Learning Invariances with Generalised Input-Convex Neural Networks
원문 초록
Considering smooth mappings from input vectors to continuous targets, our goal is to characterise subspaces of the input domain, which are invariant under such mappings. Thus, we want to characterise manifolds implicitly defined by level sets. Specifically, this characterisation should be of a global parametric form, which is especially useful for different informed data exploration tasks, such as building grid-based approximations, sampling points along the level curves, or finding trajectories on the manifold. However, global parameterisations can only exist if the level sets are connected. For this purpose, we introduce a novel and flexible class of neural networks that generalise input-convex networks. These networks represent functions that are guaranteed to have connected level sets forming smooth manifolds on the input space. We further show that global parameterisations of these level sets can be always found efficiently. Lastly, we demonstrate that our novel technique for characterising invariances is a powerful generative data exploration tool in real-world applications, such as computational chemistry.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Unlocking Chemical Insights: Superior Molecular Representations from Intermediate Encoder Layers
Efficient and Scalable Density Functional Theory Hamiltonian Prediction through Adaptive Sparsity
Towards Fast, Specialized Machine Learning Force Fields: Distilling Foundation Models via Energy Hessians
Embrace rejection: Kernel matrix approximation by accelerated randomly pivoted Cholesky
Mitigating Exposure Bias in Score-Based Generation of Molecular Conformations
Instruction-Based Molecular Graph Generation with Unified Text-Graph Diffusion Model
토론
이 논문과 연결된 포럼 글이 아직 없습니다.