2 papers
cs.LG2026
Quantization-Aware Pre-Training with Constrained Empirical Weight Distribution
Ningfeng Yang, Tor M. Aamodt
Quantization-Aware Pre-Training (QAPT) can increase the inference efficiency of DNNs, but a problematic behaviour known as rounding boundary weight oscillation can introduce detrim…
cs.LG2025
Improving the Straight-Through Estimator with Zeroth-Order Information
Ningfeng Yang, Tor M. Aamodt
We study the problem of training neural networks with quantized parameters. Learning low-precision quantized parameters by enabling computation of gradients via the Straight-Throug…