8 papers
Low-Order Explicit Hessian Imitation Method for Large-Scale Supervised Machine Learning
Yunlang Zhu, Lingjun Guo, Zahra Khatti +4
An algorithm is proposed for solving optimization problems arising in neural network training for supervised learning. The unique feature of the algorithm is the use of an auxiliar…
StableQAT: Stable Quantization-Aware Training at Ultra-Low Bitwidths
Tianyi Chen, Sihan Chen, Xiaoyi Qu +5
Quantization-aware training (QAT) is essential for deploying large models under strict memory and latency constraints, yet achieving stable and robust optimization at ultra-low bit…
PRIME: Policy-Reinforced Iterative Multi-agent Execution for Algorithmic Reasoning in Large Language Models
Jiawei Xu, Zhenyu Yu, Ziqian Bi +3
Large language models have demonstrated remarkable capabilities across diverse reasoning tasks, yet their performance on algorithmic reasoning remains limited. To handle this limit…
A Proximal-Gradient Method for Solving Regularized Optimization Problems with General Constraints
Frank E. Curtis, Xiaoyi Qu, Daniel P. Robinson
We propose, analyze, and test a proximal-gradient method for solving regularized optimization problems with general constraints. The method employs a decomposition strategy to comp…
Multi-Agent Medical Decision Consensus Matrix System: An Intelligent Collaborative Framework for Oncology MDT Consultations
Xudong Han, Xianglun Gao, Xiaoyi Qu +1
Multidisciplinary team (MDT) consultations are the gold standard for cancer care decision-making, yet current practice lacks structured mechanisms for quantifying consensus and ens…
Automatic Joint Structured Pruning and Quantization for Efficient Neural Network Training and Compression
Xiaoyi Qu, David Aponte, Colby Banbury +5
Structured pruning and quantization are fundamental techniques used to reduce the size of deep neural networks (DNNs) and typically are applied independently. Applying these techni…
HESSO: Towards Automatic Efficient and User Friendly Any Neural Network Training and Pruning
Tianyi Chen, Xiaoyi Qu, David Aponte +7
Structured pruning is one of the most popular approaches to effectively compress the heavy deep neural networks (DNNs) into compact sub-networks while retaining performance. The ex…
A Proximal-Gradient Method for Constrained Optimization
Yutong Dai, Xiaoyi Qu, Daniel P. Robinson
We present a new algorithm for solving optimization problems with objective functions that are the sum of a smooth function and a (potentially) nonsmooth regularization function, a…