170 citations · 527 across the 39 of their papers we have counts for
49 papers
MuonIO: Principled Norm-Aware Descent for Embedding Tables and Language Model Heads
Linkai Ma, Xinyu Luo, Mengbo Wang +3
The Muon optimizer derives its update rule for hidden linear layers by solving a local linearization of the loss penalized by the spectral norm, motivated by an RMS-stability argum…
The Advantages of Fresh Sketching for Ridge Regression
Linkai Ma, Qilin Li, Petros Drineas
Over the past 25 years, sketching and sampling have become widely used tools for accelerating large-scale regression. In iterative randomized solvers, a basic design choice is whet…
Stochastic Rounding Increases Small Singular Values
Linkai Ma, Tingzhou Yu, Petros Drineas
Over the past half-dozen years, stochastic rounding (SR) has regained significant attention as a quantization scheme for low-precision floating-point arithmetic, with applications…
Stacey: Promoting Stochastic Steepest Descent via Accelerated -Smooth Nonconvex Optimization
Xinyu Luo, Cedar Site Bai, Bolian Li +3
While popular optimization methods such as SGD, AdamW, and Lion depend on steepest descent updates in either or norms, there remains a critical gap in handli…
Game of Trust: How Trustworthy Does Your Blockchain Think You Are?
Petros Drineas, Rohit Nema, Rafail Ostrovsky +1
We investigate how a blockchain can distill the collective belief of its nodes regarding the trustworthiness of a (sub)set of nodes into a {\em reputation system} that reflects the…
A Note on the Stability of the Sherman-Morrison-Woodbury Formula
Linkai Ma, Christos Boutsikas, Mehrdad Ghadiri +1
We study the numerical stability of the Sherman-Morrison-Woodbury (SMW) identity. Let and assume and both have full-column rank. We explore error bounds for…