CDFlow: Building Invertible Layers with Circulant and Diagonal Matrices

arXiv:2510.25323 · cs.LG · Submitted 2025-10-29 · Read on arXiv

cs.LG

Submitted: 2025-10-29

Updated: 2026-09-08

Comments: Accepted at NeurIPS 2025. 10 pages, 12 figures, 2 tables

DOI: 10.52202/085713-0124

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Normalizing Flow — 14× in this paper · explained in 3 episodes
• Flow Matching — 6× in this paper · explained in 8 episodes
• Generative Model — 6× in this paper · explained in 2 episodes
• Normalizing Flows — 6× in this paper · explained in 4 episodes
• Fast Fourier Transform — 5× in this paper
• Generative Models — 5× in this paper · explained in 2 episodes
• Generative Modeling — 4× in this paper · explained in 3 episodes
• Fine-Tuning — 3× in this paper · explained in 5 episodes
• Flow Matching Model — 3× in this paper · explained in 2 episodes
• Parameter-Efficient Fine-Tuning — 2× in this paper · explained in 2 episodes
• Ablation — 1× in this paper · explained in 1 episode
• Ablation study — 1× in this paper · explained in 1 episode
• Abstraction — 1× in this paper · explained in 1 episode
• Core — 1× in this paper · explained in 2 episodes
• Covariate Shift — 1× in this paper · explained in 2 episodes
• Diagonal-Circulant Decomposition — 1× in this paper
• Quantization — 1× in this paper · explained in 12 episodes
• Redundancy — 1× in this paper · explained in 2 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Transfer Learning — 1× in this paper · explained in 10 episodes
• World Model — 1× in this paper · explained in 7 episodes

Sources

• Understanding and Training Deep Diagonal Circulant Neural Networks
• Parameter-Efficient Fine-Tuning with Circulant and Diagonal Vectors
• NICE: Non-linear Independent Components Estimation
• Density estimation using Real NVP
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Flow Matching for Generative Modeling
• ACDC: A Structured Efficient Linear Layer

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: Local-Consistency Optimisation for Bayesian Neural Networks
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks