Data-Free/Data-Sparse Softmax Parameter Estimation with Structured Class Geometries
This note considers softmax parameter estimation when little/no labeled training data is available, but a priori information about the relative geometry of class label log-odds boundaries is available. It is shown that `data-free' softmax model synthesis corresponds to solving a linear system of parameter equations, wherein desired dominant class log-odds boundaries are encoded via convex polytopes that decompose the input feature space. When solvable, the linear equations yield closed-form softmax parameter solution families using class boundary polytope specifications only. This allows softmax parameter learning to be implemented without expensive brute force data sampling and numerical optimization. The linear equations can also be adapted to constrained maximum likelihood estimation in data-sparse settings. Since solutions may also fail to exist for the linear parameter equations derived from certain polytope specifications, it is thus also shown that there exist probabilistic classification problems over m convexly separable classes for which the log-odds boundaries cannot be learned using an m-class softmax model.
Code (0)
등록된 구현이 없습니다.
Tasks
parameter estimationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Statistical Perspective of Top-K Sparse Softmax Gating Mixture of Experts
Top-K sparse softmax gating mixture of experts has been widely used for scaling up massive deep-learning architectures without increasing the computational cost. Despite its popularity in real-world applications, the the…
Density EstimationMixture-of-Expertsparameter estimationDoubly Sparse: Sparse Mixture of Sparse Experts for Efficient Softmax Inference
Computations for the softmax function are significantly expensive when the number of output classes is large. In this paper, we present a novel softmax inference speedup method, Doubly Sparse Softmax (DS-Softmax), that l…
image-classificationImage ClassificationLanguage ModelingLanguage Modelling+2Is Temperature Sample Efficient for Softmax Gaussian Mixture of Experts?
Dense-to-sparse gating mixture of experts (MoE) has recently become an effective alternative to a well-known sparse MoE. Rather than fixing the number of activated experts as in the latter model, which could limit the in…
Mixture-of-Expertsparameter estimationLong-Context Generalization with Sparse Attention
Transformer-based architectures traditionally employ softmax to compute attention weights, which produces dense distributions over all tokens in a sequence. While effective in many settings, this density has been shown t…
Adaptively Sparse Transformers
Attention mechanisms have become ubiquitous in NLP. Recent architectures, notably the Transformer, learn powerful context-aware word representations through layered, multi-headed attention. The multiple heads learn diver…
DiversityMachine TranslationTranslation