89 citations · 239 across the 23 of their papers we have counts for
24 papers
PAIR: Memory-Efficient and Fast Inference with Reading--Reasoning Fusion
Sejun Park, Haocheng Xia, Yongjoo Park
For context-based question answering, using one large model for both evidence extraction and answer reasoning requires substantial memory and computation. Existing approaches trade…
A continuous confinement-deconfinement transition in a triangular quantum magnet
Suguru Hosoi, Sejun Park, Michihiro Hirata +13
A continuous transition between phases hosting distinct excitations---bosonic magnons versus fermionic spinons---is a long-sought phenomenon in quantum magnetism, analogous to the…
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,…
Uniform Stability and Generalization Error of GD and SGD on Fixed-Point Parameters
Jonghyun Shin, Sejun Park
We analyze generalization error, uniform stability, and uniform argument stability of gradient descent (GD) and stochastic gradient descent (SGD) over discrete parameter spaces, wh…
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…
Expressive Power of ReLU and Step Networks under Floating-Point Operations
Yeachan Park, Geonho Hwang, Wonyeol Lee +1
The study of the expressive power of neural networks has investigated the fundamental limits of neural networks. Most existing results assume real-valued inputs and parameters as w…