A Model of Double Descent for High-dimensional Binary Linear Classification
원문 초록
We consider a model for logistic regression where only a subset of features of size $p$ is used for training a linear classifier over $n$ training samples. The classifier is obtained by running gradient descent (GD) on logistic loss. For this model, we investigate the dependence of the classification error on the overparameterization ratio $\kappa=p/n$. First, building on known deterministic results on the implicit bias of GD, we uncover a phase-transition phenomenon for the case of Gaussian features: the classification error of GD is the same as that of the maximum-likelihood (ML) solution when $\kappa<\kappa_\star$, and that of the max-margin (SVM) solution when $\kappa>\kappa_\star$. Next, using the convex Gaussian min-max theorem (CGMT), we sharply characterize the performance of both the ML and the SVM solutions. Combining these results, we obtain curves that explicitly characterize the classification error for varying values of $\kappa$. The numerical results validate the theoretical predictions and unveil double-descent phenomena that complement similar recent findings in linear regression settings as well as empirical observations in more complex learning scenarios.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Leveraging AM and FM Rhythm Spectrograms for Dementia Classification and Assessment
An Interpretable Adaptive Multiscale Attention Deep Neural Network for Tabular Data
DocXClassifier: High Performance Explainable Deep Network for Document Image Classification
SONNET: A Self-Guided Ordinal Regression Neural Network for Segmentation and Classification of Nuclei in Large-Scale Multi-Tissue Histology Images
Generative Adversarial Minority Oversampling for Spectral-Spatial Hyperspectral Image Classification
Attention-Based Adaptive Spectral-Spatial Kernel ResNet for Hyperspectral Image Classification
토론
이 논문과 연결된 포럼 글이 아직 없습니다.