@LesterMackey
Account based inUnited States
About this account
- Account based in
- United States
- Connected via
- Web
Account-level information from X, not a live location or the device used for a specific post.
Machine learning researcher @MSFTResearch (@MSRNE); adjunct professor @Stanford
Joined November 2010
- Tweets618
- Following277
- Followers3K
- Likes1.5K
Pinned Tweet
Last year my family wrestled with a math conundrum: our ages all turned odd in sequence but starting with my older son, even though my wife is the oldest and my birthday comes first each year. Why was Noah the first to turn an odd age? Do all families experience these odd cycles?
Test your math skills with our latest puzzle!
sciencenews.org/article/math…
Lester Mackey retweeted
Meet the 2026 MacArthur Fellows!
These 20 individuals explore the depths of our humanity, reveal untold origins to modern challenges, and expand the edges of scientific inquiry and life-saving research. #MacFellow
macfound.org/programs/awards…
Lester Mackey retweeted
🥉 Congratulations to @Schmidt_Center postdoctoral fellow @skoularidou who was presented the Guy Medal in Bronze for her outstanding contributions to statistics and data science by the @RoyalStatSoc at their Annual Conference this September!
Learn more: rss.org.uk/news-publication/…
Lester Mackey retweeted
Next Tuesday, our MSR NE Generative Modeling and Sampling Seminar will feature @VesseronNina speaking about "Sample and Map from a Single Convex Potential: Generation using Conjugate Moment Measures"!
Information to join below 👇
Lester Mackey retweeted
🎉 We’re excited to announce the Keynote Speakers for #UAI2026 — three researchers shaping the future of causal learning, large-scale ML, and responsible AI. 👇
Lester Mackey retweeted
Try our latest puzzle and see if you can figure out a sequence of odd events.
sciencenews.org/article/math…
[LG] Domain-Aware Scaling Laws Uncover Data Synergy
K Hamidieh, L Mackey, D Alvarez-Melis [MIT & Microsoft Research] (2026)
arxiv.org/abs/2607.11052
Lester Mackey retweeted
Very excited about this work, led brilliantly by @kimiahmdh
Does your data mixture give you synergy vibes? Like math-and-code-kind-of-vibes? Here's one (technically, two) ways to turn those vibes into concrete estimates, which can then be used to optimize mixture design.
Lester Mackey retweeted
Test your math skills with our latest puzzle!
sciencenews.org/article/math…
Lester Mackey retweeted
Can we tell whether data domains cooperate or compete during pretraining?
Adding code to the mix makes models better at math, while some other combinations hurt each other. We call this data synergy. Turns out you can incorporate data synergy into scaling laws and estimate it 🧵
Lester Mackey retweeted
arxiv.org/abs/2607.11052
Could a dataset pair have synergy, such that, if used together, it could be more effective than the sum of their effects (on the benchmarks)?
Lester Mackey retweeted
Today, I will be presenting our paper (w/ @LesterMackey) on near-linear attention in theory and practice at ICML in Seoul! If you are around and interested in principled attention approximations, please stop by!
📍Hall A #2714
📅Wednesday July 8, 10:30
🔗arxiv.org/abs/2602.10056
Lester Mackey retweeted
To address pure or applied mathematics—that is not a question for Prof @EmmanuelCandes, as he integrates both via mathematical analysis, becoming one of 2026 #ShawPrize Laureates in #MathematicalSciences.
Let’s hear from Prof Ngaiming Mok, Chair of Selection Committee.
@Stanford
Lester Mackey retweeted
Join us in recognizing Delta's Rising Professors of 2026! 🎉
Congrats to the current and incoming assistant professors our community nominated as truly exceptional. These individuals were recognized for the quality of their research, teaching, mentorship, community involvement, and industry impact.
These are the people that truly push the frontier, carefully mentor their students, and have incredibly strong research taste in their domain. We are honored to play a small role in recognizing them.
deltainstitutes.org/rising-p…
Lester Mackey retweeted
Next Tuesday, our MSR NE Generative Modeling and Sampling Seminar will feature @YuanqiD and me speaking about "Rare event analysis via stochastic optimal control" (arxiv.org/abs/2604.13213)!
Information to join below 👇
How do you study events that almost never happen? 🧵
Protein folding, phase transitions, chemical reactions—rare but decisive ⚡, and a nightmare for classical simulation.
Our new paper tackles this with stochastic optimal control: a unifying way to learn reaction statistics, sample transition paths, and go beyond reversible dynamics.
🤖 Made with AI
Lester Mackey retweeted
Very excited to get this work out! To learn the non-equilibrium behavior of scientific systems, we need to solve a control/RL problem!
How do you study events that almost never happen? 🧵
Protein folding, phase transitions, chemical reactions—rare but decisive ⚡, and a nightmare for classical simulation.
Our new paper tackles this with stochastic optimal control: a unifying way to learn reaction statistics, sample transition paths, and go beyond reversible dynamics.
Lester Mackey retweeted
Well, the idea seems cool. This uses a coreset idea from approximation theory to "expresss" strong non-causal attention approximation into a causal, streaming one. arxiv.org/abs/2606.10944
