Ambroise Odonnat

prof_pic_odonnat.jpg

Visiting TUM in Munich

I am a Predoctoral student at Huawei Noah’s Ark Lab under the supervision of Ievgen Redko. My research currently focuses on Machine Learning and Deep Learning under distribution shifts.

I graduated from Ecole des Ponts ParisTech in 2023 and hold a master’s degree from ENS Paris-Saclay in Mathematics, Vision, and Machine Learning (MVA). I did my master’s thesis in semi-supervised learning at Huawei Noah’s Ark Lab under the supervision of Ievgen Redko and Vasilii Feofanov.

Don’t hesitate to reach out for possible collaborations or questions regarding my research!

news

May 02, 2024 Presenting our AISTATS paper on ensemble diversity for robust self-training at AISTATS 2024 in Valencia, Spain. 🇪🇸 🎤
Mar 05, 2024 Presenting our AISTATS paper on ensemble diversity for robust self-training at the MLSP of ENS Lyon. 🦁 🎤
Feb 15, 2024 Very happy to share SAMformer, a lightweight transformer for time series forecasting. Check out the code here. 📑 :bulb:
Jan 19, 2024 Our paper Leveraging Ensemble Diversity for Robust Self-Training in the Presence of Sample Selection Bias has been accepted to AISTATS 2024. 📑 :trophy:
Jan 17, 2024 Very happy to share our new preprint on Unsupervised Accuracy Estimation. 📑 :bulb:

selected publications

  1. logo_hands.png
    MANO: Exploiting Matrix Norm for Unsupervised Accuracy Estimation Under Distribution Shifts
    Renchunzi Xie* ,  Ambroise Odonnat* , Vasilii Feofanov , and 3 more authors
    Preprint, 2024.
  2. transformers.png
    SAMformer: Unlocking the Potential of Transformers in Time Series Forecasting with Sharpness-Aware Minimization and Channel-Wise Attention
    Romain Ilbert* ,  Ambroise Odonnat* , Vasilii Feofanov , and 4 more authors
    Oral (top 5%), ICML, 2024. Also presented at CAp 2024 (oral).
  3. diversity.png
    Leveraging Ensemble Diversity for Robust Self-Training in the Presence of Sample Selection Bias
    Ambroise Odonnat , Vasilii Feofanov , and Ievgen Redko
    AISTATS, 2024. Also presented at CAp 2024 (long oral).
  4. neural_network.png
    Leveraging Gradients for Unsupervised Accuracy Estimation under Distribution Shift
    Renchunzi Xie ,  Ambroise Odonnat , Vasilii Feofanov , and 3 more authors
    Preprint, 2024.