InfoQ: Mixed-Precision Quantization via Global Information Flow

arXiv:2508.04753 · cs.LG · Submitted 2025-08-06 · Read on arXiv

cs.LG

Submitted: 2025-08-06

Updated: 2025-08-06

Terminology

• Quantization — 5× in this paper · explained in 12 episodes
• Accuracy — 2× in this paper · explained in 1 episode
• Combinatorial Optimization — 1× in this paper · explained in 2 episodes
• Mutual Information — 1× in this paper · explained in 2 episodes

Sources

• Information Bottleneck Analysis of Deep Neural Networks via Lossy Compression
• Towards Mixed-Precision Quantization of Neural Networks via Constrained Optimization
• PACT: Parameterized Clipping Activation for Quantized Neural Networks
• HAWQ-V2: Hessian Aware trace-Weighted Quantization of Neural Networks
• HAWQ: Hessian AWare Quantization of Neural Networks with Mixed-Precision
• Differentiable Model Compression via Pseudo Quantization Noise
• Learned Step Size Quantization
• Single Path One-Shot Neural Architecture Search with Uniform Sampling
• Deep Residual Learning for Image Recognition
• Information Bottleneck: Exact Analysis of (Quantized) Neural Networks
• AutoQ: Automated Kernel-Wise Neural Network Quantization
• OMPQ: Orthogonal Mixed Precision Quantization
• DINOv2: Learning Robust Visual Features without Supervision
• MobileNetV2: Inverted Residuals and Linear Bottlenecks
• Mixed-Precision Neural Network Quantization via Learned Layer-wise Importance
• HAQ: Hardware-Aware Automated Quantization with Mixed Precision
• Mixed Precision Quantization of ConvNets via Differentiable Neural Architecture Search
• Search What You Want: Barrier Panelty NAS for Mixed Precision Quantization
• LQ-Nets: Learned Quantization for Highly Accurate and Compact Deep Neural Networks
• An Information Theory-inspired Strategy for Automatic Network Pruning

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks