Search Results for author: Flavian vasile

Found 27 papers, 4 papers with code

3DGEN: A GAN-based approach for generating novel 3D models from image data

no code implementations13 Dec 2023 Antoine Schnepf, Flavian vasile, Ugo Tanielian

The recent advances in text and image synthesis show a great promise for the future of generative models in creative fields.

Image Generation Object Reconstruction

AdBooster: Personalized Ad Creative Generation using Stable Diffusion Outpainting

no code implementations8 Sep 2023 Veronika Shilova, Ludovic Dos Santos, Flavian vasile, Gaëtan Racic, Ugo Tanielian

In digital advertising, the selection of the optimal item (recommendation) and its best creative presentation (creative optimization) have traditionally been considered separate disciplines.

Data Augmentation

Offline Evaluation of Reward-Optimizing Recommender Systems: The Case of Simulation

no code implementations18 Sep 2022 Imad Aouali, Amine Benhalloum, Martin Bompaire, Benjamin Heymann, Olivier Jeunen, David Rohde, Otmane Sakhi, Flavian vasile

Naturally, the reason for this is that we can directly measure utility metrics that rely on interventions, being the recommendations that are being shown to users.

counterfactual Recommendation Systems

Probabilistic Rank and Reward: A Scalable Model for Slate Recommendation

no code implementations10 Aug 2022 Imad Aouali, Achraf Ait Sidi Hammou, Sergey Ivanov, Otmane Sakhi, David Rohde, Flavian vasile

We introduce Probabilistic Rank and Reward (PRR), a scalable probabilistic model for personalized slate recommendation.

Recommendation Systems

What Users Want? WARHOL: A Generative Model for Recommendation

no code implementations2 Sep 2021 Jules Samaran, Ugo Tanielian, Romain Beaumont, Flavian vasile

Current recommendation approaches help online merchants predict, for each visiting user, which subset of their existing products is the most relevant.

Combining Reward and Rank Signals for Slate Recommendation

no code implementations26 Jul 2021 Imad Aouali, Sergey Ivanov, Mike Gartrell, David Rohde, Flavian vasile, Victor Zaytsev, Diego Legrand

In this paper, we formulate several Bayesian models that incorporate the reward signal (Reward model), the rank signal (Rank model), or both (Full model), for non-personalized slate recommendation.

Recommendation Systems

Improving Offline Contextual Bandits with Distributional Robustness

no code implementations13 Nov 2020 Otmane Sakhi, Louis Faury, Flavian vasile

Our approach relies on the construction of asymptotic confidence intervals for offline contextual bandits through the DRO framework.

counterfactual Multi-Armed Bandits +1

From Clicks to Conversions: Recommendation for long-term reward

no code implementations1 Sep 2020 Philomène Chagniot, Flavian vasile, David Rohde

Recommender systems are often optimised for short-term reward: a recommendation is considered successful if a reward (e. g. a click) can be observed immediately after the recommendation.

Recommendation Systems

BLOB : A Probabilistic Model for Recommendation that Combines Organic and Bandit Signals

no code implementations28 Aug 2020 Otmane Sakhi, Stephen Bonner, David Rohde, Flavian vasile

In contrast, the organic signal is typically strong and covers most items, but is not always relevant to the recommendation task.

Recommendation Systems

Reconsidering Analytical Variational Bounds for Output Layers of Deep Networks

no code implementations2 Oct 2019 Otmane Sakhi, Stephen Bonner, David Rohde, Flavian vasile

The combination of the re-parameterization trick with the use of variational auto-encoders has caused a sensation in Bayesian deep learning, allowing the training of realistic generative models of images and has considerably increased our ability to use scalable latent variable models.

Binary Classification General Classification +1

Learning from Bandit Feedback: An Overview of the State-of-the-art

no code implementations18 Sep 2019 Olivier Jeunen, Dmytro Mykhaylov, David Rohde, Flavian vasile, Alexandre Gilotte, Martin Bompaire

In order to handle this "bandit-feedback" setting, several Counterfactual Risk Minimisation (CRM) methods have been proposed in recent years, that attempt to estimate the performance of different policies on historical data.

counterfactual Recommendation Systems

Relaxed Softmax for learning from Positive and Unlabeled data

no code implementations17 Sep 2019 Ugo Tanielian, Flavian vasile

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.

