paper-with-me

홈 › Papers

The Complexity of Verifying Feedforward Neural Networks in Quantised Settings

2026-05-28 · Eric Alsmann, Martin Lange, Marco Sälzer arxiv

We investigate the computational complexity of neural network verification in quantised settings. We distinguish three classes of Feedforward Neural Networks (FNNs): rational FNNs with exact rational weights, quantised FNNs whose weights come from a finite-width arithmetic, and dynamically quantised FNNs in which rational networks are evaluated with respect to a given finite-width arithmetic. We consider two types of specifications used in the literature. Linear programming (LP) specifications are conjunctions of linear constraints, while bit-vector (BV) specifications allow reasoning at the bit level and can express non-linear constraints. Our results give a complexity landscape of these verification problems. For quantised FNNs with fixed arithmetic precision, we show that verification under both LP and BV specifications remains NP-complete, matching the complexity of the rational case. For dynamically quantised FNNs with BV specifications, we establish upper bounds, complementing a previously known PSPACE-hardness result.

📄 PDF Abstract BibTeX arXiv:2605.29537

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Verifiable and Energy Efficient Medical Image Analysis with Quantised Self-attentive Deep Neural Networks

2022-09-30 · Rakshith Sathish, Swanand Khare, Debdoot Sheet

Convolutional Neural Networks have played a significant role in various medical imaging tasks like classification and segmentation. They provide state-of-the-art performance compared to classical image processing algorit…

ClassificationMedical Image AnalysisSegmentationSemantic Segmentation

Pruning Neural Machine Translation for Speed Using Group Lasso

2021-11-01 · WMT (EMNLP) 2021 11 · Maximiliana Behnke, Kenneth Heafield

Unlike most work on pruning neural networks, we make inference faster. Group lasso regularisation enables pruning entire rows, columns or blocks of parameters that result in a smaller dense network. Because the network i…

DecoderMachine TranslationTranslation

Protocols for Verifying Smooth Strategies in Bandits and Games

2025-07-08 · Miranda Christ, Daniel Reichman, Jonathan Shafer arxiv

We study protocols for verifying approximate optimality of strategies in multi-armed bandits and normal-form games. As the number of actions available to each player is often large, we seek protocols where the number of …

Multi-Armed Bandits

The Computational Complexity of Satisfiability in State Space Models

2025-08-25 · Eric Alsmann, Martin Lange arxiv

We analyse the complexity of the satisfiability problem ssmSAT for State Space Models (SSM), which asks whether an input sequence can lead the model to an accepting configuration. We find that ssmSAT is undecidable in ge…

Global Context with Discrete Diffusion in Vector Quantised Modelling for Image Generation

2021-12-03 · CVPR 2022 1 · Minghui Hu, Yujie Wang, Tat-Jen Cham, Jianfei Yang 외

The integration of Vector Quantised Variational AutoEncoder (VQ-VAE) with autoregressive models as generation part has yielded high-quality results on image generation. However, the autoregressive models will strictly fo…

DenoisingImage GenerationImage InpaintingText Generation