8 papers
From Trainability Diagnostics to Optimization Claims: Boundaries and Controls in Variational Quantum Optimization
Pilsung Kang
Barren plateau diagnostics characterize whether gradient signal remains available for training, but surviving signal need not translate into successful optimization. We study this…
Decomposing Gradient Suppression in Barren Plateaus: Activity, Sign Organization, and Coupling
Pilsung Kang
Barren plateaus (BPs) are conventionally characterized by suppressed gradient variance, but this aggregate description does not reveal how the loss of gradient signal is composed a…
naPINN: Noise-Adaptive Physics-Informed Neural Networks for Recovering Physics from Corrupted Measurement
Hankyeol Kim, Pilsung Kang
Physics-Informed Neural Networks (PINNs) are effective methods for solving inverse problems and discovering governing equations from observational data. However, their performance…
Implementing Pearl's -Calculus on Quantum Circuits: A Simpson-Type Case Study on NISQ Hardware
Pilsung Kang
Distinguishing correlation from causation is a central challenge in machine intelligence, and Pearl's -calculus provides a rigorous symbolic framework for reasoning a…
Quantum Entanglement as Super-Confounding: From Bell's Theorem to Robust Machine Learning
Pilsung Kang
Bell's theorem reveals a profound conflict between quantum mechanics and local realism, a conflict we reinterpret through the modern lens of causal inference. We propose and comput…
Emergent Bifurcations in Quantum Circuit Stability from Hidden Parameter Statistics
Pilsung Kang
The compression of quantum circuits is a foundational challenge for near-term quantum computing, yet the principles governing circuit stability remain poorly understood. We investi…
QFFN-BERT: An Empirical Study of Depth, Performance, and Data Efficiency in Hybrid Quantum-Classical Transformers
Pilsung Kang
Parameterized quantum circuits (PQCs) have recently emerged as promising components for enhancing the expressibility of neural architectures. In this work, we introduce QFFN-BERT,…
COUNTDOWN: Contextually Sparse Activation Filtering Out Unnecessary Weights in Down Projection
Jaewon Cheon, Pilsung Kang
The growing size of large language models has created significant computational inefficiencies. To address this challenge, sparse activation methods selectively deactivates non-ess…