5 papers
Boltzmann Attention: Learnable Ising Couplings for Cooperative Attention
Gilhan Kim, Daniel K. Park
Attention mechanisms are central to modern sequence models, yet standard attention computes relevance primarily through individual query--key similarities. Although softmax normali…
Multi-Mode Quantum Annealing for Generative Representation Learning with Boltzmann Priors
Gilhan Kim, Daniel K. Park
Energy-based models provide a natural bridge between statistical physics and machine learning by representing data through structured energy landscapes. Boltzmann machines are a pa…
Information-Geometric Decomposition of Generalization Error in Unsupervised Learning
Gilhan Kim
We decompose the Kullback--Leibler generalization error (GE) -- the expected KL divergence from the data distribution to the trained model -- of unsupervised learning into three no…
Boltzmann Sampling by Diabatic Quantum Annealing
Ju-Yeon Gyhm, Gilhan Kim, Hyukjoon Kwon +1
Boltzmann sampling is a central component of many computational frameworks, including numerous algorithms in machine learning. Although quantum annealers have been investigated as…
Diabatic quantum annealing for training energy-based generative models
Gilhan Kim, Ju-Yeon Gyhm, Daniel K. Park
Energy-based generative models, such as restricted Boltzmann machines (RBMs), require unbiased Boltzmann samples for effective training. Classical Markov chain Monte Carlo methods,…