English
Related papers

Related papers: Evidential Softmax for Sparse Multimodal Distribut…

200 papers

Sparse methods for supervised learning aim at finding good linear predictors from as few variables as possible, i.e., with small cardinality of their supports. This combinatorial selection problem is often turned into a convex optimization…

Machine Learning · Computer Science 2010-11-15 Francis Bach

We introduce a sharpness functional for probabilistic models that quantifies sharpness as an intrinsic property of the probability distribution. The measure is derived based on a rank-based concentration principle that tracks upward…

Methodology · Statistics 2026-04-03 Pekka Syrjänen

Current sequence-to-sequence models are trained to minimize cross-entropy and use softmax to compute the locally normalized probabilities over target sequences. While this setup has led to strong results in a variety of tasks, one…

Computation and Language · Computer Science 2021-03-19 Ben Peters , André F. T. Martins

Aside from offering state-of-the-art performance in medical image generation, denoising diffusion probabilistic models (DPM) can also serve as a representation learner to capture semantic information and potentially be used as an image…

Image and Video Processing · Electrical Eng. & Systems 2024-07-09 Chun-Mei Feng

Regularization is crucial to the success of many practical deep learning models, in particular in a more often than not scenario where there are only a few to a moderate number of accessible training samples. In addition to weight decay,…

Machine Learning · Computer Science 2018-08-07 Che-Wei Huang , Shrikanth S. Narayanan

Sparse coding strategies have been lauded for their parsimonious representations of data that leverage low dimensional structure. However, inference of these codes typically relies on an optimization procedure with poor computational…

Machine Learning · Computer Science 2022-09-02 Kion Fallah , Christopher J. Rozell

This thesis studies high-dimensional, continuous-valued pairwise Markov Random Fields. We are particularly interested in approximating pairwise densities whose logarithm belongs to a Sobolev space. For this problem we propose the method of…

Statistics Theory · Mathematics 2015-06-12 Eric Janofsky

Denoising diffusions are state-of-the-art generative models exhibiting remarkable empirical performance. They work by diffusing the data distribution into a Gaussian distribution and then learning to reverse this noising process to obtain…

Machine Learning · Statistics 2024-02-20 Joe Benton , Yuyang Shi , Valentin De Bortoli , George Deligiannidis , Arnaud Doucet

Stochastic variance reduced methods have gained a lot of interest recently for empirical risk minimization due to its appealing run time complexity. When the data size is large and disjointly stored on different machines, it becomes…

Machine Learning · Computer Science 2020-08-26 Shicong Cen , Huishuai Zhang , Yuejie Chi , Wei Chen , Tie-Yan Liu

We study the problem of policy optimization for infinite-horizon discounted Markov Decision Processes with softmax policy and nonlinear function approximation trained with policy gradient algorithms. We concentrate on the training dynamics…

Machine Learning · Computer Science 2020-10-23 Andrea Agazzi , Jianfeng Lu

In the past few years, deep generative models, such as generative adversarial networks \autocite{GAN}, variational autoencoders \autocite{vaepaper}, and their variants, have seen wide adoption for the task of modelling complex data…

Machine Learning · Statistics 2020-09-02 Guilherme G. P. Freitas Pires , Mário A. T. Figueiredo

We introduce a doubly stochastic proximal gradient algorithm for optimizing a finite average of smooth convex functions, whose gradients depend on numerically expensive expectations. Our main motivation is the acceleration of the…

Machine Learning · Statistics 2016-11-09 Massil Achab , Agathe Guilloux , Stéphane Gaïffas , Emmanuel Bacry

We illustrate the detrimental effect, such as overconfident decisions, that exponential behavior can have in methods like classical LDA and logistic regression. We then show how polynomiality can remedy the situation. This, among others,…

Machine Learning · Computer Science 2022-03-25 Ziqi Wang , Marco Loog

Noisy labels pose a common challenge for training accurate deep neural networks. To mitigate label noise, prior studies have proposed various robust loss functions to achieve noise tolerance in the presence of label noise, particularly…

Machine Learning · Computer Science 2025-08-05 Jialiang Wang , Xiong Zhou , Deming Zhai , Junjun Jiang , Xiangyang Ji , Xianming Liu

The softmax function is a ubiquitous component at the output of neural networks and increasingly in intermediate layers as well. This paper provides convex lower bounds and concave upper bounds on the softmax function, which are compatible…

Machine Learning · Computer Science 2023-03-06 Dennis Wei , Haoze Wu , Min Wu , Pin-Yu Chen , Clark Barrett , Eitan Farchi

We consider continuous-time sparse stochastic processes from which we have only a finite number of noisy/noiseless samples. Our goal is to estimate the noiseless samples (denoising) and the signal in-between (interpolation problem). By…

Machine Learning · Computer Science 2015-06-11 Arash Amini , Ulugbek S. Kamilov , Emrah Bostan , Michael Unser

In text generation, a large language model (LM) makes a choice of each new word based only on the former selection of its context using the softmax function. Nevertheless, the link statistics information of concurrent words based on a…

Computation and Language · Computer Science 2023-12-20 Liu Bin , Yin Guosheng

In this paper, we present a maximum likelihood estimation approach to determine the value vector in transformer models. We model the sequence of value vectors, key vectors, and the query vector as a sequence of Gaussian distributions. The…

Machine Learning · Computer Science 2025-09-17 Jiyong Ma

We consider learning a probabilistic classifier from partially-labelled supervision (inputs denoted with multiple possibilities) using standard neural architectures with a softmax as the final layer. We identify a bias phenomenon that can…

Machine Learning · Computer Science 2023-07-04 Zsolt Zombori , Agapi Rissaki , Kristóf Szabó , Wolfgang Gatterbauer , Michael Benedikt

We propose a large-margin Gaussian Mixture (L-GM) loss for deep neural networks in classification tasks. Different from the softmax cross-entropy loss, our proposal is established on the assumption that the deep features of the training set…

Computer Vision and Pattern Recognition · Computer Science 2018-03-09 Weitao Wan , Yuanyi Zhong , Tianpeng Li , Jiansheng Chen