Paris Women in Machine Learning & Data Science

The Women in Machine Learning & Data Science (WiMLDS) Meetup aims to inspire, educate, regardless of gender, and support women and gender minorities in the field.
We are back for our 45th edition, are you ready to get all the answers about data science?
All genders may attend our meetups.

Agenda

---

19:00 - Launch of the evening by the Paris WiMLDS meetup team and Women in Big Data Paris

---

19:15 - Evaluation strategies with partially or unlabeled data by Daria Stefic, PhD, Data Scientist, and Sharone Dayan, Machine Learning Engineer, @ContentSquare

Abstract : When developing ML models for real life business problems, we are often dealing with partially or even unlabeled data. This poses challenges on the model evaluation. In this talk, we will present a couple of different ML models that share the problem of missing labeled data. We will briefly present the business context for developing such models, our evaluation strategies and possible future directions.

--

19:40 - Combinatorial Optimization with Policy Adaptation using Latent Space Search by Shikha Surana, Research Engineer, and Sophie Monnier, Business Development Engineer @InstaDeep

Abstract : Combinatorial Optimization underpins many real-world applications and yet, designing performant algorithms to solve these complex, typically NP-hard, problems remains a significant research challenge. Reinforcement Learning (RL) provides a versatile framework for designing heuristics across a broad spectrum of problem domains. Building on the intuition that performant search at inference time should be anticipated during pre-training, we propose COMPASS, a novel RL approach that parameterizes a distribution of diverse and specialized policies conditioned on a continuous latent space.

--