Paul Mangold
@pmangold_
Post-doc at @Polytechnique. Optimization, federated learning, reinforcement learning. Previously PhD student @Inria_Lille on private optimization and fairness.
If you're in Vancouver this week, let's meet up! 👀 Traveling to attend ICML, and specifically ICML 2025 Workshop on Collaborative and Federated Agentic Workflows (CFAgentic) on Saturday, July 19 🚀 @flwrlabs is giving a talk at ca. 2pm PDT, and will join a panel discussion…
📢 Catch Flower Labs and William Lindskog-Munzing at ICML 2025! We’re excited to be part of the #ICML2025 Workshop on Collaborative and Federated Agentic Workflows, happening July 19 in Vancouver 🇨🇦. 🎙️ Talk: "Federated AI with Flower: Recent Advancements and Scaling to…
We are presenting the paper with Milos tomorrow at 11am, come chat at our poster ! 11am, East Exhibition Hall A-B #E-1911
📯 ICML25 spotlight 📯 How to detect and prevent audit manipulations? Do you remember 🚗 Dieselgate 💨? The car computer would detect when it was on a test-bench and reduce the engine power to fake environmental compliance. Well, this can happen in AI too. 🧵1/6
I am at ICML, presenting our new convergence results for Scaffold with **linear speed-up**. It's poster W-621 between 1:30 and 4:00. Come and chat! Paper: arxiv.org/abs/2503.07594
We’ll be at poster E-1307 today! Come chat with us about training-free guidance, diffusion models, and all things generative! Paper: arxiv.org/abs/2502.03332
❓ How long does SGD take to reach the global minimum on non-convex functions? With @FranckIutzeler, J. Malick, P. Mertikopoulos, we tackle this fundamental question in our new ICML 2025 paper: "The Global Convergence Time of Stochastic Gradient Descent in Non-Convex Landscapes"
on my way back to NYC, i met wise Leon Bottou in the airport. we talked. then i told him "you should tweet that!" and, he delivered much more than a tweet: a blog post with thoughts and insights on AI research only he can deliver this clearly and succinctly.
What course on AI should you take? Do you need theory, practice and a step-by-step plan? @flwrlabs already has a complete coursework on @DeepLearningAI. Learn how to train and fine-tune your AI in a decentralized way. This means you will in practice be able to utilize the…
I'm at NeurIPS today with @CharlesArnal to present our work on Iteration Head (Poster session 2 at 4:30PM-7:30PM PST) Come by and say hi! 👋 @CabannesVivien @alicey_ang @f_charton @KempeLab neurips.cc/virtual/2024/p…
I am excited to be at NeurIPS this week. Friday afternoon, I'll present our work on federated linear stochastic approximation and TD learning: arxiv.org/abs/2402.04114 The poster is on Friday afternoon nips.cc/virtual/2024/p… Write to me if you want to chat!
Consider this advice from 2023 medicine laureate Katalin Karikó on managing stress. Do you have any tips for stress management?
I also had to do one…
Types of Scientific Paper xkcd.com/2456/ m.xkcd.com/2456/
We’re excited to announce that the AAAI Workshop on Privacy-Preserving Artificial Intelligence (PPAI-25) is back! 🔗 ppai-workshop.github.io Please share widely! 🙏 Hosted at the 39th AAAI Conference on Artificial Intelligence (AAAI-25), this workshop will bring together AI…
Doing good science is 90% finding a science buddy to constantly talk to about the project.
"My paper bridges the gap in the literature." My paper...
We are thrilled to say that NeurIPS@Paris is back for a 4th edition on the 4th and 5th of December 2024 at @Sorbonne_Univ_. A great occasion to meet + discuss recent advances in ML in central Paris! More info: neuripsinparis.github.io/neurips2024par… Registration: forms.gle/Fc4nbeW6ubahYb…
We have a number of PhD, postdoc and intern positions in our team, mostly on distributed learning. Check here if interested: team.inria.fr/neo/job-offers/