paper-with-me

Papers

Data-Free/Data-Sparse Softmax Parameter Estimation with Structured Class Geometries

2018-06-03 · Nisar Ahmed

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.

📄 PDF Abstract BibTeX arXiv:1806.00728

Code (0)

등록된 구현이 없습니다.

Tasks

parameter estimation

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Similar Papers 제목 키워드 기반

Statistical Perspective of Top-K Sparse Softmax Gating Mixture of Experts

2023-09-25 · Huy Nguyen, Pedram Akbarian, Fanqi Yan, Nhat Ho

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 estimation

Doubly Sparse: Sparse Mixture of Sparse Experts for Efficient Softmax Inference

2019-01-30 · ICLR 2019 5 · Shun Liao, Ting Chen, Tian Lin, Denny Zhou 외

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+2

Is Temperature Sample Efficient for Softmax Gaussian Mixture of Experts?

2024-01-25 · Huy Nguyen, Pedram Akbarian, Nhat Ho

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 estimation

Long-Context Generalization with Sparse Attention

2025-06-19 · Pavlo Vasylenko, Marcos Treviso, André F. T. Martins

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

2019-08-30 · IJCNLP 2019 11 · Gonçalo M. Correia, Vlad Niculae, André F. T. Martins

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