Lester Mackey
Machine learning researcher at Microsoft Research. Adjunct professor at Stanford.
- Reposted by Lester Mackey[Not loaded yet]
- Reposted by Lester MackeyEric Zimmermann, Harley Wiltzer, Justin Szeto, David Alvarez-Melis, Lester Mackey: KerJEPA: Kernel Discrepancies for Euclidean Self-Supervised Learning arxiv.org/abs/2512.19605 arxiv.org/pdf/2512.19605 arxiv.org/html/2512.19605
- I’m happy to share our new paper, “KerJEPA: Kernel Discrepancies for Euclidean Self-Supervised Learning”: arxiv.org/abs/2512.19605 This work builds on the LeJEPA framework by reinterpreting its regularization objective through the lens of kernel discrepancies.
- Doing so allows us to place LeJEPA within a broader family of self-supervised methods and to design more flexible objectives beyond Gaussian assumptions.
- Key contributions: •We show how LeJEPA can be viewed as a special case of a more general kernel discrepancy framework. •We introduce KerJEPAs, which allow for richer regularization via alternative kernels.
-
View full threadThis project was a collaboration with Eric Zimmerman Harley Wiltzer, Justin Szeto, and @dmelis.bsky.social Many helpful discussions shaped this work, and we’re happy to discuss with anyone interested in representation learning, self-supervision, or kernel methods.
- If you're a PhD student interested in interning with me or one of my amazing colleagues at Microsoft Research New England @msftresearch.bsky.social this summer, please apply here jobs.careers.microsoft.com/global/en/jo... If you'd like to work with me, please include my name in your cover letter!
- Reposted by Lester MackeyMicrosoft Research New York City (www.microsoft.com/en-us/resear...) is seeking applicants for multiple Postdoctoral Researcher positions in ML/AI! These are positions for up to 2 years, starting in July 2026. Application deadline: October 22, 2025
- Reposted by Lester MackeyMSR NYC is hiring spring and summer interns in AI/ML/RL! Apply here: jobs.careers.microsoft.com/global/en/jo...
- Only in LA 🐢
- Reposted by Lester MackeyVery excited to share our preprint: Self-Speculative Masked Diffusions We speed up sampling of masked diffusion models by ~2x by using speculative sampling and a hybrid non-causal / causal transformer arxiv.org/abs/2510.03929 w/ @vdebortoli.bsky.social, Jiaxin Shi, @arnauddoucet.bsky.social
- Could this be our future? (Sound on)
- Reposted by Lester Mackey[Not loaded yet]
- Reposted by Lester Mackey[Not loaded yet]
- If you're an undergraduate interested in interning with me or one of my amazing colleagues at Microsoft Research New England this summer, please apply here: msft.it/6015scgSJ
- Reposted by Lester MackeyTomorrow we're excited to host @sarahalamdari.bsky.social at Chalmers for the AI4Science seminar and hear about generative models for protein design! Talk at 3pm CEST. 🤩 For more info, including details on how to join virtually, please see psolsson.github.io/AI4ScienceSe... @smnlssn.bsky.social
- Reposted by Lester Mackey[Not loaded yet]
- Reposted by Lester Mackey[Not loaded yet]
- Reposted by Lester Mackey[Not loaded yet]
- Reposted by Lester MackeyJikai Jin, Lester Mackey, Vasilis Syrgkanis: It's Hard to Be Normal: The Impact of Noise on Structure-agnostic Estimation arxiv.org/abs/2507.02275 arxiv.org/pdf/2507.02275 arxiv.org/html/2507.02275
- Reposted by Lester Mackey[Not loaded yet]
- Reposted by Lester Mackey[Not loaded yet]
- Reposted by Lester Mackey[Not loaded yet]
- Reposted by Lester MackeyNeurIPS is seeking additional ethics reviewers this year. If you are able and willing to participate in the review process, please sign up at the form in the link: neurips.cc/Conferences/... Please share this call with your colleagues!
- Reposted by Lester Mackey[Not loaded yet]
- Reposted by Lester Mackey
🏆 I'm delighted to share that I've won a 2025 COPSS Emerging Leader Award! 😃 And congratulations to my fellow winners! 🙌🏽 Check out how each of us is improving and advancing the profession of #statistics and #datascience here: tinyurl.com/copss-emerging-leader-award - Reposted by Lester Mackey[Not loaded yet]
- Reposted by Lester MackeyNeurIPS 2025 is soliciting self-nominations for reviewers and ACs. Please read our blog post for details on eligibility criteria, and process to self-nominate:
- Reposted by Lester MackeyCongratulations to @lestermackey.bsky.social for receiving the 2025 COPSS Award! 🎉👏 Lester is currently the Chair of the Section on Bayesian Statistical Sciences (SBSS) of the American Statistical Association.
- Reposted by Lester MackeyOff to #AAAI25! We're presenting #SatCLIP (w/ @marccoru.bsky.social, @estherrolf.bsky.social, @calebrob6.bsky.social & @lestermackey.bsky.social) at the 12.30-2.30pm poster session on Feb 28! Let me know if you're around & want to chat #GeoAI!🛰️ Paper: tinyurl.com/5eejz5kw Code: tinyurl.com/2zm64967
- Reposted by Lester Mackey[Not loaded yet]
- Reposted by Lester Mackey[Not loaded yet]
- Reposted by Lester Mackey[Not loaded yet]
- New guarantees for approximating attention, accelerating SGD, and testing sample quality in near-linear time
- Inspired by the groundbreaking work of Amir Zandieh, Insu Han, Majid Daliri, @aminkarbasi.bsky.social, Yucheng Lu, Wentao Guo, Christopher De Sa, @afedercooper.bsky.social, Khiem Pham, Tiancheng Yuan, Yucheng Lu, and Carles Domingo-Enrich
- Why permute when you can cheaply permute?
- Reposted by Lester MackeyPlease read our statement on the remarks made by Dr. Rosalind Picard at her NeurIPS 2024 invited talk and our commitment to respect, inclusivity, and upholding our values: neurips.cc/Conferences/2024/StatementOnInclusivity
- Reposted by Lester MackeyInvited Talk, Right now! The Golem vs. Stone Soup: Understanding How Children Learn Can Help Us Understand And Improve AI Alison Gopnik West Exhibition Hall C, B3 Watch online: buff.ly/4g7tvuI
