Ji-Ha's Blog
jiha-kim.github.io · 377 words · saved by 2 readers
Ji-Ha Kim’s blog for sharing things.
Post When Equivalent Weights Train Differently Why coordinate-level optimizers can behave differently on weights that represent the same model, and how quotient-aware updates remove the hidden gauge. May 6, 2026 Machine Learning , Mathematical Optimization Fast Tight Spectral-Norm Bounds A GPU-friendly algorithm for tight certified singular-value endpoint bounds using scaled Gram matrices, SYRKs, Frobenius reductions, and a small scalar moment problem. Apr 28, 2026 Numerical Linear Algebra , Matrix Computations Autoregression vs Diffusion - Understanding Sampling via Optimal…
saved by
related reading
- Modular Manifolds - Thinking Machines Labthinkingmachines.ai
- Marginally Better blogrishit-dagli.github.io
- Distill — Latest articles about machine learningdistill.pub
- Eric Jangevjang.com
- Home - colah's blogcolah.github.io
- Lil'Loglilianweng.github.io
- Pen and Paper Exercises in Machine Learningarxiv.org
- Natural Intelligencegreydanus.github.io
- Gregory Gundersengregorygundersen.com
- rsrch spacersrch.space
- Keep the gradient flowingfa.bianp.net
- Non_Interactive – Software & MLnonint.com