English
Related papers

Related papers: Improving Negative Sampling for Word Representatio…

200 papers

Many Collaborative Filtering (CF) algorithms are item-based in the sense that they analyze item-item relations in order to produce item similarities. Recently, several works in the field of Natural Language Processing (NLP) suggested to…

Machine Learning · Computer Science 2017-02-22 Oren Barkan , Noam Koenigstein

We simulate first- and second-order context overlap and show that Skip-Gram with Negative Sampling is similar to Singular Value Decomposition in capturing second-order co-occurrence information, while Pointwise Mutual Information is…

Computation and Language · Computer Science 2019-06-10 Dominik Schlechtweg , Cennet Oguz , Sabine Schulte im Walde

In this work we define a unified mathematical framework to deepen our understanding of the role of stochastic gradient (SG) noise on the behavior of Markov chain Monte Carlo sampling (SGMCMC) algorithms. Our formulation unlocks the design…

Machine Learning · Computer Science 2020-06-11 Giulio Franzese , Rosa Candela , Dimitrios Milios , Maurizio Filippone , Pietro Michiardi

The stochastic gradient descent (SGD) method and its variants are algorithms of choice for many Deep Learning tasks. These methods operate in a small-batch regime wherein a fraction of the training data, say $32$-$512$ data points, is…

Machine Learning · Computer Science 2017-02-13 Nitish Shirish Keskar , Dheevatsa Mudigere , Jorge Nocedal , Mikhail Smelyanskiy , Ping Tak Peter Tang

In practice, machine learning experts are often confronted with imbalanced data. Without accounting for the imbalance, common classifiers perform poorly and standard evaluation metrics mislead the practitioners on the model's performance. A…

Machine Learning · Computer Science 2020-07-21 Ramiro Camino , Christian Hammerschmidt , Radu State

The convergence speed of stochastic gradient descent (SGD) can be improved by actively selecting mini-batches. We explore sampling schemes where similar data points are less likely to be selected in the same mini-batch. In particular, we…

Machine Learning · Statistics 2018-06-21 Cheng Zhang , Cengiz Öztireli , Stephan Mandt , Giampiero Salvi

Subsampling or subdata selection is a useful approach in large-scale statistical learning. Most existing studies focus on model-based subsampling methods which significantly depend on the model assumption. In this paper, we consider the…

Methodology · Statistics 2022-09-09 Mei Zhang , Yongdao Zhou , Zheng Zhou , Aijun Zhang

Embedding based product recommendations have gained popularity in recent years due to its ability to easily integrate to large-scale systems and allowing nearest neighbor searches in real-time. The bulk of studies in this area has…

Information Retrieval · Computer Science 2022-11-30 Giorgi Kvernadze , Putu Ayu G. Sudyanti , Nishan Subedi , Mohammad Hajiaghayi

In this paper, we first present an explanation regarding the common occurrence of spikes in the training loss when neural networks are trained with stochastic gradient descent (SGD). We provide evidence that the spikes in the training loss…

Machine Learning · Computer Science 2024-06-07 Libin Zhu , Chaoyue Liu , Adityanarayanan Radhakrishnan , Mikhail Belkin

The recent progress in language-based open-vocabulary object detection can be largely attributed to finding better ways of leveraging large-scale data with free-form text annotations. Training such models with a discriminative objective…

Computer Vision and Pattern Recognition · Computer Science 2024-04-16 Shiyu Zhao , Long Zhao , Vijay Kumar B. G , Yumin Suh , Dimitris N. Metaxas , Manmohan Chandraker , Samuel Schulter

This paper reviews the gradient sampling methodology for solving nonsmooth, nonconvex optimization problems. An intuitively straightforward gradient sampling algorithm is stated and its convergence properties are summarized. Throughout this…

Optimization and Control · Mathematics 2018-05-01 James V. Burke , Frank E. Curtis , Adrian S. Lewis , Michael L. Overton , Lucas E. A. Simões

We study a distributed consensus-based stochastic gradient descent (SGD) algorithm and show that the rate of convergence involves the spectral properties of two matrices: the standard spectral gap of a weight matrix from the network…

Optimization and Control · Mathematics 2016-09-02 Avleen S. Bijral , Anand D. Sarwate , Nathan Srebro

To avoid collapse in self-supervised learning (SSL), a contrastive loss is widely used but often requires a large number of negative samples. Without negative samples yet achieving competitive performance, a recent work has attracted…

Machine Learning · Computer Science 2022-03-31 Chaoning Zhang , Kang Zhang , Chenshuang Zhang , Trung X. Pham , Chang D. Yoo , In So Kweon

Distributed representations of words encode lexical semantic information, but what type of information is encoded and how? Focusing on the skip-gram with negative-sampling method, we found that the squared norm of static word embedding…

Computation and Language · Computer Science 2023-11-03 Momose Oyama , Sho Yokoi , Hidetoshi Shimodaira

We present ImplicitSLIM, a novel unsupervised learning approach for sparse high-dimensional data, with applications to collaborative filtering. Sparse linear methods (SLIM) and their variations show outstanding performance, but they are…

Information Retrieval · Computer Science 2024-06-04 Ilya Shenbin , Sergey Nikolenko

Next-item recommender systems are often trained using only positive feedback with randomly-sampled negative feedback. We show the benefits of using real negative feedback both as inputs into the user sequence and also as negative targets…

Machine Learning · Computer Science 2025-07-28 M. Jeffrey Mei , Oliver Bembom , Andreas F. Ehmann

We propose a stochastic optimization method for minimizing loss functions, expressed as an expected value, that adaptively controls the batch size used in the computation of gradient approximations and the step size used to move along such…

Machine Learning · Computer Science 2020-03-04 Achraf Bahamou , Donald Goldfarb

The skip-gram model (SGM), which employs a neural network to generate node vectors, serves as the basis for numerous popular graph embedding techniques. However, since the training datasets contain sensitive linkage information, the…

Machine Learning · Computer Science 2025-03-28 Sen Zhang , Qingqing Ye , Haibo Hu , Jianliang Xu

Learning by contrasting positive and negative samples is a general strategy adopted by many methods. Noise contrastive estimation (NCE) for word embeddings and translating embeddings for knowledge graphs are examples in NLP employing this…

Computation and Language · Computer Science 2018-08-06 Avishek Joey Bose , Huan Ling , Yanshuai Cao

Unsupervised word segmentation in audio utterances is challenging as, in speech, there is typically no gap between words. In a preliminary experiment, we show that recent deep self-supervised features are very effective for word…

Audio and Speech Processing · Electrical Eng. & Systems 2023-04-04 Tzeviya Sylvia Fuchs , Yedid Hoshen