Michael Choi
@michaelchchoi
Assistant Professor @NUSingapore. Applied probabilist. Probability, MCMC, statistical physics, optimization, information theory, TCS. Opinions my own.
arxiv.org/abs/2111.02675 Ever experience the frustration that your MCMC algorithm is stuck at local mode? No worries, landscape modification comes to your rescue. [1/3]
I am pleased to announce that together with some friends, we are organising a workshop on Non-Reversible MCMC Sampling, taking place at Newcastle University from 8–10 September 2025. Details can be found at the workshop website sites.google.com/view/probai-wo….
Another classic by this pair is the first cutoff paper of Bernoulli-Laplace model. Diaconis, P. & Shahshahani, M. Time to Reach Stationarity in the Bernoulli-Laplace Diffusion Model. SIAM J Math Anal 18(1):208-218. Link from Diaconis website: drive.google.com/file/d/1axFWUv…
This is the second-best paper I have ever read. It combines random walks, group theory, and representation theory. It's amazing how two people managed to combine so many difficult topics into one clean paper.
This is the second-best paper I have ever read. It combines random walks, group theory, and representation theory. It's amazing how two people managed to combine so many difficult topics into one clean paper.
Jason Gaitonde, Elchanan Mossel. [math.PR]. Comparison Theorems for the Mixing Times of Systematic and Random Scan Dynamics. (Replacement). arxiv.org/abs/2410.11136
Pietro Caputo, Zongchen Chen, Yuzhou Gu, Yury Polyanskiy: Entropy Contractions in Markov Chains: Half-Step, Full-Step and Continuous-Time arxiv.org/abs/2409.07689 arxiv.org/pdf/2409.07689
Yuanyuan Liu 👍 Aaron Smith 👍
New article on First View titled: Perturbation Analysis of Markov Chain Monte Carlo for Graphical Models. Scheduled for publication in JAP September 2025 cambridge.org/core/journals/…
Hier sind meine Folien für das Seminar an der Universität Ulm! Ich hoffe, es ist ein guter Anfang für die zwei Wochen hier! 162348.github.io/posts/2025/Sli…
🚨 PhD opportunity! I’m recruiting a PhD student with a strong background in math/stats/CS to join my group at NTU Singapore 🇸🇬 Start: Jan or Aug 2026 Topic: Foundations of Epistemic Uncertainty in ML 🧠🔍 📌 Details: chau999.github.io/group/ RT appreciated!
Congratulations to my former student, Jun Yang, for winning a Sapere Aude !! Jun has opened up a number of new areas of high-dimensional Monte Carlo analysis and Monte Carlo algortithms since graduating. dff.dk/en/our-funded-…
Permutations accelerate Markov chain convergence and MCMC as well! onlinelibrary.wiley.com/doi/10.1002/rs…
Antoine Luciano, Charly Andral, Christian P. Robert, Robin J. Ryder. [stat.ME]. Permutations accelerate Approximate Bayesian Computation. arxiv.org/abs/2507.06037
Francesca Romana Crucinio. [stat.ME]. A note on the unique properties of the Kullback--Leibler divergence for sampling via gradient flows. arxiv.org/abs/2507.04330
Another year: arrived at Xuzhou for the 20th Workshop on Markov processes and related topics, with a book of selected papers on popular science by Mufa Chen
Arrived for the 19th (!!) Workshop on Markov processes and related topics at Fuzhou.
Check out my earlier work on what I call landscape modification!
cambridge.org/core/journals/… （どういう話？）
My first bioinformatics paper on adaptive gradient scaling for protein structure prediction is out in BMC Bioinformatics! It is very fun and fulfilling to work from Markov chain theory to protein and back. Joint work with Vitalii Kapitan. bmcbioinformatics.biomedcentral.com/articles/10.11…
Alexander Goyal, et al.: Mixing Time Bounds for the Gibbs Sampler under Isoperimetry arxiv.org/abs/2506.22258 arxiv.org/pdf/2506.22258 arxiv.org/html/2506.22258
🎖️The 2025 @KyotoPrize Shun-ichi Amari 👏👏👏 🔓Amari's research survey article "Information geometry" (48 pages): link.springer.com/article/10.100… #DownloadForFree til July 31, 2025 🎉 🏵️#TakagiLectures ↓Expository news on his prize acceptance in Greek🇬🇷+🌐
🏆 Το Βραβείο Κιότο 2025 για την Προηγμένη Τεχνολογία στον Shun-ichi Amari eisatopon.blogspot.com/2025/06/2025-s…
The article is published in RSA and is open access thanks to @NUSLibraries and @WileyGlobal Check it out! doi.org/10.1002/rsa.70…
Proud to share that this paper has been accepted at Random Structures and Algorithms. arxiv.org/abs/2411.08295 Thanks to @max_hird for raising an important question, which forms the basis of this work.