English
Related papers

Related papers: Unbiased scalable softmax optimization

200 papers

Learning distributed representations, or embeddings, that encode the relational similarity patterns among objects is a relevant task in machine learning. A popular method to learn the embedding matrices $X, Y$ is optimizing a loss function…

Machine Learning · Computer Science 2025-06-03 Lorenzo Dall'Amico , Enrico Maria Belliardo

We propose a unified framework for estimating low-rank matrices through nonconvex optimization based on gradient descent algorithm. Our framework is quite general and can be applied to both noisy and noiseless observations. In the general…

Machine Learning · Statistics 2016-10-18 Lingxiao Wang , Xiao Zhang , Quanquan Gu

In this paper, we introduce an unbiased gradient simulation algorithms for solving convex optimization problem with stochastic function compositions. We show that the unbiased gradient generated from the algorithm has finite variance and…

Optimization and Control · Mathematics 2017-11-22 Jose Blanchet , Donald Goldfarb , Garud Iyengar , Fengpei Li , Chaoxu Zhou

Nonparametric maximum likelihood estimation is intended to infer the unknown density distribution while making as few assumptions as possible. To alleviate the over parameterization in nonparametric data fitting, smoothing assumptions are…

Machine Learning · Statistics 2021-04-21 YunPeng Li , ZhaoHui Ye

A framework is presented for unsupervised learning of representations based on infomax principle for large-scale neural populations. We use an asymptotic approximation to the Shannon's mutual information for a large neural population to…

Machine Learning · Computer Science 2017-03-13 Wentao Huang , Kechen Zhang

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

This paper presents a framework in which hierarchical softmax is used to create a global hierarchical classifier. The approach is applicable for any classification task where there is a natural hierarchy among classes. We show empirical…

Machine Learning · Statistics 2023-08-03 Jetze Schuurmans , Flavius Frasincar

In many applications we seek to maximize an expectation with respect to a distribution over discrete variables. Estimating gradients of such objectives with respect to the distribution parameters is a challenging problem. We analyze…

Machine Learning · Statistics 2019-06-18 Evgeny Andriyash , Arash Vahdat , Bill Macready

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

Sampling random graphs with given properties is a key step in the analysis of networks, as random ensembles represent basic null models required to identify patterns such as communities and motifs. An important requirement is that the…

Methodology · Statistics 2015-02-23 Tiziano Squartini , Rossana Mastrandrea , Diego Garlaschelli

A distributed consensus algorithm for estimating the maximum value of the initial measurements in a sensor network with communication noise is proposed. In the absence of communication noise, max estimation can be done by updating the state…

Systems and Control · Computer Science 2016-02-04 Sai Zhang , Cihan Tepedelenlioglu , Mahesh K. Banavar , Andreas Spanias

Typically, Softmax is used in the final layer of a neural network to get a probability distribution for output classes. But the main problem with Softmax is that it is computationally expensive for large scale data sets with large number of…

Machine Learning · Computer Science 2018-12-17 Abdul Arfat Mohammed , Venkatesh Umaashankar

This article introduces a decentralized robust optimization framework for safe multi-agent control under uncertainty. Although stochastic noise has been the primary form of modeling uncertainty in such systems, these formulations might fall…

Optimization and Control · Mathematics 2025-08-19 Arshiya Taj Abdul , Augustinos D. Saravanos , Evangelos A. Theodorou

A number of optimization approaches have been proposed for optimizing nonconvex objectives (e.g. deep learning models), such as batch gradient descent, stochastic gradient descent and stochastic variance reduced gradient descent. Theory…

Machine Learning · Computer Science 2019-05-15 Jia Bi , Steve R. Gunn

We present general principles for the design and analysis of unbiased Monte Carlo estimators in a wide range of settings. Our estimators posses finite work-normalized variance under mild regularity conditions. We apply our estimators to…

Statistics Theory · Mathematics 2019-04-23 Jose H. Blanchet , Peter W. Glynn , Yanan Pei

In a multi-class classification problem, it is standard to model the output of a neural network as a categorical distribution conditioned on the inputs. The output must therefore be positive and sum to one, which is traditionally enforced…

Neural and Evolutionary Computing · Computer Science 2016-03-01 Alexandre de Brébisson , Pascal Vincent

Large language models (LLMs) have brought about significant transformations in human society. Among the crucial computations in LLMs, the softmax unit holds great importance. Its helps the model generating a probability distribution on…

Machine Learning · Computer Science 2023-07-18 Yichuan Deng , Zhihang Li , Sridhar Mahadevan , Zhao Song

This work explores maximum likelihood optimization of neural networks through hypernetworks. A hypernetwork initializes the weights of another network, which in turn can be employed for typical functional tasks such as regression and…

Machine Learning · Statistics 2018-01-15 Abdul-Saboor Sheikh , Kashif Rasul , Andreas Merentitis , Urs Bergmann

Choosing the optimization algorithm that performs best on a given machine learning problem is often delicate, and there is no guarantee that current state-of-the-art algorithms will perform well across all tasks. Consequently, the more…

Optimization and Control · Mathematics 2024-06-25 Måns Williamson , Monika Eisenmann , Tony Stillfjord

Constructing confidence intervals for the value of an (unknown) optimal treatment policy is a fundamental problem in causal inference. Insight into the optimal policy value can guide the development of reward-maximizing, individualized…

Econometrics · Economics 2026-04-01 Justin Whitehouse , Qizhao Chen , Morgane Austern , Vasilis Syrgkanis