SGD and Weight Decay Secretly Minimize the Rank of Your Neural Network
We investigate the inherent bias of Stochastic Gradient Descent (SGD) toward learning low-rank weight matrices during the training of deep neural networks. Our results demonstrate that training with mini-batch SGD and weight decay induces a bias toward rank minimization in the weight matrices. Specifically, we show both theoretically and empirically that this bias becomes more pronounced with smaller batch sizes, higher learning rates, or stronger weight decay. Additionally, we predict and empirically confirm that weight decay is essential for this bias to occur. Unlike previous literature, our analysis does not rely on assumptions about the data, convergence, or optimality of the weight matrices, making it applicable to a wide range of neural network architectures of any width or depth. Finally, we empirically explore the connection between this bias and generalization, finding that it has a marginal effect on the test performance.
Code (0)
등록된 구현이 없습니다.
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
How to decay your learning rate
Complex learning rate schedules have become an integral part of deep learning. We find empirically that common fine-tuned schedules decay the learning rate after the weight norm bounces. This leads to the proposal of ABE…
Your Classifier can Secretly Suffice Multi-Source Domain Adaptation
Multi-Source Domain Adaptation (MSDA) deals with the transfer of task knowledge from multiple labeled source domains to an unlabeled target domain, under a domain-shift. Existing methods aim to minimize this domain-shift…
Domain AdaptationMulti-Source Unsupervised Domain AdaptationYour Data Manifold is Secretly a Reward Model: Shell-LCC for Text-to-Video Generation
Recent text-to-video (T2V) diffusion models rely heavily on auxiliary reward signals (e.g., via reward models or DPO) to align generated content with human aesthetics and improve realism. These signals, however, incur su…
Text-to-Video GenerationConvergence Bound and Critical Batch Size of Muon Optimizer
Muon, a recently proposed optimizer that leverages the inherent matrix structure of neural network parameters, has demonstrated strong empirical performance, indicating its potential as a successor to standard optimizers…
Image ClassificationYour Weak LLM is Secretly a Strong Teacher for Alignment
The burgeoning capabilities of large language models (LLMs) have underscored the need for alignment to ensure these models act in accordance with human values and intentions. Existing alignment frameworks present constra…