A Tensor-Based Compiler and a Runtime for Neuron-Level DNN Certifier Specifications

• URL: http://arxiv.org/abs/2507.20055v1
• Date: Sat, 26 Jul 2025 20:38:29 GMT
• Title: A Tensor-Based Compiler and a Runtime for Neuron-Level DNN Certifier Specifications
• Authors: Avaljot Singh, Yamin Chandini Sarita, Aditya Mishra, Ishaan Goyal, Gagandeep Singh, Charith Mendis,
• Abstract summary: We propose a compiler framework that translates neuron-level specifications of DNN certifiers into tensor-based, layer-level implementations.<n>This is enabled by a novel stack-based intermediate representation (IR) and a shape analysis that infers the implicit tensor operations needed to simulate the neuron-level semantics.<n>Using our compiler and g-BCSR, we make it easy to develop new certifiers and analyze their utility across diverse DNNs.
• Score: 4.681322438383984
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The uninterpretability of DNNs has led to the adoption of abstract interpretation-based certification as a practical means to establish trust in real-world systems that rely on DNNs. However, the current landscape supports only a limited set of certifiers, and developing new ones or modifying existing ones for different applications remains difficult. This is because the mathematical design of certifiers is expressed at the neuron level, while their implementations are optimized and executed at the tensor level. This mismatch creates a semantic gap between design and implementation, making manual bridging both complex and expertise-intensive -- requiring deep knowledge in formal methods, high-performance computing, etc. We propose a compiler framework that automatically translates neuron-level specifications of DNN certifiers into tensor-based, layer-level implementations. This is enabled by two key innovations: a novel stack-based intermediate representation (IR) and a shape analysis that infers the implicit tensor operations needed to simulate the neuron-level semantics. During lifting, the shape analysis creates tensors in the minimal shape required to perform the corresponding operations. The IR also enables domain-specific optimizations as rewrites. At runtime, the resulting tensor computations exhibit sparsity tied to the DNN architecture. This sparsity does not align well with existing formats. To address this, we introduce g-BCSR, a double-compression format that represents tensors as collections of blocks of varying sizes, each possibly internally sparse. Using our compiler and g-BCSR, we make it easy to develop new certifiers and analyze their utility across diverse DNNs. Despite its flexibility, the compiler achieves performance comparable to hand-optimized implementations.

Related papers

• Implicit Language Models are RNNs: Balancing Parallelization and Expressivity [4.332158627306896]
  State-space models (SSMs) and transformers dominate the language modeling landscape.<n>We propose implicit SSMs, which implement a transformation until convergence to a fixed point.<n>Our approach demonstrates superior state-tracking capabilities on regular languages, surpassing transformers and SSMs.
  arXiv  Detail & Related papers  (2025-02-10T19:59:31Z)
• Asymmetric Certified Robustness via Feature-Convex Neural Networks [11.605936648692543]
  We show that an ICNN can be generalizationd to an adversarial network. Experiments show that the network is far more efficient than any competitive baseline.
  arXiv  Detail & Related papers  (2023-02-03T19:17:28Z)
• Convolutional Neural Operators for robust and accurate learning of PDEs [11.562748612983956]
  We present novel adaptations for convolutional neural networks to process functions as inputs and outputs. The resulting architecture is termed as convolutional neural operators (CNOs) We prove a universality theorem to show that CNOs can approximate operators arising in PDEs to desired accuracy.
  arXiv  Detail & Related papers  (2023-02-02T15:54:45Z)
• Intelligence Processing Units Accelerate Neuromorphic Learning [52.952192990802345]
  Spiking neural networks (SNNs) have achieved orders of magnitude improvement in terms of energy consumption and latency. We present an IPU-optimized release of our custom SNN Python package, snnTorch.
  arXiv  Detail & Related papers  (2022-11-19T15:44:08Z)
• Recurrent Bilinear Optimization for Binary Neural Networks [58.972212365275595]
  BNNs neglect the intrinsic bilinear relationship of real-valued weights and scale factors. Our work is the first attempt to optimize BNNs from the bilinear perspective. We obtain robust RBONNs, which show impressive performance over state-of-the-art BNNs on various models and datasets.
  arXiv  Detail & Related papers  (2022-09-04T06:45:33Z)
• Complexity-Driven CNN Compression for Resource-constrained Edge AI [1.6114012813668934]
  We propose a novel and computationally efficient pruning pipeline by exploiting the inherent layer-level complexities of CNNs. We define three modes of pruning, namely parameter-aware (PA), FLOPs-aware (FA), and memory-aware (MA), to introduce versatile compression of CNNs.
  arXiv  Detail & Related papers  (2022-08-26T16:01:23Z)
• Self-Ensembling GAN for Cross-Domain Semantic Segmentation [107.27377745720243]
  This paper proposes a self-ensembling generative adversarial network (SE-GAN) exploiting cross-domain data for semantic segmentation. In SE-GAN, a teacher network and a student network constitute a self-ensembling model for generating semantic segmentation maps, which together with a discriminator, forms a GAN. Despite its simplicity, we find SE-GAN can significantly boost the performance of adversarial training and enhance the stability of the model.
  arXiv  Detail & Related papers  (2021-12-15T09:50:25Z)
• Sub-bit Neural Networks: Learning to Compress and Accelerate Binary Neural Networks [72.81092567651395]
  Sub-bit Neural Networks (SNNs) are a new type of binary quantization design tailored to compress and accelerate BNNs. SNNs are trained with a kernel-aware optimization framework, which exploits binary quantization in the fine-grained convolutional kernel space. Experiments on visual recognition benchmarks and the hardware deployment on FPGA validate the great potentials of SNNs.
  arXiv  Detail & Related papers  (2021-10-18T11:30:29Z)
• Designing Interpretable Approximations to Deep Reinforcement Learning [14.007731268271902]
  Deep neural networks (DNNs) set the bar for algorithm performance. It may not be feasible to actually use such high-performing DNNs in practice. This work seeks to identify reduced models that not only preserve a desired performance level, but also, for example, succinctly explain the latent knowledge represented by a DNN.
  arXiv  Detail & Related papers  (2020-10-28T06:33:09Z)
• BLK-REW: A Unified Block-based DNN Pruning Framework using Reweighted Regularization Method [69.49386965992464]
  We propose a new block-based pruning framework that comprises a general and flexible structured pruning dimension as well as a powerful and efficient reweighted regularization method. Our framework is universal, which can be applied to both CNNs and RNNs, implying complete support for the two major kinds ofintensive computation layers. It is the first time that the weight pruning framework achieves universal coverage for both CNNs and RNNs with real-time mobile acceleration and no accuracy compromise.
  arXiv  Detail & Related papers  (2020-01-23T03:30:56Z)
• PatDNN: Achieving Real-Time DNN Execution on Mobile Devices with Pattern-based Weight Pruning [57.20262984116752]
  We introduce a new dimension, fine-grained pruning patterns inside the coarse-grained structures, revealing a previously unknown point in design space. With the higher accuracy enabled by fine-grained pruning patterns, the unique insight is to use the compiler to re-gain and guarantee high hardware efficiency.
  arXiv  Detail & Related papers  (2020-01-01T04:52:07Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.