Information Theoretic Meta Learning with Gaussian Processes
원문 초록
We formulate meta learning using information theoretic concepts; namely, mutual information and the information bottleneck. The idea is to learn a stochastic representation or encoding of the task description, given by a training set, that is highly informative about predicting the validation set. By making use of variational approximations to the mutual information, we derive a general and tractable framework for meta learning. This framework unifies existing gradient-based algorithms and also allows us to derive new algorithms. In particular, we develop a memory-based algorithm that uses Gaussian processes to obtain non-parametric encoding representations. We demonstrate our method on a few-shot regression problem and on four few-shot classification problems, obtaining competitive accuracy when compared to existing baselines.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Sparse Gaussian Neural Processes
Statistical Machine Learning for Astronomy -- A Textbook
LLINBO: Trustworthy LLM-in-the-Loop Bayesian Optimization
Geo-ORBIT: A Federated Digital Twin Framework for Scene-Adaptive Lane Geometry Detection
MathOptAI.jl: Embed trained machine learning predictors into JuMP models
DIP: Unsupervised Dense In-Context Post-training of Visual Representations
토론
이 논문과 연결된 포럼 글이 아직 없습니다.