## 20 Jan 2021 [5 papers @ICLR 2021, 1 paper @ALT 2021 co-authored by Criteo AI Lab folks!](https://ailab.criteo.com/5-papers-iclr-2021-1-paper-alt-2021-co-authored-by-criteo-ai-lab-folks/) Happy to have 5 papers accepted at ICLR 2021 (among which 2 oral presentations) and 1 paper at ALT 2021! - **ICLR 2021:** Scalable Learning and MAP Inference for Nonsymmetric Determinantal Point Processes (oral), Mike Gartrell, Insu Han, Elvis Dohmatob, Jennifer Gillenwater, Victor-Emmanuel... [Read More](https://ailab.criteo.com/5-papers-iclr-2021-1-paper-alt-2021-co-authored-by-criteo-ai-lab-folks/) ## 01 Oct 2020 [9 papers accepted to @NeurIPS20 co-authored by researchers from Criteo AI Lab](https://ailab.criteo.com/9-papers-accepted-neurips20-from-criteo-ai-lab/) We are happy to have 9 papers co-authored by researchers from the Criteo AI Lab at NeurIPS 2020 - Online non-convex optimization with inexact models, A. Héliou, M. Martin, P. Mertikopoulos, and T. Rahier - Explore aggressively, update conservatively: Stochastic extragradient... [Read More](https://ailab.criteo.com/9-papers-accepted-neurips20-from-criteo-ai-lab/) ## 18 Sep 2020 [Series of posts on "Counterfactual evaluation and Recommender systems", by A. Gilotte](https://ailab.criteo.com/series-of-posts-on-counterfactual-evaluation-and-recommender-systems-by-a-gilotte-https-criteo-research-github-io-counterfactual_evaluation_and_recommendation/) Alex Gilotte, researcher at the Criteo AI Lab, details how counterfactual reasoning may be applied to evaluate a recommender system. The first posts introduce the topic and the intuitions behind the mathematics of counterfactual reasoning, and the later... [Read More](https://ailab.criteo.com/series-of-posts-on-counterfactual-evaluation-and-recommender-systems-by-a-gilotte-https-criteo-research-github-io-counterfactual_evaluation_and_recommendation/) ## 08 Sep 2020 [New post by O. Koch: "The Trade-Offs of Large-Scale Machine Learning: the price of time"](https://ailab.criteo.com/new-post-by-o-koch-the-trade-offs-of-large-scale-machine-learning-the-price-of-time/) What defines large-scale machine learning? This seemingly innocent question is often answered with petabytes of data and hundreds of GPUs. It turns out that large-scale machine learning does not have much to do with all of that. [Read More](https://ailab.criteo.com/new-post-by-o-koch-the-trade-offs-of-large-scale-machine-learning-the-price-of-time/) ## 02 Sep 2020 [Best student ML paper award runner-up @ECMLPKDD](https://ailab.criteo.com/best-student-ml-paper-award-runner-up-ecmlpkdd/) The paper on "A Principle of Least Action for the Training of Neural Networks" by Skander Karkar, Patrick Gallinari and their LIP6_lab co-authors, has been selected as the best student ML paper award Runner-up @ECMLPKDD! [Read More](https://ailab.criteo.com/best-student-ml-paper-award-runner-up-ecmlpkdd/) ## 06 Aug 2020 [DeepR — Training TensorFlow Models for Production](https://ailab.criteo.com/deepr-training-tensorflow-models-for-production/) The Reco team has released DeepR, a package to train deep recommendation models in production! See the full post here, with links to Github, docs, quick start guide and some examples: DeepR on Medium. [Read More](https://ailab.criteo.com/deepr-training-tensorflow-models-for-production/) ## 03 Jul 2020 [One paper accepted at ECCV2020: "Do not mask what you do not need to mask: a parser free Virtual Try-on"](https://ailab.criteo.com/one-paper-accepted-at-eccv2020-do-not-mask-what-you-do-not-need-to-mask-a-parser-free-virtual-try-on/) One paper accepted at ECCV2020! "Do not mask what you do not need to mask: a parser free Virtual Try-on" Authors: T. Issenhuth (Criteo AI Lab), J. Mary (Criteo AI Lab), C. Calauzènes (Criteo AI Lab) [Read More](https://ailab.criteo.com/one-paper-accepted-at-eccv2020-do-not-mask-what-you-do-not-need-to-mask-a-parser-free-virtual-try-on/) ## 10 Jun 2020 [1 paper accepted at ECML 2020: "A Principle of Least Action for the Training of Neural Networks"](https://ailab.criteo.com/1-paper-accepted-at-ecml-2020-a-principle-of-least-action-for-the-training-of-neural-networks/) One paper accepted at ECML 2020: A Principle of Least Action for the Training of Neural Networks. Authors. Skander Karkar (LIP6, Sorbonne Université / Criteo AI Lab), Ibrahim Ayed (LIP6, Sorbonne Université), Emmanuel de Bézenac (LIP6, Sorbonne Université)... [Read More](https://ailab.criteo.com/1-paper-accepted-at-ecml-2020-a-principle-of-least-action-for-the-training-of-neural-networks/) ## 01 Jun 2020 [9 papers @ICML 2020, from Criteo AI Lab](https://ailab.criteo.com/9-papers-icml-2020-from-criteo-ai-lab/) We are happy to have 9 papers co-authored by members of the Criteo AI Lab getting in ICML 2020: - Gradient-free Online Learning in Continuous Games with Delayed Rewards, A. Héliou, P. Mertikopoulos, and Z. Zhou. - Finite-Time Last-Iterate Convergence... [Read More](https://ailab.criteo.com/9-papers-icml-2020-from-criteo-ai-lab/) ## 26 May 2020 [2 papers accepted @COLT’20, from Criteo AI Lab](https://ailab.criteo.com/2-papers-accepted-at-colt20/) Two papers co-authored by Vianney Perchet, researcher at Criteo AI Lab, got accepted at COLT 2020 - Selfish Robustness and Equilibria in Multi-Player Bandits, E. Boursier, V. Perchet. https://arxiv.org/abs/2002.01197 - Covariance-adapting algorithm for semi-bandits with application to sparse rewards, P.... [Read More](https://ailab.criteo.com/2-papers-accepted-at-colt20/)