A Sample Complexity Separation between Non-Convex and Convex Meta-Learning
원문 초록
One popular trend in meta-learning is to learn from many training tasks a common initialization for a gradient-based method that can be used to solve a new task with few samples. The theory of meta-learning is still in its early stages, with several recent learning-theoretic analyses of methods such as Reptile [Nichol et al., 2018] being for convex models. This work shows that convex-case analysis might be insufficient to understand the success of meta-learning, and that even for non-convex models it is important to look inside the optimization black-box, specifically at properties of the optimization trajectory. We construct a simple meta-learning instance that captures the problem of one-dimensional subspace learning. For the convex formulation of linear regression on this instance, we show that the new task sample complexity of any initialization-based meta-learning algorithm is $\Omega(d)$, where $d$ is the input dimension. In contrast, for the non-convex formulation of a two layer linear network on the same instance, we show that both Reptile and multi-task representation learning can have new task sample complexity of $\mathcal{O}(1)$, demonstrating a separation from convex meta-learning. Crucially, analyses of the training dynamics of these methods reveal that they can meta-learn the correct subspace onto which the data should be projected.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Latent Representation Learning of Multi-scale Thermophysics: Application to Dynamics in Shocked Porous Energetic Material
Are encoders able to learn landmarkers for warm-starting of Hyperparameter Optimization?
Semantic Structure Enhanced Contrastive Adversarial Hash Network for Cross-media Representation Learning
An Experimental Study of Quantitative Evaluations on Saliency Methods
On Designing Diffusion Autoencoders for Efficient Generation and Representation Learning
Dual Dimensions Geometric Representation Learning Based Document Dewarping
토론
이 논문과 연결된 포럼 글이 아직 없습니다.