English
Related papers

Related papers: Unbiased scalable softmax optimization

200 papers

We consider distributed optimization problems where forming the Hessian is computationally challenging and communication is a significant bottleneck. We develop unbiased parameter averaging methods for randomized second order optimization…

Machine Learning · Statistics 2020-02-18 Burak Bartan , Mert Pilanci

Replicated Softmax model, a well-known undirected topic model, is powerful in extracting semantic representations of documents. Traditional learning strategies such as Contrastive Divergence are very inefficient. This paper provides a novel…

Machine Learning · Computer Science 2015-06-25 Jiatao Gu , Victor O. K. Li

Approximate numerical methods are one of the most used strategies to extract information from many-interacting-agents systems. In particular, numerical approximations are of extended use to deal with epidemic, ecological and biological…

Physics and Society · Physics 2025-08-27 Javier Aguilar , Jose J. Ramasco , Raúl Toral

To encourage intra-class compactness and inter-class separability among trainable feature vectors, large-margin softmax methods are developed and widely applied in the face recognition community. The introduction of the large-margin concept…

Audio and Speech Processing · Electrical Eng. & Systems 2021-04-22 Jingjing Huo , Yingbo Gao , Weiyue Wang , Ralf Schlüter , Hermann Ney

Modern machine learning forces practitioners to choose between powerful but expensive deep networks and fast but limited classical algorithms. Here we introduce Soft Learning, a framework that maintains a library of heterogeneous…

Machine Learning · Computer Science 2026-05-20 Mohammed Aledhari , Ali Aledhari , Fatimah Aledhari , Mohamed Rahouti

For rare events described in terms of Markov processes, truly unbiased estimation of the rare event probability generally requires the avoidance of numerical approximations of the Markov process. Recent work in the exact and…

Statistics Theory · Mathematics 2021-11-08 James Hodgson , Adam M. Johansen , Murray Pollock

Simple exponential smoothing is widely used in forecasting economic time series. This is because it is quick to compute and it generally delivers accurate forecasts. On the other hand, its multivariate version has received little attention…

Computation · Statistics 2021-03-17 Federico Poloni , Giacomo Sbrana

Deep classifiers have achieved great success in visual recognition. However, real-world data is long-tailed by nature, leading to the mismatch between training and testing distributions. In this paper, we show that the Softmax function,…

Machine Learning · Computer Science 2020-11-24 Jiawei Ren , Cunjun Yu , Shunan Sheng , Xiao Ma , Haiyu Zhao , Shuai Yi , Hongsheng Li

Normalization is a vital process for any machine learning task as it controls the properties of data and affects model performance at large. The impact of particular forms of normalization, however, has so far been investigated in limited…

Machine Learning · Computer Science 2022-06-22 Chintan Trivedi , Konstantinos Makantasis , Antonios Liapis , Georgios N. Yannakakis

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

Extracting a common robust signal from data divided into heterogeneous groups can be difficult when each group -- in addition to the signal -- can contain large, unique variation components. Previously, maximin estimation has been proposed…

Methodology · Statistics 2022-04-11 Adam Lund , Søren Wengel Mogensen , Niels Richard Hansen

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

Softmax is popular normalization method used in machine learning. Deep learning solutions like Transformer or BERT use the softmax function intensively, so it is worthwhile to optimize its performance. This article presents our methodology…

Mathematical Software · Computer Science 2019-05-28 Jacek Czaja , Michal Gallus , Tomasz Patejko , Jian Tang

Necessary and sufficient conditions for the square-integrability of recently proposed unbiased estimators are established. A geometric characterization of a distribution that optimizes the performance of these estimators is given. An…

Statistics Theory · Mathematics 2019-09-09 Nabil Kahale

Unbiased estimation for parameters of maximal distribution is a very fundamental problem in the statistical theory of sublinear expectation. In this paper, we proved that the maximum estimator is the largest unbiased estimator for the upper…

Probability · Mathematics 2016-11-28 Hanqing Jin , Shige Peng

The Softmax function is ubiquitous in machine learning, multiple previous works suggested faster alternatives for it. In this paper we propose a way to compute classical Softmax with fewer memory accesses and hypothesize that this reduction…

Performance · Computer Science 2018-07-31 Maxim Milakov , Natalia Gimelshein

To mitigate the problem of having to traverse over the full vocabulary in the softmax normalization of a neural language model, sampling-based training criteria are proposed and investigated in the context of large vocabulary word-based…

Computation and Language · Computer Science 2022-06-20 Zijian Yang , Yingbo Gao , Alexander Gerstenberger , Jintao Jiang , Ralf Schlüter , Hermann Ney

Softmax is widely used in deep learning to map some representation to a probability distribution. As it is based on exp/log functions that are relatively expensive in multi-party computation, Mohassel and Zhang (2017) proposed a simpler…

Machine Learning · Computer Science 2021-07-07 Marcel Keller , Ke Sun

This work provides simple algorithms for multi-class (and multi-label) prediction in settings where both the number of examples n and the data dimension d are relatively large. These robust and parameter free algorithms are essentially…

Machine Learning · Computer Science 2013-10-22 Alekh Agarwal , Sham M. Kakade , Nikos Karampatziakis , Le Song , Gregory Valiant

The Softmax function on top of a final linear layer is the de facto method to output probability distributions in neural networks. In many applications such as language models or text generation, this model has to produce distributions over…

Machine Learning · Computer Science 2019-05-15 Octavian-Eugen Ganea , Sylvain Gelly , Gary Bécigneul , Aliaksei Severyn