On Generalization of Decentralized Learning with Separable Data
원문 초록
Decentralized learning offers privacy and communication efficiency when data are naturally distributed among agents communicating over an underlying graph. Motivated by overparameterized learning settings, in which models are trained to zero training loss, we study algorithmic and generalization properties of decentralized learning with gradient descent on separable data. Specifically, for decentralized gradient descent (DGD) and a variety of loss functions that asymptote to zero at infinity (including exponential and logistic losses), we derive novel finite-time generalization bounds. This complements a long line of recent work that studies the generalization performance and the implicit bias of gradient descent over separable data, but has thus far been limited to centralized learning scenarios. Notably, our generalization bounds approximately match in order their centralized counterparts. Critical behind this, and of independent interest, is establishing novel bounds on the training loss and the rate-of-consensus of DGD for a class of self-bounded losses. Finally, on the algorithmic front, we design improved gradient-based routines for decentralized learning with separable data and empirically demonstrate orders-of-magnitude of speed-up in terms of both training and generalization performance.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Learning Non-Vacuous Generalization Bounds from Optimization
Learning Where to Learn: Training Distribution Selection for Provable OOD Performance
Operator Learning for Schrödinger Equation: Unitarity, Error Bounds, and Time Generalization
Graph Representational Learning: When Does More Expressivity Hurt Generalization?
Model Steering: Learning with a Reference Model Improves Generalization Bounds and Scaling Laws
Achieving Distributive Justice in Federated Learning via Uncertainty Quantification
토론
이 논문과 연결된 포럼 글이 아직 없습니다.