NS-RIS, a Newton-Schulz retraction method on the Stiefel manifold, gives hidden quantum Markov models better likelihoods than EM-trained HMMs and prior HQMM learners on synthetic and splice-sequence data.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Newton-Schulz Retraction-Based Inference Enables Hidden Quantum Markov Models to Outperform Classical HMMs
NS-RIS, a Newton-Schulz retraction method on the Stiefel manifold, gives hidden quantum Markov models better likelihoods than EM-trained HMMs and prior HQMM learners on synthetic and splice-sequence data.