Density Estimation Language Modelling

On the Value of Bandit Feedback for Offline Recommender System Evaluation

no code implementations26 Jul 2019 Olivier Jeunen, David Rohde, Flavian vasile

The procedure aims to give an answer to the question: "Given the natural sequence of user-item interactions up to time t, can we predict which item the user will interact with at time t+1?".

Recommendation Systems

Distributionally Robust Counterfactual Risk Minimization

no code implementations14 Jun 2019 Louis Faury, Ugo Tanielian, Flavian vasile, Elena Smirnova, Elvis Dohmatob

This manuscript introduces the idea of using Distributionally Robust Optimization (DRO) for the Counterfactual Risk Minimization (CRM) problem.

counterfactual Decision Making

Partially Mutual Exclusive Softmax for Positive and Unlabeled data

no code implementations ICLR 2019 Ugo Tanielian, Flavian vasile, Mike Gartrell

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.

Language Modelling

Three Methods for Training on Bandit Feedback

no code implementations24 Apr 2019 Dmytro Mykhaylov, David Rohde, Flavian vasile, Martin Bompaire, Olivier Jeunen

There are three quite distinct ways to train a machine learning model on recommender system logs.

Recommendation Systems

Causal Embeddings for Recommendation: An Extended Abstract

no code implementations10 Apr 2019 Stephen Bonner, Flavian vasile

Recommendations are commonly used to modify user's natural behavior, for example, increasing product sales or the time spent on a website.

Domain Adaptation

RecoGym: A Reinforcement Learning Environment for the problem of Product Recommendation in Online Advertising

1 code implementation2 Aug 2018 David Rohde, Stephen Bonner, Travis Dunlop, Flavian vasile, Alexandros Karatzoglou

Recommender Systems are becoming ubiquitous in many settings and take many forms, from product recommendation in e-commerce stores, to query suggestions in search engines, to friend recommendation in social networks.

Product Recommendation Recommendation Systems +2

Neural Generative Models for Global Optimization with Gradients

no code implementations22 May 2018 Louis Faury, Flavian vasile, Clément Calauzènes, Olivier Fercoq

The aim of global optimization is to find the global optimum of arbitrary classes of functions, possibly highly multimodal ones.

Bayesian Optimization Gaussian Processes

Adversarial Training of Word2Vec for Basket Completion

no code implementations22 May 2018 Ugo Tanielian, Mike Gartrell, Flavian vasile

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.

Language Modelling Word Similarity

Rover Descent: Learning to optimize by learning to navigate on prototypical loss surfaces

no code implementations22 Jan 2018 Louis Faury, Flavian vasile

Learning to optimize - the idea that we can learn from data algorithms that optimize a numerical criterion - has recently been at the heart of a growing number of research efforts.

Navigate

Causal Embeddings for Recommendation

1 code implementation23 Jun 2017 Stephen Bonner, Flavian vasile

Many current applications use recommendations in order to modify the natural user behavior, such as to increase the number of sales or the time spent on a website.

Domain Adaptation

Contextual Sequence Modeling for Recommendation with Recurrent Neural Networks

1 code implementation23 Jun 2017 Elena Smirnova, Flavian vasile

Recommendations can greatly benefit from good representations of the user state at recommendation time.

Session-Based Recommendations

Meta-Prod2Vec - Product Embeddings Using Side-Information for Recommendation

2 code implementations25 Jul 2016 Flavian Vasile, Elena Smirnova, Alexis Conneau

We propose Meta-Prod2vec, a novel method to compute item similarities for recommendation that leverages existing item metadata.

Cost-sensitive Learning for Utility Optimization in Online Advertising Auctions

no code implementations11 Mar 2016 Flavian Vasile, Damien Lefortier, Olivier Chapelle

One of the most challenging problems in computational advertising is the prediction of click-through and conversion rates for bidding in online advertising auctions.

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