paper-with-me

홈 › Papers

Sparsest Models Elude Pruning: An Exposé of Pruning's Current Capabilities

2024-07-04 · Stephen Zhang, Vardan Papyan

Pruning has emerged as a promising approach for compressing large-scale models, yet its effectiveness in recovering the sparsest of models has not yet been explored. We conducted an extensive series of 485,838 experiments, applying a range of state-of-the-art pruning algorithms to a synthetic dataset we created, named the Cubist Spiral. Our findings reveal a significant gap in performance compared to ideal sparse networks, which we identified through a novel combinatorial search algorithm. We attribute this performance gap to current pruning algorithms' poor behaviour under overparameterization, their tendency to induce disconnected paths throughout the network, and their propensity to get stuck at suboptimal solutions, even when given the optimal width and initialization. This gap is concerning, given the simplicity of the network architectures and datasets used in our study. We hope that our research encourages further investigation into new pruning techniques that strive for true network sparsity.

📄 PDF Abstract BibTeX arXiv:2407.04075

Code (1)

stephenqz/sparsest 공식 구현 pytorch

Tasks

Attribute

Methods 이 논문이 사용한 방법론

Pruning 설명 없음

Similar Papers 제목 키워드 기반

SparseStreet: Sparse Gaussian Splatting for Real-Time Street Scene Simulation

2026-06-02 · Qingpo Wuwu, Xiaobao Wei, Peng Chen, Nan Huang 외 arxiv

While 3D Gaussian Splatting has shown promising results in street scene reconstruction, existing methods require massive numbers of Gaussian primitives to capture fine details, leading to prohibitive storage costs and sl…

Sharp Eyes and Memory for VideoLLMs: Information-Aware Visual Token Pruning for Efficient and Reliable VideoLLM Reasoning

2025-11-11 · Jialong Qin, Xin Zou, Di Lu, Yibo Yan 외 arxiv

Current Video Large Language Models (VideoLLMs) suffer from quadratic computational complexity and key-value cache scaling, due to their reliance on processing excessive redundant visual tokens. To address this problem, …

Efficient Adversarial Training With Data Pruning

2022-07-01 · Maximilian Kaufmann, Yiren Zhao, Ilia Shumailov, Robert Mullins 외

Neural networks are susceptible to adversarial examples-small input perturbations that cause models to fail. Adversarial training is one of the solutions that stops adversarial examples; models are exposed to attacks dur…

Max-Affine Spline Insights Into Deep Network Pruning

2021-01-07 · Haoran You, Randall Balestriero, Zhihan Lu, Yutong Kou 외

In this paper, we study the importance of pruning in Deep Networks (DNs) and the yin & yang relationship between (1) pruning highly overparametrized DNs that have been trained from random initialization and (2) training …

Network Pruning

Pruning Cannot Hurt Robustness: Certified Trade-offs in Reinforcement Learning

2025-10-14 · James Pedley, Benjamin Etheridge, Stephen J. Roberts, Francesco Quinzan arxiv

Reinforcement learning (RL) policies deployed in real-world environments must remain reliable under adversarial perturbations. At the same time, modern deep RL agents are heavily over-parameterized, raising costs and fra…

Reinforcement Learning