mlsanityData to 14 Oct 2026

Linear-Time Non-Local Codec Placement for Machine Learning Model Compression

arXiv 2610.14703 ↗First posted 10 Oct 2026cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

On-device inference imposes constraints on model storage and operand traffic and thus benefits from compressed operand representations, which mandate the use of encoding and decoding operators. However, na"ive placement of codec operators can cancel the operand traffic gains sought from compression. In this work, I present an algorithm to place codec operators into a source computational graph to make it compatible with target hardware. The edges of the graph are colored so that each induced subgraph is weakly connected and has a maximal node that both postdominates all subgraph inputs and dominates all subgraph outputs; this unique node - dubbed the textitabsolute dominator - is the natural location to observe the traffic flowing through the subgraph and learn parametric codec operators. The algorithm's time complexity is linear in the source graph's size. With respect to na"ive local codec placement, the algorithm reduces modeled operand traffic by 24%-44% across four models, including 24% on SigLIP and 34% on SmolLM2.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 13 of its 19 references that are in the map. First posted on arXiv 10 Oct 2026.

Builds on

13 of 19 references.

References · 13

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  2. 2023Sigmoid Loss for Language Image Pre-Trainingcited by 3,109
  3. 2013Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computationcited by 2,079
  4. 2022SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Modelscited by 1,386
  5. 2018ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Designcited by 1,136
  6. 2024QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMscited by 634
  7. 2019Learned Step Size Quantizationcited by 628
  8. 2021A White Paper on Neural Network Quantizationcited by 472
  9. 2017Incremental Network Quantization: Towards Lossless CNNs with Low-Precision Weightscited by 217
  10. 2023Microscaling Data Formats for Deep Learningcited by 152
  11. 2025TurboQuant: Online Vector Quantization with Near-optimal Distortion Ratecited by 125
  12. 2025TorchAO: PyTorch-Native Training-to-Serving Model Optimizationcited by 26
1 more
  1. 2026ExecuTorch -- A Unified PyTorch Solution to Run AI Models On-Devicecited by 5

Built on by

Not cited yet.