paper-with-me

Papers

BINGO: A Novel Pruning Mechanism to Reduce the Size of Neural Networks

2025-05-15 · Aditya Panangat

Over the past decade, the use of machine learning has increased exponentially. Models are far more complex than ever before, growing to gargantuan sizes and housing millions of weights. Unfortunately, the fact that large models have become the state of the art means that it often costs millions of dollars to train and operate them. These expenses not only hurt companies but also bar non-wealthy individuals from contributing to new developments and force consumers to pay greater prices for AI. Current methods used to prune models, such as iterative magnitude pruning, have shown great accuracy but require an iterative training sequence that is incredibly computationally and environmentally taxing. To solve this problem, BINGO is introduced. BINGO, during the training pass, studies specific subsets of a neural network one at a time to gauge how significant of a role each weight plays in contributing to a network's accuracy. By the time training is done, BINGO generates a significance score for each weight, allowing for insignificant weights to be pruned in one shot. BINGO provides an accuracy-preserving pruning technique that is less computationally intensive than current methods, allowing for a world where AI growth does not have to mean model growth, as well.

📄 PDF Abstract BibTeX arXiv:2505.09864

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Pruning 설명 없음

Similar Papers 제목 키워드 기반

Bingo: Boosting Efficient Reasoning of LLMs via Dynamic and Significance-based Reinforcement Learning

2025-06-09 · Hanbing Liu, Lang Cao, Yuanyi Ren, Mengyu Zhou 외

Large language models have demonstrated impressive reasoning capabilities, yet they often suffer from inefficiencies due to unnecessarily verbose or redundant outputs. While many works have explored reinforcement learnin…

Reinforcement Learning (RL)

BInGo: Bayesian Intrinsic Groupwise Registration via Explicit Hierarchical Disentanglement

2022-06-06 · Xin Wang, Xinzhe Luo, Xiahai Zhuang

Multimodal groupwise registration aligns internal structures in a group of medical images. Current approaches to this problem involve developing similarity measures over the joint intensity profile of all images, which m…

Bayesian InferenceComputational EfficiencyDisentanglement

BingoGuard: LLM Content Moderation Tools with Risk Levels

2025-03-09 · Fan Yin, Philippe Laban, Xiangyu Peng, Yilun Zhou 외

Malicious content generated by large language models (LLMs) can pose varying degrees of harm. Although existing LLM-based moderators can detect harmful content, they struggle to assess risk levels and may miss lower-risk…

BINGO: A Dependency Grammar Framework to Understand Hardware Specifications Written in English

2021-12-01 · DepLing (SyntaxFest) 2021 12 · Rahul Krishnamurthy, Michael S. Hsiao

Accelerating ViT Inference on FPGA through Static and Dynamic Pruning

2024-03-21 · Dhruv Parikh, Shouyi Li, Bingyi Zhang, Rajgopal Kannan 외

Vision Transformers (ViTs) have achieved state-of-the-art accuracy on various computer vision tasks. However, their high computational complexity prevents them from being applied to many real-world applications. Weight a…