English
Related papers

Related papers: Beyond Softmax: A Natural Parameterization for Cat…

200 papers

In classification tasks, softmax functions are ubiquitously used as output activations to produce predictive probabilities. Such outputs only capture aleatoric uncertainty. To capture epistemic uncertainty, approximate Gaussian inference…

Machine Learning · Computer Science 2026-02-12 Bálint Mucsányi , Nathaël Da Costa , Philipp Hennig

Despite great popularity of applying softmax to map the non-normalised outputs of a neural network to a probability distribution over predicting classes, this normalised exponential transformation still seems to be artificial. A theoretic…

Machine Learning · Computer Science 2019-10-16 Zhenyue Qin , Dongwoo Kim

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

Many real-world optimization problems contain parameters that are unknown before deployment time, either due to stochasticity or to lack of information (e.g., demand or travel times in delivery problems). A common strategy in such cases is…

We introduce Gradient Agreement Filtering (GAF) to improve on gradient averaging in distributed deep learning optimization. Traditional distributed data-parallel stochastic gradient descent involves averaging gradients of microbatches to…

Machine Learning · Computer Science 2024-12-31 Francois Chaubard , Duncan Eddy , Mykel J. Kochenderfer

Task specific fine-tuning of a pre-trained neural language model using a custom softmax output layer is the de facto approach of late when dealing with document classification problems. This technique is not adequate when labeled examples…

Computation and Language · Computer Science 2020-10-27 Natraj Raman , Armineh Nourbakhsh , Sameena Shah , Manuela Veloso

This is a short communication on a Lyapunov function argument for softmax in bandit problems. There are a number of excellent papers coming out using differential equations for policy gradient algorithms in reinforcement learning…

Machine Learning · Computer Science 2020-07-21 Neil Walton

In this paper we introduce Feature Gradients, a gradient-based search algorithm for feature selection. Our approach extends a recent result on the estimation of learnability in the sublinear data regime by showing that the calculation can…

Machine Learning · Statistics 2019-08-29 Rishit Sheth , Nicolo Fusi

A major obstacle to achieving global convergence in distributed and federated learning is the misalignment of gradients across clients, or mini-batches due to heterogeneity and stochasticity of the distributed data. In this work, we show…

Machine Learning · Computer Science 2021-12-14 Yatin Dandi , Luis Barba , Martin Jaggi

Adapting a model to perform well on unforeseen data outside its training set is a common problem that continues to motivate new approaches. We demonstrate that application of batch normalization in the output layer, prior to softmax…

Computer Vision and Pattern Recognition · Computer Science 2021-03-23 Matthew R. Behrend , Sean M. Robinson

Stochastic gradient descent procedures have gained popularity for parameter estimation from large data sets. However, their statistical properties are not well understood, in theory. And in practice, avoiding numerical instability requires…

Methodology · Statistics 2016-09-29 Panos Toulis , Edoardo M. Airoldi

Existing deep learning methods have made significant progress in gait representation learning. Quantization can facilitate the application of gait models as a model-agnostic general compression technique. Typically, appearance-based models…

Computer Vision and Pattern Recognition · Computer Science 2026-03-24 S. Tian , H. Gao , G. Hong , S. Wang , J. Wang , X. Yu , S. Zhang

Parameter-transfer is a well-known and versatile approach for meta-learning, with applications including few-shot learning, federated learning, and reinforcement learning. However, parameter-transfer algorithms often require sharing models…

Machine Learning · Computer Science 2020-02-24 Jeffrey Li , Mikhail Khodak , Sebastian Caldas , Ameet Talwalkar

Equipping a deep model the abaility of few-shot learning, i.e., learning quickly from only few examples, is a core challenge for artificial intelligence. Gradient-based meta-learning approaches effectively address the challenge by learning…

Machine Learning · Computer Science 2024-01-09 Baoquan Zhang , Chuyao Luo , Demin Yu , Huiwei Lin , Xutao Li , Yunming Ye , Bowen Zhang

Although normalization layers have long been viewed as indispensable components of deep learning architectures, the recent introduction of Dynamic Tanh (DyT) has demonstrated that alternatives are possible. The point-wise function DyT…

Machine Learning · Computer Science 2026-04-01 Mingzhi Chen , Taiming Lu , Jiachen Zhu , Mingjie Sun , Zhuang Liu

In this paper, we point out that differential architecture search (DARTS) makes gradient of architecture parameters biased for network weights and architecture parameters are updated in different datasets alternatively in the bi-level…

Machine Learning · Computer Science 2020-12-22 Pengfei Hou , Ying Jin

Feature whitening is a known technique for speeding up training of DNN. Under certain assumptions, whitening the activations reduces the Fisher information matrix to a simple identity matrix, in which case stochastic gradient descent is…

Machine Learning · Computer Science 2020-11-10 Shmulik Markovich-Golan , Barak Battash , Amit Bleiweiss

We study the training dynamics of gradient descent in a softmax self-attention layer trained to perform linear regression and show that a simple first-order optimization algorithm can converge to the globally optimal self-attention…

Machine Learning · Computer Science 2026-03-03 Gautam Goel , Mahdi Soltanolkotabi , Peter Bartlett

In this paper, we introduce a powerful and efficient framework for direct optimization of ranking metrics. The problem is ill-posed due to the discrete structure of the loss, and to deal with that, we introduce two important techniques:…

Machine Learning · Computer Science 2020-08-21 Aleksei Ustimenko , Liudmila Prokhorenkova

Many problems encountered in science and engineering can be formulated as estimating a low-rank object (e.g., matrices and tensors) from incomplete, and possibly corrupted, linear measurements. Through the lens of matrix and tensor…

Machine Learning · Computer Science 2023-10-11 Cong Ma , Xingyu Xu , Tian Tong , Yuejie Chi