English
Related papers

Related papers: r-softmax: Generalized Softmax with Controllable S…

200 papers

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

Deep embedding learning is expected to learn a metric space in which features have smaller maximal intra-class distance than minimal inter-class distance. In recent years, one research focus is to solve the open-set problem by…

Computer Vision and Pattern Recognition · Computer Science 2020-11-24 Hao Zhu , Yang Yuan , Guosheng Hu , Xiang Wu , Neil Robertson

Current state-of-the-art text generators build on powerful language models such as GPT-2, achieving impressive performance. However, to avoid degenerate text, they require sampling from a modified softmax, via temperature parameters or…

Computation and Language · Computer Science 2020-10-06 Pedro Henrique Martins , Zita Marinho , André F. T. Martins

In probabilistic classification, a discriminative model based on the softmax function has a potential limitation in that it assumes unimodality for each class in the feature space. The mixture model can address this issue, although it leads…

Machine Learning · Computer Science 2021-05-10 Hideaki Hayashi , Seiichi Uchida

Random feature methods have been successful in various machine learning tasks, are easy to compute, and come with theoretical accuracy bounds. They serve as an alternative approach to standard neural networks since they can represent…

Machine Learning · Statistics 2026-01-21 Abolfazl Hashemi , Hayden Schaeffer , Robert Shi , Ufuk Topcu , Giang Tran , Rachel Ward

Attention is a core component of transformer architecture, whether encoder-only, decoder-only, or encoder-decoder model. However, the standard softmax attention often produces noisy probability distribution, which can impair effective…

Computation and Language · Computer Science 2025-11-11 Dhananjay Ram , Wei Xia , Stefano Soatto

This article proposes diffusion LMS strategies for distributed estimation over adaptive networks that are able to exploit sparsity in the underlying system model. The approach relies on convex regularization, common in compressive sensing,…

Machine Learning · Computer Science 2015-06-05 Paolo Di Lorenzo , Ali H. Sayed

Transformer attention is typically implemented using softmax normalization, which enforces attention weights with unit sum normalization. While effective in many settings, this constraint can limit flexibility in controlling attention…

Computation and Language · Computer Science 2026-02-27 Jeongin Bae , Baeseong Park , Gunho Park , Minsub Kim , Joonhyung Lee , Junhee Yoo , Sunghyeon Woo , Jiwon Ryu , Se Jung Kwon , Dongsoo Lee

Generations from large language models (LLMs) can be improved by sampling and scoring multiple solutions to select a final answer. Current "sample and select" methods such as self-consistency (SC) rely on majority voting to score answers.…

Computation and Language · Computer Science 2024-06-07 Han Wang , Archiki Prasad , Elias Stengel-Eskin , Mohit Bansal

Sparsifying neural networks often suffers from seemingly inevitable performance degradation, and it remains challenging to restore the original performance despite much recent progress. Motivated by recent studies in robust optimization, we…

Machine Learning · Computer Science 2025-06-17 Dongyeop Lee , Kwanhee Lee , Jinseok Chung , Namhoon Lee

We present a latent variable model for classification that provides a novel probabilistic interpretation of neural network softmax classifiers. We derive a variational objective to train the model, analogous to the evidence lower bound…

Machine Learning · Computer Science 2024-01-10 Shehzaad Dhuliawala , Mrinmaya Sachan , Carl Allen

Recently, diffusion probabilistic models (DPMs) have achieved promising results in diverse generative tasks. A typical DPM framework includes a forward process that gradually diffuses the data distribution and a reverse process that…

Machine Learning · Computer Science 2023-10-31 Tianyu Pang , Cheng Lu , Chao Du , Min Lin , Shuicheng Yan , Zhijie Deng

In the past few years, Softmax has become a common component in neural network frameworks. In this paper, a gradient decay hyperparameter is introduced in Softmax to control the probability-dependent gradient decay rate during training. By…

Machine Learning · Statistics 2023-10-10 Siyuan Zhang , Linbo Xie , Ying Chen

Mixture-of-experts models provide a flexible framework for learning complex probabilistic input-output relationships by combining multiple expert models through an input-dependent gating mechanism. These models have become increasingly…

Machine Learning · Statistics 2026-04-23 Nicola Bariletto , Huy Nguyen , Nhat Ho , Alessandro Rinaldo

Recently, speech recognition with ad-hoc microphone arrays has received much attention. It is known that channel selection is an important problem of ad-hoc microphone arrays, however, this topic seems far from explored in speech…

Audio and Speech Processing · Electrical Eng. & Systems 2022-02-15 Junqi Chen , Xiao-Lei Zhang

Although sparse training has been successfully used in various resource-limited deep learning tasks to save memory, accelerate training, and reduce inference time, the reliability of the produced sparse models remains unexplored. Previous…

Machine Learning · Computer Science 2023-03-02 Bowen Lei , Ruqi Zhang , Dongkuan Xu , Bani Mallick

This paper presents meta-sparsity, a framework for learning model sparsity, basically learning the parameter that controls the degree of sparsity, that allows deep neural networks (DNNs) to inherently generate optimal sparse shared…

Machine Learning · Computer Science 2025-01-22 Richa Upadhyay , Ronald Phlypo , Rajkumar Saini , Marcus Liwicki

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

Magnetic systems are highly promising for implementing probabilistic computing paradigms because of the fitting energy scales and conspicuous non-linearities. While conventional binary probabilistic computing has been realized, implementing…

Neighbor-based methods are a natural alternative to linear prediction for tabular data when relationships between inputs and targets exhibit complexity such as nonlinearity, periodicity, or heteroscedasticity. Yet in deep learning on…

Machine Learning · Computer Science 2025-12-05 Aviad Susman , Baihan Lin , Mayte Suárez-Fariñas , Joseph T Colonel