5 papers · 1 filter
Rethinking Prediction Horizons: Decoupling Model Queries from State Updates in Few-Step MeanFlow
Tinglan Wang, Haixu Liu, Shaobo Chen +4
MeanFlow predicts interval-average velocities, but conventional few-step sampling ties the interval queried from the model to the duration of the state update. We separate these tw…
Q-DEQ: Discrete Solving and Quantization for Deep Equilibrium Models in Time Series Forecasting under Edge Deployment Coding Constraints
Ruotong Yang, Hongdong Zhu, Qi Gao +3
Edge deployment motivates forecasting models with compact parameter storage and low-bit representations. Deep equilibrium models (DEQs) obtain implicit depth by repeatedly applying…
Exact and Asymptotically Complete Robust Verifications of Neural Networks via Ising Solvers
Wenxin Li, Wenchao Liu, Anzhe Jiang +6
We present an Ising-compatible framework for formal neural-network robustness verification under bounded input perturbations. For piecewise activations (both continuous piecewise-l…
Quantum-Boosted High-Fidelity Deep Learning
Feng-ao Wang, Shaobo Chen, Yao Xuan +12
A fundamental limitation of probabilistic deep learning is its predominant reliance on Gaussian priors. This simplistic assumption prevents models from accurately capturing the com…
Towards Provable and Scalable Training of Quantized Neural Networks with Ising Optimization
Wenxin Li, Chuan Wang, Hongdong Zhu +4
Training quantized neural networks remains fundamentally challenging due to non-convex loss landscapes and discrete parameter spaces. We introduce an exact Quadratic Constrained Bi…