Blei Lab

@blei_lab

Machine learning lab at Columbia University. Probabilistic modeling and approximate inference, embeddings, Bayesian deep learning, and recommendation systems.

Vrijeme pridruživanja: lipanj 2017.

Tweetovi

Blokirali ste korisnika/cu @blei_lab

Jeste li sigurni da želite vidjeti te tweetove? Time nećete deblokirati korisnika/cu @blei_lab

  1. proslijedio/la je Tweet
    11. pro 2019.

    If you're at , come talk to us at the Human-Aligned AI Social on Thursday :)

    Poništi
  2. 9. pro 2019.

    -5:30pm: & David Blei, "Variational Bayes under Model Misspecification." - poster session @ East Exhibition Hall B +

    Prikaži ovu nit
    Poništi
  3. 9. pro 2019.

    -5:30pm: , & DaviD Blei "Using Embeddings to Correct for Unobserved Confounding in Networks." - poster session @ East Exhibition Hall B + C

    Prikaži ovu nit
    Poništi
  4. 9. pro 2019.

    -5:30pm: , , Mingyuan Zhou, David Blei and . "Poisson-Randomized Gamma Dynamical Systems." - poster session @ East Exhibition Hall B + C

    Prikaži ovu nit
    Poništi
  5. 9. pro 2019.

    The Blei Lab at on Dec 10th: -10:45am: & , David Blei "Adapting Neural Networks for the Estimation of Treatment Effects". - poster session @ East Exhibition Hall B + C

    Prikaži ovu nit
    Poništi
  6. proslijedio/la je Tweet
    9. pro 2019.

    Excited to present "Poisson-Randomized Gamma Dynamical Systems", a paper (2 years in the making!) with , Mingyuan Zhou, Dave , and , tomorrow at ! Poster #154. Tues 5:30–7:30 @ East Exhibition Hall B+C Paper:

    Prikaži ovu nit
    Poništi
  7. 5. pro 2019.

    Friday, 12/6 at : from , Max Raginsky from and our David Blei will give tutorials on & . More details:

    Poništi
  8. 6. stu 2019.

    Thursday, 11/7 at 2pm: David Blei will visit to talk about "The Blessings of Multiple Causes". This talk is part of the MaD seminar, organized by the Center for Data Science and the Courant Institute of Mathematical Sciences, NYU. Details:

    Poništi
  9. 16. lis 2019.

    Blei and reply to Ogburn et al. about the deconfounder.

    Poništi
  10. 2. lis 2019.

    Today at at 12pm: David Blei will present his joint work with "The Blessings of Multiple Causes".

    Poništi
  11. 24. ruj 2019.

    David Blei to give a mini-course on at this Thursday, Sept 26 & Friday, Sept. 27. This tutorial is part of Columbia's Program for Economic Research

    Poništi
  12. 30. srp 2019.

    Rajesh Ranganath to talk about Black Box Variational Inference at the Savage Award Session of . Today, 2:00 PM to 3:50 PM. Details:

    Poništi
  13. 29. srp 2019.

    The "Frequentist Consistency of Variational Bayes" () by and David Blei presented today at the Student Paper Award Session II of .

    Poništi
  14. 29. srp 2019.

    Today at : David Blei to discuss "The Blessings of Multiple Causes" with Guido Imbens, , Susan Murphy, and Kosuke Imai. Mon, 7/29/2019, 10:30 AM - 12:20 PM at CC-207.

    Poništi
  15. 15. srp 2019.

    "Topic Modeling in Embedding Spaces". New work from , , and David Blei develops a generative model of documents that marries traditional topic models with word embeddings. Check the preprint here:

    Poništi
  16. 26. lip 2019.

    "The Medical Deconfounder: Assessing Treatment Effect with Electronic Health Records (EHRs)" by Linying Zhang, , Anna Ostropolets, Jami Mulgrave, David Blei, and George Hripcsak to appear in the Machine Learning for Healthcare conference.

    Poništi
  17. proslijedio/la je Tweet
    6. lip 2019.

    We want to estimate a causal effect by adjusting for (gnarly) covariates using a neural net. How should we design the neural net? Answer: translate classical statistical results to neural net design! Works great. with and

    Prikaži ovu nit
    Poništi
  18. proslijedio/la je Tweet
    2. svi 2019.

    Hierarchical Recurrent State Space Models Reveal Discrete and Continuous Dynamics of Neural Activity in C. elegans This has been a big part of my postdoc and I'm glad to finally share it! Huge thanks to my coauthors/mentors Annika, Dave, Manuel, and Liam.

    Prikaži ovu nit
    Poništi
  19. 18. tra 2019.

    Today at at 3pm: David Blei will talk about the "The Blessings of Multiple Causes", a way to do causal inference from observational data with weaker assumptions that the classical methods require.

    Poništi
  20. proslijedio/la je Tweet
    13. tra 2019.

    1/ of presents the holdout randomization test as a principled and tractable approach to feature selection using black box predictive models, producing a valid p-value for each feature while enabling FDR control. MIA

    Prikaži ovu nit
    Poništi

Čini se da učitavanje traje već neko vrijeme.

Twitter je možda preopterećen ili ima kratkotrajnih poteškoća u radu. Pokušajte ponovno ili potražite dodatne informacije u odjeljku Status Twittera.

    Možda bi vam se svidjelo i ovo:

    ·