Distribution of Classification Margins: Are All Data Equal?
원문 초록
Recent theoretical results show that gradient descent on deep neural networks under exponential loss functions locally maximizes classification margin, which is equivalent to minimizing the norm of the weight matrices under margin constraints. This property of the solution however does not fully characterize the generalization performance. We motivate theoretically and show empirically that the area under the curve of the margin distribution on the training set is in fact a good measure of generalization. We then show that, after data separation is achieved, it is possible to dynamically reduce the training set by more than 99% without significant loss of performance. Interestingly, the resulting subset of "high capacity" features is not consistent across different training runs, which is consistent with the theoretical claim that all training points should converge to the same asymptotic margin under SGD and in the presence of both batch normalization and weight decay.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Attention to Patterns is all you need for Insider threat detection
Efficient Calisthenics Skills Classification through Foreground Instance Selection and Depth Estimation
AI-Enhanced Pediatric Pneumonia Detection: A CNN-Based Approach Using Data Augmentation and Generative Adversarial Networks (GANs)
Is Diversity All You Need for Scalable Robotic Manipulation?
Hybrid-View Attention for csPCa Classification in TRUS
EAMamba: Efficient All-Around Vision State Space Model for Image Restoration
토론
이 논문과 연결된 포럼 글이 아직 없습니다.