user avatar
Michael Oberst
@MichaelOberst
Assistant Professor of CS at @JohnsHopkins, Part-time Visiting Scientist @AbridgeHQ. Previously: Postdoc at @CarnegieMellon. PhD from @MIT_CSAIL.
Baltimore, MD
michaelkoberst.com
Joined August 2011
984
Following
2,058
Followers
Posts
  • user avatar
    Michael Oberst
    @MichaelOberst
    May 26, 2023
    It's official! I'll be joining @JohnsHopkins as an Assistant Professor of Computer Science in summer 2024 - in the interim I'll be a postdoc at @CarnegieMellon in the Machine Learning Department working with @zacharylipton. Excited for the next chapter!
    46K
  • user avatar
    Michael Oberst
    @MichaelOberst
    Nov 27, 2024
    I'm recruiting PhD students for Fall 2025! CS PhD Deadline: Dec. 15th. I work on safe/reliable ML and causal inference, motivated by healthcare applications. Beyond myself, Johns Hopkins has a rich community of folks doing similar work! Come join us!
    52K
  • user avatar
    Michael Oberst
    @MichaelOberst
    Dec 3, 2023
    I'm recruiting PhD students for my lab at Johns Hopkins! Please apply if you're interested in reliable ML / causal inference for decision-making in healthcare. See my website (moberst.com) for more info. Deadline 12/15. Retweets welcome :) cs.jhu.edu/academic-progr…
    113K
  • user avatar
    Michael Oberst
    @MichaelOberst
    Jul 21, 2021
    When can we learn predictive models that are robust to shifts in unobserved variables? With co-authors @nikolajthams, Jonas Peters, and @david_sontag, we tackle this question in our recent ICML paper. Paper: arxiv.org/abs/2103.02477 Video: youtu.be/8ZiZDtJDIFk [1/n]
  • user avatar
    Michael Oberst
    @MichaelOberst
    Jul 21, 2022
    How should you evaluate the worst-case performance of your model under distribution shift, with only data from the training distribution? Preprint with @david_sontag, @nikolajthams, at SCIS (Fri) and PODS (Sat) workshops at #ICML2022 Paper: arxiv.org/abs/2205.15947 (1/6)
  • user avatar
    Michael Oberst
    @MichaelOberst
    Nov 2, 2020
    When doing causal inference (e.g., comparing effectiveness of drugs, or evaluating a treatment policy) how do you characterize the population to whom your conclusions apply? Belated thread on our AISTATS-20 paper [1/5] Paper arxiv.org/abs/1907.04138 Video slideslive.com/38930020/chara…
    GIF
  • user avatar
    Michael Oberst
    @MichaelOberst
    Jun 12, 2019
    I'll be presenting "Counterfactual Off-Policy Evaluation with Gumbel-Max Structural Causal Models" at 2:20pm today in the Grand Ballroom at #ICML2019 @icmlconf. Please also stop by our poster (72) at 6:30pm! This is work with my advisor @david_sontag.
  • user avatar
    Michael Oberst
    @MichaelOberst
    Jul 18, 2022
    Just got my badge at #ICML2022, it’s been a while! Excited to reconnect with old friends and meet new ones - DM me if you’re interested in chatting about causality and/or distributional robustness!
  • user avatar
    Michael Oberst
    @MichaelOberst
    Dec 5, 2023
    I'll be at NeurIPS next week - excited to see old friends and meet new ones with similar research interests (reliable ML/causal inference/ML for healthcare). Hit me up (DM or email) if you'll be at NeurIPS and would like to chat! I'm also recruiting PhD students for Fall 2024.
    user avatar
    Michael Oberst
    @MichaelOberst
    Dec 3, 2023
    I'm recruiting PhD students for my lab at Johns Hopkins! Please apply if you're interested in reliable ML / causal inference for decision-making in healthcare. See my website (moberst.com) for more info. Deadline 12/15. Retweets welcome :) cs.jhu.edu/academic-progr…
    5K
  • user avatar
    Michael Oberst
    @MichaelOberst
    Dec 21, 2023
    Worth reading, esp. for PhD students stressed about # of pubs. Refreshing to have a take from someone who isn't "on the other side", as Elan puts it. Since Elan is on the job market, I should note he really puts this into practice - I have deep respect/admiration for his work.
    user avatar
    Elan Rosenfeld
    @ElanRosenfeld
    Dec 20, 2023
    Another round of "publication incentives are messed up". He's right, of course, but the people who say this are almost always those who publish lots and are no longer beholden to the game. This is something I've thought a lot about. As a senior PhD student, I have no... 1/n
    7.9K
  • user avatar
    Michael Oberst
    @MichaelOberst
    Nov 29, 2022
    I'm at #NeurIPS2022! Presenting (w/@david_sontag) 1⃣ Evaluating Robustness to Dataset Shift via Parametric Robustness Sets (Tue 4pm, #313) neurips.cc/virtual/2022/p… 2⃣ Falsification before Extrapolation in Causal Effect Estimation (Thu 11am, #813) neurips.cc/virtual/2022/p… 🧵(1/3)
  • user avatar
    Michael Oberst
    @MichaelOberst
    Jun 11, 2019
    The Whova app schedule at #ICML2019 does not appear to be robust to adversarial words like “lunch”...
  • user avatar
    Michael Oberst
    @MichaelOberst
    Jul 22, 2022
    Come check out the poster in the Spurious Correlations, Invariance, and Stability (SCIS) workshop at #ICML2022 ! Come chat 1:30pm-2:45pm today (Fri), in room 340, and again from 5:45pm-7pm.
    user avatar
    Michael Oberst
    @MichaelOberst
    Jul 21, 2022
    How should you evaluate the worst-case performance of your model under distribution shift, with only data from the training distribution? Preprint with @david_sontag, @nikolajthams, at SCIS (Fri) and PODS (Sat) workshops at #ICML2022 Paper: arxiv.org/abs/2205.15947 (1/6)
  • user avatar
    Michael Oberst
    @MichaelOberst
    Nov 29, 2022
    Replying to @MichaelOberst
    2⃣ How should you use experimental data in causal inference, if it *excludes* the population you care about? Idea: Uncover bias in observational data that *does* cover the relevant population (w/@zeshanmh @rg_shih @david_sontag) 📅 Poster: Thu 11am, #813 arxiv.org/abs/2209.13708