标签:loss based NETWORK parameters GRADIENT measures FLOW gradient norm
论文阅读
一、重要性评判准则:
变量说明:Θ(t)代表t时刻的参数; g(Θ(t))为loss对t时刻参数的梯度;H(Θ(t))为Hessian矩阵;损失为L(Θ(t));I(Θp(t))为重要性。
1.Magnitude-based measures:
2.Loss-preservation based measures
3.Increase in gradient-norm based measures:
二、论文第四节
1.GRADIENT FLOW AND MAGNITUDE-BASED PRUNING
Observation 1: The larger the magnitude of parameters at a particular instant, the smaller the model loss at that instant will be. If these large-magnitude parameters are preserved while pruning (instead of smaller ones), the pruned model’s loss decreases faster
Observation 2: Up to a constant, the magnitude of time-derivative of norm of model parameters (the score for magnitude-based pruning) is equal to the importance measure used for loss-preservation (Equation 3). Further, loss-preservation corresponds to removal of the slowest changing parameters.
Observation 3: Due to their closely related nature, when used with additional heuristics, magnitudebased importance measures preserve loss.
Observation 4: Increasing gradient-norm via pruning removes parameters that maximally increase model loss
Observation 5: Preserving gradient-norm maintains second-order model evolution dynamics and results in better-performing models than increasing gradient-norm.
(未完)
总结
此篇论文根据公式出发,解释了过去在剪枝领域中表现较好的论文中提出的重要性评判准则的本质是什么,即为什么不同的剪枝方法都会得到较好的效果。
标签:loss,based,NETWORK,parameters,GRADIENT,measures,FLOW,gradient,norm 来源: https://blog.csdn.net/qu_learner/article/details/121149689
本站声明: 1. iCode9 技术分享网(下文简称本站)提供的所有内容,仅供技术学习、探讨和分享; 2. 关于本站的所有留言、评论、转载及引用,纯属内容发起人的个人观点,与本站观点和立场无关; 3. 关于本站的所有言论和文字,纯属内容发起人的个人观点,与本站观点和立场无关; 4. 本站文章均是网友提供,不完全保证技术分享内容的完整性、准确性、时效性、风险性和版权归属;如您发现该文章侵犯了您的权益,可联系我们第一时间进行删除; 5. 本站为非盈利性的个人网站,所有内容不会用来进行牟利,也不会利用任何形式的广告来间接获益,纯粹是为了广大技术爱好者提供技术内容和技术思想的分享性交流网站。