Log inSign up
Andreas Mueller
9,439 posts
Andreas Mueller profile banner
@amuellerml

Andreas Mueller

@amuellerml
Machine learner, Python geek and scikit-learn developer. Principal Research SDE @AzureData @Microsoft. Posting on LinkedIn now.
Santa Cruz Mountains
amueller.github.io
Joined January 2012
1,037
Following
47.9K
Followers
RepliesRepliesRepostsRepostsMediaMedia

Log in or sign up for X

See what’s happening and join the conversation

Continue with phone
or
Log in with username or email
Terms·Privacy·Cookies·Accessibility·Ads Info·© 2026 X Corp.
  • @amuellerml
    Andreas Mueller
    @amuellerml
    Sep 8
    I'm so thankful to have been part of this incredible team effort. The next generation of models will be truly incredible.
    @OpenAI
    OpenAI
    @OpenAI
    Sep 8
    We’re sharing a solution to the Navier-Stokes Millennium Prize Problem, one of the deepest problems at the frontier of mathematics. The proof was produced by a group of agents, using an OpenAI next-generation model significantly more capable than GPT-6 Astra. The problem
    Image
    10
  • @amuellerml
    Andreas Mueller
    @amuellerml
    Feb 11, 2025
    New preprint arxiv.org/abs/2502.05392 Open Challenges in Time Series Anomaly Detection: An Industry Perspective This is a vision paper about what I think it missing from current research in time series anomaly detection, and how it could align better with practical applications.
    arXiv logo
    arxiv.org
    Open Challenges in Time Series Anomaly Detection: An Industry Perspective
    Current research in time-series anomaly detection is using definitions that miss critical aspects of how anomaly detection is commonly used in practice. We list several areas that are of practical...
    4
  • @amuellerml
    Andreas Mueller
    @amuellerml
    Aug 15, 2024
    I'm pretty frustrated with the current review process in ML (both from an author, reviewer and meta-reviewer perspective). There's possible solutions or at least experiments and changes, but I feel like business as usual is no longer feasible.
    3
  • @amuellerml
    Andreas Mueller
    @amuellerml
    Dec 15, 2023
    @MadelonHulsebos knows what's up
    Image
  • @amuellerml
    Andreas Mueller
    @amuellerml
    Dec 15, 2023
    I'm excited to share our results on MotherNet, a new hyper-network architecture based on TabPFN that can learn an MLP in-context using a single forward pass. This substantially improves prediction times over predicting with TabPFN directly: arxiv.org/abs/2312.08598
    3
Advertisement
Advertisement