paper-with-me

Papers

Squeeze-Release: Iterative Pruning with Exact Structural Minimization

2026-06-12 · Roman Denkin, Ida Akerholm, Prashant Singh, Ida-Maria Sintorn arxiv

Unstructured pruning produces sparse weight tensors, but the standard implementation keeps tensor shapes unchanged so the deployed model is no smaller than before pruning. We present an exact structural rewrite, which we call minimization, that converts a masked network into a smaller dense network with the same forward function up to floating-point rounding. The Squeeze-Release cycle iterates pruning and minimization with an intermediate release step that re-enables the exact-zero positions inside the compacted tensors as small calibrated noise, turning otherwise wasted capacity back into trainable parameters. Successive cycles use that capacity to find structural redundancy a single pass cannot reach. We additionally introduce CompensatedLayerNorm, a function-preserving replacement for LayerNorm that extends minimization to channel reduction across LayerNorm-equipped residual streams. Squeeze-Release compresses the deployable network to 39x smaller than the unpruned model on a fully-connected model network and 14.8x smaller on modern CNN (ConvNeXt-Tiny), at comparable accuracy. In addition we prove that the rewrite can be extended to transformer architectures.

📄 PDF Abstract BibTeX arXiv:2606.14346

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

SqueezerFaceNet: Reducing a Small Face Recognition CNN Even More Via Filter Pruning

2023-07-20 · Fernando Alonso-Fernandez, Kevin Hernandez-Diaz, Jose Maria Buades Rubio, Josef Bigun

The widespread use of mobile devices for various digital services has created a need for reliable and real-time person authentication. In this context, facial recognition technologies have emerged as a dependable method …

Face RecognitionFace VerificationNetwork Pruning

From Local to Global: Revisiting Structured Pruning Paradigms for Large Language Models

2025-10-20 · Ziyan Wang, Enmao Diao, Qi Le, Pu Wang 외 arxiv

Structured pruning is a practical approach to deploying large language models (LLMs) efficiently, as it yields compact, hardware-friendly architectures. However, the dominant local paradigm is task-agnostic: by optimizin…

Solving Marginal MAP Exactly by Probabilistic Circuit Transformations

2021-11-08 · YooJung Choi, Tal Friedman, Guy Van Den Broeck

Probabilistic circuits (PCs) are a class of tractable probabilistic models that allow efficient, often linear-time, inference of queries such as marginals and most probable explanations (MPE). However, marginal MAP, whic…

Decision Making

Scaling Laws for Task-Specific LLM Distillation

2026-06-23 · Lavinia Ghita, Dhruv Desai, Ioana Boier arxiv

Large Language Models (LLMs) achieve strong performance across a growing range of domains, yet their scale poses deployment challenges in applications where latency and cost constraints are critical. This paper derives e…

General Knowledge

Iterative Activation-based Structured Pruning

2022-01-22 · Kaiqi Zhao, Animesh Jain, Ming Zhao

Deploying complex deep learning models on edge devices is challenging because they have substantial compute and memory resource requirements, whereas edge devices' resource budget is limited. To solve this problem, exten…