functionals in general metric spaces, including the space of probabilities endowed with the Wasserstein metric.

Fair Mixup: Fairness via Interpolation

1 code implementation ICLR 2021 Ching-Yao Chuang, Youssef Mroueh

Training classifiers under fairness constraints such as group fairness, regularizes the disparities of predictions between the groups.

Data Augmentation Fairness

Image Captioning as an Assistive Technology: Lessons Learned from VizWiz 2020 Challenge

1 code implementation21 Dec 2020 Pierre Dognin, Igor Melnyk, Youssef Mroueh, Inkit Padhi, Mattia Rigotti, Jarret Ross, Yair Schiff, Richard A. Young, Brian Belgodere

Image captioning has recently demonstrated impressive progress largely owing to the introduction of neural network algorithms trained on curated dataset like MS-COCO.

Image Captioning Navigate

Alleviating Noisy Data in Image Captioning with Cooperative Distillation

no code implementations21 Dec 2020 Pierre Dognin, Igor Melnyk, Youssef Mroueh, Inkit Padhi, Mattia Rigotti, Jarret Ross, Yair Schiff

Image captioning systems have made substantial progress, largely due to the availability of curated datasets like Microsoft COCO or Vizwiz that have accurate descriptions of their corresponding images.

Image Captioning

On the Convergence of Gradient Descent in GANs: MMD GAN As a Gradient Flow

no code implementations4 Nov 2020 Youssef Mroueh, Truyen Nguyen

We then derive an explicit condition which ensures that gradient descent on the parameter space of the generator in gradient regularized $\mathrm{MMD}$ GAN is globally convergent to the target distribution.

Tabular Transformers for Modeling Multivariate Time Series

1 code implementation3 Nov 2020 Inkit Padhi, Yair Schiff, Igor Melnyk, Mattia Rigotti, Youssef Mroueh, Pierre Dognin, Jerret Ross, Ravi Nair, Erik Altman

This results in two architectures for tabular time series: one for learning representations that is analogous to BERT and can be pre-trained end-to-end and used in downstream tasks, and one that is akin to GPT and can be used for generation of realistic synthetic tabular sequences.

Fraud Detection Synthetic Data Generation +2

Unbalanced Sobolev Descent

1 code implementation NeurIPS 2020 Youssef Mroueh, Mattia Rigotti

USD transports particles along gradient flows of the witness function of the Sobolev-Fisher discrepancy (advection step) and reweighs the mass of particles with respect to this witness function (reaction step).

Active learning of deep surrogates for PDEs: Application to metasurface design

no code implementations24 Aug 2020 Raphaël Pestourie, Youssef Mroueh, Thanh V. Nguyen, Payel Das, Steven G. Johnson

Surrogate models for partial-differential equations are widely used in the design of meta-materials to rapidly evaluate the behavior of composable components.

Active Learning

Kernel Stein Generative Modeling

no code implementations6 Jul 2020 Wei-Cheng Chang, Chun-Liang Li, Youssef Mroueh, Yiming Yang

NCK is crucial for successful inference with SVGD in high dimension, as it adapts the kernel to the noise level of the score estimate.

Bayesian Inference

Learning Implicit Text Generation via Feature Matching

no code implementations ACL 2020 Inkit Padhi, Pierre Dognin, Ke Bai, Cicero Nogueira dos santos, Vijil Chenthamarakshan, Youssef Mroueh, Payel Das

Generative feature matching network (GFMN) is an approach for training implicit generative models for images by performing moment matching on features from pre-trained neural networks.

Conditional Text Generation Style Transfer +2

Improving Efficiency in Large-Scale Decentralized Distributed Training

no code implementations4 Feb 2020 Wei Zhang, Xiaodong Cui, Abdullah Kayi, Mingrui Liu, Ulrich Finkler, Brian Kingsbury, George Saon, Youssef Mroueh, Alper Buyuktosunoglu, Payel Das, David Kung, Michael Picheny

Decentralized Parallel SGD (D-PSGD) and its asynchronous variant Asynchronous Parallel SGD (AD-PSGD) is a family of distributed learning algorithms that have been demonstrated to perform well for large-scale deep learning tasks.

speech-recognition Speech Recognition +1

Generative Modeling with Denoising Auto-Encoders and Langevin Sampling

no code implementations31 Jan 2020 Adam Block, Youssef Mroueh, Alexander Rakhlin

We show that both DAE and DSM provide estimates of the score of the Gaussian smoothed population density, allowing us to apply the machinery of Empirical Processes.


