Researchers debate optimizer equivariance: argument without orthogonality is more convincing
jasondeanlee · x · 2026-11-10
Researchers Jason Lee and Jianlin discuss the geometric properties of an optimizer in a recent work.
Lee initially questioned how w₁ᵀg₁ = w₂ᵀg₂ implies approximately w₁ᵀg₁ = 0 = w₂ᵀg₂. He then noted the paper's comment that the optimizer is equivariant, which doesn't require orthogonality, and concluded "this one is more convincing."
More from Research
- Quanta: Injecting 'thoughts' into LLMs to test whether AI can introspect — burny_tech · 2026-11-10
- 1,000 Fable agents formalize Fermat's Last Theorem in 30 hours; Opus 5.5 hits 26% — burny_tech · 2026-11-10
- Two CoRL papers speed up VLAs 2.4x and 4.7x, fast enough for real-time robot control — songhan_mit · 2026-11-10
- Four Free Math Books for ML: Linear Algebra, Probability, Optimization, Information Theory — cneuralnetwork · 2026-11-10
- 4 free math books that actually matter for ML: linear algebra to information theory — cneuralnetwork · 2026-11-10
- Meta FAIR's e-means beats k-means in 1/10 epochs with 10-45x GPU speedups — burny_tech · 2026-11-10