Search Results for author:
Found 18 papers, 1 papers with code
Learning disconnected manifolds: a no GAN's land
Typical architectures of Generative Adversarial Networks make use of a unimodal latent/input distribution transformed by a continuous generator.
3DGEN: A GAN-based approach for generating novel 3D models from image data
The recent advances in text and image synthesis show a great promise for the future of generative models in creative fields.
AdBooster: Personalized Ad Creative Generation using Stable Diffusion Outpainting
In digital advertising, the selection of the optimal item (recommendation) and its best creative presentation (creative optimization) have traditionally been considered separate disciplines.
Unveiling the Latent Space Geometry of Push-Forward Generative Models
We investigate the relationship between the performance of these models and the geometry of their latent space.
Lessons from the AdKDD'21 Privacy-Preserving ML Challenge
Designing data sharing mechanisms providing performance and strong privacy guarantees is a hot topic for the Online Advertising industry.
Optimal 1-Wasserstein Distance for WGANs
The mathematical forces at work behind Generative Adversarial Networks raise challenging theoretical issues.
EdiBERT, a generative model for image editing
Advances in computer vision are pushing the limits of im-age manipulation, with generative models sampling detailed images on various tasks.
Latent reweighting, an almost free improvement for GANs
Standard formulations of GANs, where a continuous function deforms a connected latent space, have been shown to be misspecified when fitting different classes of images.
What Users Want? WARHOL: A Generative Model for Recommendation
Current recommendation approaches help online merchants predict, for each visiting user, which subset of their existing products is the most relevant.
Learning Disconnected Manifolds: Avoiding The No Gan's Land by Latent Rejection
Standard formulations of GANs, where a continuous function deforms a connected latent space, have been shown to be misspecified when fitting disconnected manifolds.
Wasserstein Learning of Determinantal Point Processes
Through an evaluation on a real-world dataset, we show that our Wasserstein learning approach provides significantly improved predictive performance on a generative task compared to DPPs trained using MLE.
Approximating Lipschitz continuous functions with GroupSort neural networks
Recent advances in adversarial attacks and Wasserstein GANs have advocated for use of neural networks with restricted Lipschitz constants.
Learning disconnected manifolds: a no GANs land
Typical architectures of Generative AdversarialNetworks make use of a unimodal latent distribution transformed by a continuous generator.
Some Theoretical Insights into Wasserstein GANs
Generative Adversarial Networks (GANs) have been successful in producing outstanding results in areas as diverse as image, video, and text generation.
Relaxed Softmax for learning from Positive and Unlabeled data
In recent years, the softmax model and its fast approximations have become the de-facto loss functions for deep neural networks when dealing with multi-class prediction.
Distributionally Robust Counterfactual Risk Minimization
This manuscript introduces the idea of using Distributionally Robust Optimization (DRO) for the Counterfactual Risk Minimization (CRM) problem.
Partially Mutual Exclusive Softmax for Positive and Unlabeled data
This is often the case for applications such as language modeling, next event prediction and matrix factorization, where many of the potential outcomes are not mutually exclusive, but are more likely to be independent conditionally on the state.
Adversarial Training of Word2Vec for Basket Completion
In recent years, the Word2Vec model trained with the Negative Sampling loss function has shown state-of-the-art results in a number of machine learning tasks, including language modeling tasks, such as word analogy and word similarity, and in recommendation tasks, through Prod2Vec, an extension that applies to modeling user shopping activity and user preferences.