Towards Better Understanding of Adaptive Gradient Algorithms in Generative Adversarial Nets

no code implementations ICLR 2020 Mingrui Liu, Youssef Mroueh, Jerret Ross, Wei zhang, Xiaodong Cui, Payel Das, Tianbao Yang

Then we propose an adaptive variant of OSG named Optimistic Adagrad (OAdagrad) and reveal an \emph{improved} adaptive complexity $O\left(\epsilon^{-\frac{2}{1-\alpha}}\right)$, where $\alpha$ characterizes the growth rate of the cumulative stochastic gradient and $0\leq \alpha\leq 1/2$.

Unsupervised Hierarchy Matching with Optimal Transport over Hyperbolic Spaces

no code implementations6 Nov 2019 David Alvarez-Melis, Youssef Mroueh, Tommi S. Jaakkola

This paper focuses on the problem of unsupervised alignment of hierarchical data such as ontologies or lexical databases.

Ontology Matching Word Alignment

Sobolev Independence Criterion

1 code implementation NeurIPS 2019 Youssef Mroueh, Tom Sercu, Mattia Rigotti, Inkit Padhi, Cicero dos Santos

In the kernel version we show that SIC can be cast as a convex optimization problem by introducing auxiliary variables that play an important role in feature selection as they are normalized feature importance scores.

Feature Importance feature selection +1

A Decentralized Parallel Algorithm for Training Generative Adversarial Nets

no code implementations NeurIPS 2020 Mingrui Liu, Wei zhang, Youssef Mroueh, Xiaodong Cui, Jerret Ross, Tianbao Yang, Payel Das

Despite recent progress on decentralized algorithms for training deep neural networks, it remains unclear whether it is possible to train GANs in a decentralized manner.

Surrogate-Based Constrained Langevin Sampling With Applications to Optimal Material Configuration Design

no code implementations25 Sep 2019 Thanh V Nguyen, Youssef Mroueh, Samuel C. Hoffman, Payel Das, Pierre Dognin, Giuseppe Romano, Chinmay Hegde

We consider the problem of generating configurations that satisfy physical constraints for optimal material nano-pattern design, where multiple (and often conflicting) properties need to be simultaneously satisfied.

Wasserstein Style Transfer

1 code implementation30 May 2019 Youssef Mroueh

Moreover interpolates between a content and a style image can be seen as geodesics in the Wasserstein Geometry.

Style Transfer

Generative Feature Matching Networks

no code implementations ICLR 2019 Cicero Nogueira dos Santos, Inkit Padhi, Pierre Dognin, Youssef Mroueh

We propose a non-adversarial feature matching-based approach to train generative models.

Learning Implicit Generative Models by Matching Perceptual Features

no code implementations ICCV 2019 Cicero Nogueira dos Santos, Youssef Mroueh, Inkit Padhi, Pierre Dognin

Perceptual features (PFs) have been used with great success in tasks such as transfer learning, style transfer, and super-resolution.

Style Transfer Super-Resolution +1

Improved Adversarial Image Captioning

no code implementations ICLR Workshop DeepGenStruct 2019 Pierre Dognin, Igor Melnyk, Youssef Mroueh, Jarret Ross, Tom Sercu

In this paper we study image captioning as a conditional GAN training, proposing both a context-aware LSTM captioner and co-attentive discriminator, which enforces semantic alignment between images and captions.

Image Captioning

Implicit Kernel Learning

no code implementations26 Feb 2019 Chun-Liang Li, Wei-Cheng Chang, Youssef Mroueh, Yiming Yang, Barnabás Póczos

While learning the kernel in a data driven way has been investigated, in this paper we explore learning the spectral distribution of kernel via implicit generative models parametrized by deep neural networks.

Text Generation

Wasserstein Barycenter Model Ensembling

1 code implementation13 Feb 2019 Pierre Dognin, Igor Melnyk, Youssef Mroueh, Jerret Ross, Cicero dos Santos, Tom Sercu

In this paper we propose to perform model ensembling in a multiclass or a multilabel learning setting using Wasserstein (W.) barycenters.

General Classification Image Captioning +1

Sobolev Descent

no code implementations30 May 2018 Youssef Mroueh, Tom Sercu, Anant Raj

We study a simplification of GAN training: the problem of transporting particles from a source to a target distribution.

Regularized Finite Dimensional Kernel Sobolev Discrepancy

no code implementations16 May 2018 Youssef Mroueh

We show in this note that the Sobolev Discrepancy introduced in Mroueh et al in the context of generative adversarial networks, is actually the weighted negative Sobolev norm $||.||_{\dot{H}^{-1}(\nu_q)}$, that is known to linearize the Wasserstein $W_2$ distance and plays a fundamental role in the dynamic formulation of optimal transport of Benamou and Brenier.

Adversarial Semantic Alignment for Improved Image Captions

no code implementations30 Apr 2018 Pierre L. Dognin, Igor Melnyk, Youssef Mroueh, Jarret Ross, Tom Sercu

When evaluated on OOC and MS-COCO benchmarks, we show that SCST-based training has a strong performance in both semantic score and human evaluation, promising to be a valuable new approach for efficient discrete GAN training.

