English
Related papers

Related papers: On Controllable Sparse Alternatives to Softmax

200 papers

We propose a linear time and constant space algorithm for computing Euclidean projections onto sets on which a normalized sparseness measure attains a constant value. These non-convex target sets can be characterized as intersections of a…

Computational Geometry · Computer Science 2013-03-22 Markus Thom , Günther Palm

For networks of systems, with possibly improper transfer function matrices, we present a design framework which enables $\mathcal{H}_\infty$ control, while imposing sparsity constraints on the controller's coprime factors. We propose a…

Systems and Control · Electrical Eng. & Systems 2023-10-24 Andrei Sperilă , Cristian Oară , Bogdan D. Ciubotaru , Şerban Sabău

We examine the linear regression problem in a challenging high-dimensional setting with correlated predictors where the vector of coefficients can vary from sparse to dense. In this setting, we propose a combination of probabilistic…

Methodology · Statistics 2025-05-13 Roman Parzer , Peter Filzmoser , Laura Vana-Gür

In recent years, the softmax model and its fast approximations have become the de-facto loss functions for deep neural networks when dealing with multi-class prediction. This loss has been extended to language modeling and recommendation,…

Machine Learning · Statistics 2019-09-19 Ugo Tanielian , Flavian Vasile

Attention mechanism is contributing to the majority of recent advances in machine learning for natural language processing. Additionally, it results in an attention map that shows the proportional influence of each input in its decision.…

Computation and Language · Computer Science 2025-01-23 Duc Hau Nguyen , Cyrielle Mallart , Guillaume Gravier , Pascale Sébillot

In this paper, we develop a randomized algorithm and theory for learning a sparse model from large-scale and high-dimensional data, which is usually formulated as an empirical risk minimization problem with a sparsity-inducing regularizer.…

Machine Learning · Computer Science 2016-10-18 Lijun Zhang , Tianbao Yang , Rong Jin , Zhi-Hua Zhou

In this chapter, we discuss recent work on learning sparse approximations to high-dimensional functions on data, where the target functions may be scalar-, vector- or even Hilbert space-valued. Our main objective is to study how the…

Numerical Analysis · Mathematics 2022-02-08 Ben Adcock , Juan M. Cardenas , Nick Dexter , Sebastian Moraga

The maximum element of the vector output by the Softmax function approaches zero as the input vector size increases. Transformer-based language models rely on Softmax to compute attention scores, causing the attention distribution to…

Computation and Language · Computer Science 2025-02-03 Ken M. Nakanishi

Attention architectures are widely used; they recently gained renewed popularity with Transformers yielding a streak of state of the art results. Yet, the geometrical implications of softmax-attention remain largely unexplored. In this work…

Machine Learning · Computer Science 2020-05-20 Oliver Richter , Roger Wattenhofer

Classification and probability estimation are fundamental tasks with broad applications across modern machine learning and data science, spanning fields such as biology, medicine, engineering, and computer science. Recent development of…

Methodology · Statistics 2026-03-25 Liyun Zeng , Hao Helen Zhang

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 leverages sparse…

Machine Learning · Computer Science 2019-07-04 Shun Liao , Ting Chen , Tian Lin , Denny Zhou , Chong Wang

Sparseness is a useful regularizer for learning in a wide range of applications, in particular in neural networks. This paper proposes a model targeted at classification tasks, where sparse activity and sparse connectivity are used to…

Machine Learning · Computer Science 2016-04-19 Markus Thom , Günther Palm

We propose a new approach for metric learning by framing it as learning a sparse combination of locally discriminative metrics that are inexpensive to generate from the training data. This flexible framework allows us to naturally derive…

Machine Learning · Computer Science 2019-01-25 Yuan Shi , Aurélien Bellet , Fei Sha

This paper presents a novel hybrid algorithm for minimizing the sum of a continuously differentiable loss function and a nonsmooth, possibly nonconvex, sparse regularization function. The proposed method alternates between solving a…

Optimization and Control · Mathematics 2025-04-01 Hao Wang , Xiangyu Yang , Yichen Zhu

In this paper, a sparsity-aware adaptive algorithm for distributed learning in diffusion networks is developed. The algorithm follows the set-theoretic estimation rationale. At each time instance and at each node of the network, a closed…

Information Theory · Computer Science 2015-06-03 Symeon Chouvardas , Konstantinos Slavakis , Yannis Kopsinis , Sergios Theodoridis

The softmax function is a cornerstone of multi-class classification, integral to a wide range of machine learning applications, from large-scale retrieval and ranking models to advanced large language models. However, its computational cost…

Machine Learning · Computer Science 2025-01-16 Jin Chen , Jin Zhang , Xu huang , Yi Yang , Defu Lian , Enhong Chen

Most learning methods with rank or sparsity constraints use convex relaxations, which lead to optimization with the nuclear norm or the $\ell_1$-norm. However, several important learning applications cannot benefit from this approach as…

Machine Learning · Computer Science 2013-04-11 Anastasios Kyrillidis , Stephen Becker , Volkan Cevher and , Christoph Koch

In sparse optimization, enforcing hard constraints using the $\ell_0$ pseudo-norm offers advantages like controlled sparsity compared to convex relaxations. However, many real-world applications demand not only sparsity constraints but also…

Optimization and Control · Mathematics 2025-06-12 William de Vazelhes , Xiao-Tong Yuan , Bin Gu

Based on a new atomic norm, we propose a new convex formulation for sparse matrix factorization problems in which the number of nonzero elements of the factors is assumed fixed and known. The formulation counts sparse PCA with multiple…

Machine Learning · Statistics 2014-12-05 Emile Richard , Guillaume Obozinski , Jean-Philippe Vert

Solving l1 regularized optimization problems is common in the fields of computational biology, signal processing and machine learning. Such l1 regularization is utilized to find sparse minimizers of convex functions. A well-known example is…

Numerical Analysis · Computer Science 2016-07-04 Eran Treister , Javier S. Turek , Irad Yavneh