Hong-Yi Wang (@HYWangphy) header
Hong-Yi Wang (@HYWangphy) profile picture

Ph.D. student studying quantum physics and machine learning theory

Princeton, NJ, USA
Joined April 2026
Photo by Hong-Yi Wang (@HYWangphy)Photo by Hong-Yi Wang (@HYWangphy)Photo by Hong-Yi Wang (@HYWangphy)Photo by Hong-Yi Wang (@HYWangphy)
Hong-Yi Wang retweeted
What determines the compressibility of a neural network? In our most recent work, we showed that (sufficiently smooth) deep MLPs can be compressed to a size that depends only on the input data dimension and, surprisingly, is independent of the model's width. arxiv.org/abs/2608.21752
2
15
107
5,422
1/7 🧵 Can we make neural networks and datasets radically smaller without losing anything? Our new ICLR 2026 paper says yes — provably. d variables can be losslessly compressed to O(polylog d), and this is optimal. 📄 Paper: openreview.net/forum?id=vxkz…
1
2
4
399
6/7 Application 2 — Improving neural scaling laws. Compress dataset (or width) from d to d′=⌈16d​⌉ before training. The scaling exponent roughly doubles in our experiments: – Dataset: α=0.68→1.27 – Width: α=0.31→0.61
1
31
7/7 Asymptotically, power-law scaling can be boosted all the way to stretched-exponential. Anywhere a permutation symmetry hides, compression follows. We also demo it on transformers. 💻 Code: github.com/WHY-David/moment_… w/ Di Luo, Tomaso Poggio, Isaac Chuang, @LiuZiyin10 Ziyin
2
48
Hong-Yi Wang retweeted
Excited to share our theory on the universal compressibility of neural nets (led by @HYWangphy)! This leads to a new dynamical lottery ticket hypothesis and implications for improving neural scaling laws. arxiv.org/abs/2510.00504 Check out our ICLR poster!
4
14
1
128
10,276
A new formulation of non-Hermitian band theory is applicable to any number of spatial dimensions, a development useful for the study of physical effects exclusive to open systems. Read go.aps.org/3TSHPxe #openaccedd #PRXjustpublished #PRXcondmatt
4
9
1,321