English
Related papers

Related papers: A Quantitative Evaluation of Approximate Softmax F…

200 papers

Uncertainty approximation in text classification is an important area with applications in domain adaptation and interpretability. One of the most widely used uncertainty approximation methods is Monte Carlo (MC) Dropout, which is…

Machine Learning · Computer Science 2023-07-20 Andreas Nugaard Holm , Dustin Wright , Isabelle Augenstein

In order to push the performance on realistic computer vision tasks, the number of classes in modern benchmark datasets has significantly increased in recent years. This increase in the number of classes comes along with increased ambiguity…

Machine Learning · Statistics 2016-04-14 Maksim Lapin , Matthias Hein , Bernt Schiele

Transformers have revolutionized natural language processing, but their use for numerical computation has received less attention. We study the approximation of matrix functions, which map scalar functions to matrices, using neural networks…

Machine Learning · Computer Science 2026-02-10 Rahul Padmanabhan , Simone Brugiapaglia

Research has shown that deep neural networks contain significant redundancy, and thus that high classification accuracy can be achieved even when weights and activations are quantized down to binary values. Network binarization on FPGAs…

Machine Learning · Computer Science 2020-03-04 Erwei Wang , James J. Davis , Peter Y. K. Cheung , George A. Constantinides

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

We propose sparsemax, a new activation function similar to the traditional softmax, but able to output sparse probabilities. After deriving its properties, we show how its Jacobian can be efficiently computed, enabling its use in a network…

Computation and Language · Computer Science 2016-02-09 André F. T. Martins , Ramón Fernandez Astudillo

Learning complicated value functions in high dimensional state space by function approximation is a challenging task, partially due to that the max-operator used in temporal difference updates can theoretically cause instability for most…

Machine Learning · Computer Science 2020-12-21 Yaozhong Gan , Zhe Zhang , Xiaoyang Tan

Softmax attention is a central component of transformer architectures, yet its nonlinear structure poses significant challenges for theoretical analysis. We develop a unified, measure-based framework for studying single-layer softmax…

Machine Learning · Computer Science 2025-12-15 Etienne Boursier , Claire Boyer

Real-world sensor-based learning systems require uncertainty estimation that is both reliable and computationally efficient. Evidential Deep Learning (EDL) provides single-pass uncertainty estimation by modeling the class probabilities via…

Machine Learning · Computer Science 2026-05-22 Berk Hayta , Hannah Laus , Simon Mittermaier , Felix Krahmer

Matrix and tensor completion aim to recover a low-rank matrix / tensor from limited observations and have been commonly used in applications such as recommender systems and multi-relational data mining. A state-of-the-art matrix completion…

Numerical Analysis · Computer Science 2018-08-28 Quanming Yao , James T. Kwok

Linear attentions have shown potential for improving Transformer efficiency, reducing attention's quadratic complexity to linear in sequence length. This holds exciting promise for (1) training linear Transformers from scratch, (2)…

Machine Learning · Computer Science 2024-02-08 Michael Zhang , Kush Bhatia , Hermann Kumbong , Christopher Ré

The rapid development of the Transformer-based Large Language Models (LLMs) in recent years has been closely linked to their ever-growing and already enormous sizes. Many LLMs contain hundreds of billions of parameters and require dedicated…

Computation and Language · Computer Science 2025-02-26 Mahsa Salmani , Ilya Soloveychik

Deep learning at its core, contains functions that are composition of a linear transformation with a non-linear function known as activation function. In past few years, there is an increasing interest in construction of novel activation…

Neural and Evolutionary Computing · Computer Science 2020-09-09 Koushik Biswas , Sandeep Kumar , Shilpak Banerjee , Ashish Kumar Pandey

Deep Neural Networks (DNNs) have performed admirably in classification tasks. However, the characterization of their classification uncertainties, required for certain applications, has been lacking. In this work, we investigate the issue…

Machine Learning · Computer Science 2023-11-28 Yu Pan , Kwo-Sen Kuo , Michael L. Rilee , Hongfeng Yu

The impact of softmax on the value function itself in reinforcement learning (RL) is often viewed as problematic because it leads to sub-optimal value (or Q) functions and interferes with the contraction properties of the Bellman operator.…

Machine Learning · Computer Science 2019-05-21 Zhao Song , Ronald E. Parr , Lawrence Carin

Constrained low-rank matrix approximations have been known for decades as powerful linear dimensionality reduction techniques to be able to extract the information contained in large data sets in a relevant way. However, such low-rank…

Machine Learning · Computer Science 2021-12-20 Pierre De Handschutter , Nicolas Gillis , Xavier Siebert

Large language models (LLMs) have revolutionized natural language processing (NLP) by excelling at understanding and generating human-like text. However, their widespread deployment can be prohibitively expensive. SortedNet is a recent…

Computation and Language · Computer Science 2024-02-12 Parsa Kavehzadeh , Mojtaba Valipour , Marzieh Tahaei , Ali Ghodsi , Boxing Chen , Mehdi Rezagholizadeh

In this work, we show that saturating output activation functions, such as the softmax, impede learning on a number of standard classification tasks. Moreover, we present results showing that the utility of softmax does not stem from the…

Machine Learning · Computer Science 2017-07-14 Anders Oland , Aayush Bansal , Roger B. Dannenberg , Bhiksha Raj

Large language models rely on attention mechanisms with a softmax activation. Yet the dominance of softmax over alternatives (e.g., component-wise or linear) remains poorly understood, and many theoretical works have focused on the…

Machine Learning · Computer Science 2026-02-27 O. Duranthon , P. Marion , C. Boyer , B. Loureiro , L. Zdeborová

While transformer models exhibit strong in-context learning (ICL) abilities, they often fail to generalize under simple distribution shifts. We analyze these failures and identify Softmax, the scoring function in the attention mechanism, as…

Computation and Language · Computer Science 2026-05-12 Omar Naim , Swarnadeep Bhar , Jérôme Bolte , Nicholas Asher
‹ Prev 1 4 5 6 7 8 10 Next ›