Stable Self-Modulating Quantum Fast-Weight Programmers with Bounded Memory Gates
2026-07-02 • Artificial Intelligence
Artificial IntelligenceEmerging TechnologiesMachine LearningNeural and Evolutionary Computing
AI summaryⓘ
The authors study a quantum method called Quantum Fast-Weight Programmers (QFWPs), which helps model sequences by storing information in quantum circuit settings instead of traditional memory states. They improve this method by adding gates that control how old information influences updates, but found the original method could become unstable for long sequences. To fix this, they propose a new way to limit how much old information affects the system, preventing instability while still keeping benefits. Their experiments show that this new bounded approach improves performance and stability on both quantum physics predictions and real-world telecom data.
Quantum Fast-Weight Programmersvariational circuitssequence modelingself-modulating gatesrecurrent memorytanh gatelong-sequence stabilityquantum dynamics forecastingtelecommunication prediction
Authors
Kuo-Chung Peng, Jiun-Cheng Jiang, Chun-Hua Lin, Yifeng Peng, Junghoon Justin Park, Huan-Hsin Tseng, Hsin-Yi Lin, Kuan-Cheng Chen, Chen-Yu Liu, Shinjae Yoo, Samuel Yen-Chi Chen
Abstract
Quantum Fast-Weight Programmers (QFWPs) store temporal information in dynamically programmed variational-circuit parameters rather than in nonlinear recurrent hidden states, offering a practical route to quantum sequence modeling. Self-Modulating QFWP improves this framework by using input-dependent gates for both new fast-weight updates and the accumulated fast-weight state, but its unbounded old-state multiplier can diverge in long-sequence regimes. We propose a bounded old-state modulation rule that applies a sign-preserving tanh gate only to the recurrent memory branch while leaving the additive update and new-update modulation unchanged. We evaluate standard QFWP, full Self-Modulating QFWP, Only-New, and Only-Old variants on two CUDA-Q quantum-dynamics forecasting tasks and on Milan SMS telecommunication activity prediction. The quantum-dynamics results show that old-state modulation is the most consistent source of improvement over Standard QFWP, and that bounding the old-state gate removes long-sequence divergence while improving aggregate robustness. On Milan SMS forecasting, the original unbounded Self-Modulating QFWP converges across the tested grid and shows its clearest gains at longer input windows, with behavior close to the Only-Old ablation. These findings identify accumulated-memory modulation as the key mechanism of Self-Modulating QFWP and bounded old-state gating as a targeted stabilization strategy.