Search Results for author:
Found 14 papers, 2 papers with code
Robust Consensus in Ranking Data Analysis: Definitions, Properties and Computational Issues
As the issue of robustness in AI systems becomes vital, statistical learning techniques that are reliable even in presence of partly contaminated data have to be developed.
Jointly Efficient and Optimal Algorithms for Logistic Bandits
Logistic Bandits have recently undergone careful scrutiny by virtue of their combined theoretical and practical relevance.
Pure Exploration and Regret Minimization in Matching Bandits
Finding an optimal matching in a weighted graph is a standard combinatorial problem.
Regret Bounds for Generalized Linear Bandits under Parameter Drift
Generalized Linear Bandits (GLBs) are powerful extensions to the Linear Bandit (LB) setting, broadening the benefits of reward parametrization beyond linearity.
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.
Instance-Wise Minimax-Optimal Algorithms for Logistic Bandits
It was shown by Faury et al. (2020) that the learning-theoretic difficulties of Logistic Bandits can be embodied by a large (sometimes prohibitively) problem-dependent constant $\kappa$, characterizing the magnitude of the reward's non-linearity.
Real-Time Optimisation for Online Learning in Auctions
In display advertising, a small group of sellers and bidders face each other in up to 10 12 auctions a day.
Do Not Mask What You Do Not Need to Mask: a Parser-Free Virtual Try-On
This task requires fitting an in-shop cloth image on the image of a person, which is highly challenging because it involves cloth warping, image compositing, and synthesizing.
Improved Optimistic Algorithms for Logistic Bandits
For logistic bandits, the frequentist regret guarantees of existing algorithms are $\tilde{\mathcal{O}}(\kappa \sqrt{T})$, where $\kappa$ is a problem-dependent constant.
End-to-End Learning of Geometric Deformations of Feature Maps for Virtual Try-On
This task requires to fit an in-shop cloth image on the image of a person.
Bridging the gap between regret minimization and best arm identification, with application to A/B tests
State of the art online learning procedures focus either on selecting the best alternative ("best arm identification") or on minimizing the cost (the "regret").
Neural Generative Models for Global Optimization with Gradients
The aim of global optimization is to find the global optimum of arbitrary classes of functions, possibly highly multimodal ones.
Offline A/B testing for Recommender Systems
Before A/B testing online a new version of a recommender system, it is usual to perform some offline evaluations on historical data.
Distributed SAGA: Maintaining linear convergence rate with limited communication
In recent years, variance-reducing stochastic methods have shown great practical performance, exhibiting linear convergence rate when other stochastic methods offered a sub-linear rate.
