Tao Jiang

Binary Quantized Neural Network Training Is W[1]-Hard Parameterized by Input and Output Dimensions

Ganian et al. (ICLR 2026) proved that quantized neural network training is fixed-parameter tractable when parameterized jointly by architecture treewidth, input dimension $\alpha$, and output dimension $\omega$, and left open whether $\alpha+\omega$ alone yields fixed-parameter tractability. We prove that 2-QNNT is W[1...