arXiv AI September 2, 2026 By Wenxin Li, Chuan Wang, Hongdong Zhu, Qi Gao, Yin Ma, Hai Wei, Kai Wen

Towards Provable and Scalable Training of Quantized Neural Networks with Ising Optimization

The paper presents a Quadratic Constrained Binary Optimization (QCBO) framework that provides provable guarantees for training quantized neural networks. It characterizes the topology of zero‑loss level sets, compiles finite‑depth architectures into bounded QCBOs, and introduces a sample‑wise Decomposed Lower‑Bound Optimization (DLBO) to scale Ising‑based optimization. Experiments on a coherent Ising machine show high accuracy on binary Fashion‑MNIST at 1.1‑bit precision and validate the approach on multi‑class datasets.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

efficiency

arXiv Machine Learning

Jul 1

Beyond the Expressivity-Trainability Paradox: A Dynamical Lie Algebra Perspective on Navigating Barren Plateaus in Quantum Machine Learning

arXiv:2606. 31536v1 Announce Type: new Abstract: As Quantum Machine Learning (QML) transitions toward practical implementation, the field faces a critical architectural bottleneck that challenges the fundamental assumptions of classical statistical learning theory.

By Kung-Ming Lan

rag safety

arXiv Machine Learning

Jun 4

AlphaQ: Calibration-Free Bit Allocation for Mixture-of-Experts Quantization

arXiv:2606. 04980v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) architectures scale model capacity through sparse expert activation, but their deployment remains memory-bound because all expert weights must reside in memory.

By Wanqi Yang, Yuexiao Ma, Alexander Conzelmann, Xiawu Zheng, Michael W. Mahoney, T. Konstantin Rusch, Shiwei Liu

llms efficiency

arXiv Machine Learning

Jun 16

Quantization Robustness of Monotone Operator Equilibrium Networks

arXiv:2603. 10562v2 Announce Type: replace-cross Abstract: Monotone operator equilibrium networks are implicit-layer models whose output is the unique equilibrium of a monotone operator, guaranteeing existence, uniqueness, and convergence.

By James Li, Philip H. W. Leong, Thomas Chaffey

efficiency

Hugging Face Trending Papers

Jun 25

CAT-Q: Cost-efficient and Accurate Ternary Quantization for LLMs

In this paper, we present CAT-Q, Cost-efficient and Accurate Ternary Quantization, for compressing and accelerating LLMs. Unlike existing state-of-the-art ternary quantization methods that rely on data-intensive and costly quantization-aware training to mitigate severe performance degradation, CAT-Q is a simple yet effective post-training quantization scheme that is readily applicable to LLMs with diverse architectures and model sizes.

llms efficiency benchmarks

Hugging Face Trending Papers

Aug 14

QUASAR: Lowering the Loss Floor of Quantization-Aware Training with Loss-Aware Reconstruction

As large language model inference shifts toward lower precision, post-training quantization (PTQ) becomes increasingly brittle, making quantization-aware training (QAT) essential for preserving model...

llms efficiency

arXiv AI

Jun 26

CAT-Q: Cost-efficient and Accurate Ternary Quantization for LLMs

arXiv:2606. 26650v1 Announce Type: cross Abstract: In this paper, we present CAT-Q, Cost-efficient and Accurate Ternary Quantization, for compressing and accelerating LLMs.

By Shigeng Wang, Chao Li, Yangyuxuan Kang, Jiawei Fan, Anbang Yao

llms efficiency benchmarks

One email a morning, machine-written

Related stories

Beyond the Expressivity-Trainability Paradox: A Dynamical Lie Algebra Perspective on Navigating Barren Plateaus in Quantum Machine Learning

AlphaQ: Calibration-Free Bit Allocation for Mixture-of-Experts Quantization

Quantization Robustness of Monotone Operator Equilibrium Networks

CAT-Q: Cost-efficient and Accurate Ternary Quantization for LLMs

QUASAR: Lowering the Loss Floor of Quantization-Aware Training with Loss-Aware Reconstruction

CAT-Q: Cost-efficient and Accurate Ternary Quantization for LLMs