Showing 2026Show all
3 papers · 1 filter
cs.LG2026
Floating-Point Networks with Automatic Differentiation Can Represent Almost All Floating-Point Functions and Their Gradients
Sejun Park, Yeachan Park, Geonho Hwang
Theoretical studies show that for any differentiable function on a compact domain, there exists a neural network that approximates both the function values and gradients. However,…
cs.LG2026
Expressive Power of Floating-Point Neural Networks with Arbitrary Reduction Orders and Inexact Activation Implementations
Yeachan Park, Geonho Hwang, Wonyeol Lee +1
Most existing expressivity theories for neural networks assume exact real arithmetic, whereas practical neural networks are executed under finite-precision floating-point arithmeti…
cs.LG2026
On the Expressive Power of Floating-Point Transformers
Sejun Park, Yeachan Park, Geonho Hwang
The study on the expressive power of transformers shows that transformers are permutation equivariant, and they can approximate all permutation-equivariant continuous functions on…