# Rethinking Data-Free Quantization as a Zero-Sum Game

arXiv: https://arxiv.org/abs/2302.09572 · HTML: https://mlsanity.com/paper/2302.09572/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 29 references that are in the map.
- First posted on arXiv 19 Feb 2023.

## Builds on (most cited first, 21 of 21)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding](https://mlsanity.com/paper/1510.00149/) (2015)
- [Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference](https://mlsanity.com/paper/1712.05877/) (2017)
- [Conditional Image Synthesis With Auxiliary Classifier GANs](https://mlsanity.com/paper/1610.09585/) (2016)
- [ZeroQ: A Novel Zero Shot Quantization Framework](https://mlsanity.com/paper/2001.00281/) (2020)
- [Geometric GAN](https://mlsanity.com/paper/1705.02894/) (2017)
- [Fixed Point Quantization of Deep Convolutional Networks](https://mlsanity.com/paper/1511.06393/) (2015)
- [Generative Low-bitwidth Data Free Quantization](https://mlsanity.com/paper/2003.03603/) (2020)
- [Diversifying Sample Generation for Accurate Data-Free Quantization](https://mlsanity.com/paper/2103.01049/) (2021)
- [Survey on Deep Multi-modal Data Analytics: Collaboration, Rivalry and Fusion](https://mlsanity.com/paper/2006.08159/) (2020)
- [Zero-shot Adversarial Quantization](https://mlsanity.com/paper/2103.15263/) (2021)
- [IntraQ: Learning Synthetic Images with Intra-Class Heterogeneity for Zero-Shot Network Quantization](https://mlsanity.com/paper/2111.09136/) (2021)
- [Qimera: Data-free Quantization with Synthetic Boundary Supporting Samples](https://mlsanity.com/paper/2111.02625/) (2021)
- [Switchable Online Knowledge Distillation](https://mlsanity.com/paper/2209.04996/) (2022)
- [It's All In the Teacher: Zero-Shot Quantization Brought Closer to the Teacher](https://mlsanity.com/paper/2203.17008/) (2022)
- [AutoReCon: Neural Architecture Search-based Reconstruction for Data-free Compression](https://mlsanity.com/paper/2105.12151/) (2021)
- [Diversifying Inference Path Selection: Moving-Mobile-Network for Landmark Recognition](https://mlsanity.com/paper/1912.00418/) (2019)
- [Policy Learning for Robust Markov Decision Process with a Mismatched Generative Model](https://mlsanity.com/paper/2203.06587/) (2022)

## Built on by (most cited first, 13 of 13)

- [M3Net: Multi-view Encoding, Matching, and Fusion for Few-shot Fine-grained Action Recognition](https://mlsanity.com/paper/2308.03063/) (2023)
- [Adaptive Data-Free Quantization](https://mlsanity.com/paper/2303.06869/) (2023)
- [Low-bit Model Quantization for Deep Neural Networks: A Survey](https://mlsanity.com/paper/2505.05530/) (2025)
- [Zero-shot Quantization: A Comprehensive Survey](https://mlsanity.com/paper/2505.09188/) (2025)
- [Manifold-based Incomplete Multi-view Clustering via Bi-Consistency Guidance](https://mlsanity.com/paper/2405.10987/) (2024)
- [Sharpness-Aware Data Generation for Zero-shot Quantization](https://mlsanity.com/paper/2510.07018/) (2025)
- [Robustness-Guided Image Synthesis for Data-Free Quantization](https://mlsanity.com/paper/2310.03661/) (2023)
- [SynQ: Accurate Zero-shot Quantization by Synthesis-aware Fine-tuning](https://mlsanity.com/paper/2603.18423/) (2026)
- [Selective Coupling of Decoupled Informative Regions: Masked Attention Alignment for Data-Free Quantization of Vision Transformers](https://mlsanity.com/paper/2606.04373/) (2026)
- [A method of using RSVD in residual calculation of LowBit GEMM](https://mlsanity.com/paper/2409.18772/) (2024)
- [AI-T2I: Aggregating-and-Isolating Cross-Attention to Diffusion Models for Text-to-Image Synthesis](https://mlsanity.com/paper/2605.25763/) (2026)
- [Toward Multi-Domain and Long-Tailed Quantization via Feature Alignment and Scaling](https://mlsanity.com/paper/2606.04920/) (2026)
- [STEDiff: Strengthening Text Embedding for Text-to-Image Alignment in Diffusion Model](https://mlsanity.com/paper/2606.10653/) (2026)

## Abstract (arXiv)

Data-free quantization (DFQ) recovers the performance of quantized network (Q) without accessing the real data, but generates the fake sample via a generator (G) by learning from full-precision network (P) instead. However, such sample generation process is totally independent of Q, specialized as failing to consider the adaptability of the generated samples, i.e., beneficial or adversarial, over the learning process of Q, resulting into non-ignorable performance loss. Building on this, several crucial questions -- how to measure and exploit the sample adaptability to Q under varied bit-width scenarios? how to generate the samples with desirable adaptability to benefit the quantized network? -- impel us to revisit DFQ. In this paper, we answer the above questions from a game-theory perspective to specialize DFQ as a zero-sum game between two players -- a generator and a quantized network, and further propose an Adaptability-aware Sample Generation (AdaSG) method. Technically, AdaSG reformulates DFQ as a dynamic maximization-vs-minimization game process anchored on the sample adaptability. The maximization process aims to generate the sample with desirable adaptability, such sample adaptability is further reduced by the minimization process after calibrating Q for performance recovery. The Balance Gap is defined to guide the stationarity of the game process to maximally benefit Q. The theoretical analysis and empirical studies verify the superiority of AdaSG over the state-of-the-arts. Our code is available at https://github.com/hfutqian/AdaSG.