Jack Xin

Convergence of a Relaxed Variable Splitting Coarse Gradient Descent Method for Learning Sparse Weight Binarized Activation Neural Networks

2019 · arXiv (Cornell University)

Sparsification of neural networks is one of the effective complexity reduction methods to improve efficiency and generalizability. Binarized activation offers an additional computational saving for inference. Due to vanishing gradient issue in training networks with …

RARTS: An Efficient First-Order Relaxed Architecture Search Method

2022 · IEEE Access

Differentiable architecture search (DARTS) is an effective method for data-driven neural network design based on solving a bilevel optimization problem. Despite its success in many architecture search tasks, there are still some concerns about the …

Recurrence of Optimum for Training Weight and Activation Quantized Networks

2020 · arXiv (Cornell University)

Deep neural networks (DNNs) are quantized for efficient inference on resource-constrained platforms. However, training deep learning models with low-precision weights and activations involves a demanding optimization task, which calls for minimizing a stage-wise loss function …

COMQ: A Backpropagation-Free Algorithm for Post-Training Quantization

2025 · IEEE Access

Post-training quantization (PTQ) has emerged as a practical approach to compress large neural networks, making them highly efficient for deployment. However, effectively reducing these models to their low-bit counterparts without compromising the original accuracy remains …