Image Captioning Test

Semi-Supervised Learning with IPM-based GANs: an Empirical Study

no code implementations7 Dec 2017 Tom Sercu, Youssef Mroueh

We present an empirical investigation of a recent class of Generative Adversarial Networks (GANs) using Integral Probability Metrics (IPM) and their performance for semi-supervised learning.

General Classification

Sobolev GAN

2 code implementations ICLR 2018 Youssef Mroueh, Chun-Liang Li, Tom Sercu, Anant Raj, Yu Cheng

We show that the Sobolev IPM compares two distributions in high dimensions based on weighted conditional Cumulative Distribution Functions (CDF) of each coordinate on a leave one out basis.

Text Generation

Fisher GAN

2 code implementations NeurIPS 2017 Youssef Mroueh, Tom Sercu

In this paper we introduce Fisher GAN which fits within the Integral Probability Metrics (IPM) framework for training GANs.

General Classification

McGan: Mean and Covariance Feature Matching GAN

no code implementations ICML 2017 Youssef Mroueh, Tom Sercu, Vaibhava Goel

We introduce new families of Integral Probability Metrics (IPM) for training Generative Adversarial Networks (GAN).

Local Group Invariant Representations via Orbit Embeddings

no code implementations6 Dec 2016 Anant Raj, Abhishek Kumar, Youssef Mroueh, P. Thomas Fletcher, Bernhard Schölkopf

We consider transformations that form a \emph{group} and propose an approach based on kernel methods to derive local group invariant representations.

Rotated MNIST

Self-critical Sequence Training for Image Captioning

31 code implementations CVPR 2017 Steven J. Rennie, Etienne Marcheret, Youssef Mroueh, Jarret Ross, Vaibhava Goel

In this paper we consider the problem of optimizing image captioning systems using reinforcement learning, and show that by carefully optimizing our systems using the test metrics of the MSCOCO task, significant gains in performance can be realized.

Image Captioning Policy Gradient Methods +3

Co-Occuring Directions Sketching for Approximate Matrix Multiply

no code implementations25 Oct 2016 Youssef Mroueh, Etienne Marcheret, Vaibhava Goel

We introduce co-occurring directions sketching, a deterministic algorithm for approximate matrix product (AMM), in the streaming model.

Learning with Group Invariant Features: A Kernel Perspective.

no code implementations NeurIPS 2015 Youssef Mroueh, Stephen Voinea, Tomaso A. Poggio

Our analysis bridges invariant feature learning with kernel methods, as we show that this feature map defines an expected Haar-integration kernel that is invariant to the specified group action.

Random Maxout Features

no code implementations11 Jun 2015 Youssef Mroueh, Steven Rennie, Vaibhava Goel

In this paper, we propose and study random maxout features, which are constructed by first projecting the input data onto sets of randomly generated vectors with Gaussian elements, and then outputing the maximum projection value for each set.

Data Visualization Dimensionality Reduction +2

Learning with Group Invariant Features: A Kernel Perspective

no code implementations NeurIPS 2015 Youssef Mroueh, Stephen Voinea, Tomaso Poggio

Our analysis bridges invariant feature learning with kernel methods, as we show that this feature map defines an expected Haar integration kernel that is invariant to the specified group action.

Convex Learning of Multiple Tasks and their Structure

1 code implementation13 Apr 2015 Carlo Ciliberto, Youssef Mroueh, Tomaso Poggio, Lorenzo Rosasco

In this context a fundamental question is how to incorporate the tasks structure in the learning problem. We tackle this question by studying a general computational framework that allows to encode a-priori knowledge of the tasks structure in the form of a convex penalty; in this setting a variety of previously proposed methods can be recovered as special cases, including linear and non-linear approaches.

Multi-Task Learning

Deep Multimodal Learning for Audio-Visual Speech Recognition

no code implementations22 Jan 2015 Youssef Mroueh, Etienne Marcheret, Vaibhava Goel

In this paper, we present methods in deep multimodal learning for fusing speech and visual modalities for Audio-Visual Automatic Speech Recognition (AV-ASR).

Audio-Visual Speech Recognition Automatic Speech Recognition +3

Multiclass Learning with Simplex Coding

no code implementations NeurIPS 2012 Youssef Mroueh, Tomaso Poggio, Lorenzo Rosasco, Jean-Jeacques Slotine

In this paper we dicuss a novel framework for multiclass learning, defined by a suitable coding/decoding strategy, namely the simplex coding, that allows to generalize to multiple classes a relaxation approach commonly used in binary classification.

Binary Classification General Classification

Cannot find the paper you are looking for? You can Submit a new open access paper.