English
Related papers

Related papers: Data-Free/Data-Sparse Softmax Parameter Estimation…

200 papers

This paper investigates the deep learning optimization problem with softmax cross-entropy loss. We propose a layer separation strategy to alleviate the strong nonconvexity encountered during training deep networks. For cross-entropy models…

Machine Learning · Computer Science 2026-04-28 Yaru Liu , Michael K. Ng , Yiqi Gu

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

Learning recommender systems with multi-class optimization objective is a prevalent setting in recommendation. However, as observed user feedback often accounts for a tiny fraction of the entire item pool, the standard Softmax loss tends to…

Information Retrieval · Computer Science 2024-10-10 Hao Zhang , Mingyue Cheng , Qi Liu , Yucong Luo , Rui Li , Enhong Chen

We introduce a convex optimization modeling framework that transforms a convex optimization problem expressed in a form natural and convenient for the user into an equivalent cone program in a way that preserves fast linear transforms in…

Optimization and Control · Mathematics 2015-11-05 Steven Diamond , Stephen Boyd

Contextual representation models have achieved great success in improving various downstream tasks. However, these language-model-based encoders are difficult to train due to the large parameter sizes and high computational complexity. By…

Computation and Language · Computer Science 2019-03-01 Liunian Harold Li , Patrick H. Chen , Cho-Jui Hsieh , Kai-Wei Chang

Deep learning models have become increasingly useful in many different industries. On the domain of image classification, convolutional neural networks proved the ability to learn robust features for the closed set problem, as shown in many…

Computer Vision and Pattern Recognition · Computer Science 2022-03-01 Rafael S. Pereira , Alexis Joly , Patrick Valduriez , Fabio Porto

Neural networks utilize the softmax as a building block in classification tasks, which contains an overconfidence problem and lacks an uncertainty representation ability. As a Bayesian alternative to the softmax, we consider a random…

Machine Learning · Computer Science 2020-06-30 Taejong Joo , Uijung Chung , Min-Gwan Seo

Distance metric learning (DML) is to learn the embeddings where examples from the same class are closer than examples from different classes. It can be cast as an optimization problem with triplet constraints. Due to the vast number of…

Computer Vision and Pattern Recognition · Computer Science 2020-04-16 Qi Qian , Lei Shang , Baigui Sun , Juhua Hu , Hao Li , Rong Jin

We propose a prototype-based approach for improving explainability of softmax classifiers that provides an understandable prediction confidence, generated through stochastic sampling of prototypes, and demonstrates potential for out of…

Machine Learning · Computer Science 2024-07-17 Hilarie Sit , Brendan Keith , Karianne Bergen

Softmax is the most commonly used output function for multiclass problems and is widely used in areas such as vision, natural language processing, and recommendation. A softmax model has linear costs in the number of classes which makes it…

Machine Learning · Computer Science 2018-08-03 Guy Blanc , Steffen Rendle

We study the problem of estimation and testing in logistic regression with class-conditional noise in the observed labels, which has an important implication in the Positive-Unlabeled (PU) learning setting. With the key observation that the…

Methodology · Statistics 2020-08-14 Hyebin Song , Ran Dai , Garvesh Raskutti , Rina Foygel Barber

Sparse matrices are favorable objects in machine learning and optimization. When such matrices are used, in place of dense ones, the overall complexity requirements in optimization can be significantly reduced in practice, both in terms of…

Information Theory · Computer Science 2016-04-05 Anastasios Kyrillidis , Bubacarr Bah , Rouzbeh Hasheminezhad , Quoc Tran-Dinh , Luca Baldassarre , Volkan Cevher

In industrial systems, certain process variables that need to be monitored for detecting faults are often difficult or impossible to measure. Soft sensor techniques are widely used to estimate such difficult-to-measure process variables…

Signal Processing · Electrical Eng. & Systems 2019-02-26 Shun Takeuchi , Takuya Nishino , Takahiro Saito , Isamu Watanabe

Softmax is a standard final layer used in Neural Nets (NNs) to summarize information encoded in the trained NN and return a prediction. However, Softmax leverages only a subset of the class-specific structure encoded in the trained model…

Machine Learning · Computer Science 2019-12-09 Charles B. Delahunt , Courosh Mehanian , J. Nathan Kutz

In label-noise learning, the transition matrix plays a key role in building statistically consistent classifiers. Existing consistent estimators for the transition matrix have been developed by exploiting anchor points. However, the…

Machine Learning · Computer Science 2021-10-22 Xuefeng Li , Tongliang Liu , Bo Han , Gang Niu , Masashi Sugiyama

We consider high-dimensional multiclass classification by sparse multinomial logistic regression. Unlike binary classification, in the multiclass setup one can think about an entire spectrum of possible notions of sparsity associated with…

Statistics Theory · Mathematics 2023-01-18 Tomer Levy , Felix Abramovich

We analyze the properties of gradient descent on convex surrogates for the zero-one loss for the agnostic learning of linear halfspaces. If $\mathsf{OPT}$ is the best classification error achieved by a halfspace, by appealing to the notion…

Machine Learning · Computer Science 2021-02-16 Spencer Frei , Yuan Cao , Quanquan Gu

We study a class of conditional independence models for discrete data with the property that one or more log-linear interactions are defined within two different marginal distributions and then constrained to 0; all the conditional…

Statistics Theory · Mathematics 2012-10-31 R. Colombi , A. Forcina

Recent work has argued that classification losses utilizing softmax cross-entropy are superior not only for fixed-set classification tasks, but also by outperforming losses developed specifically for open-set tasks including few-shot…

Machine Learning · Computer Science 2021-12-07 Tyler R. Scott , Andrew C. Gallagher , Michael C. Mozer

In many industrial processes, an apparent lack of data limits the development of data-driven soft sensors. There are, however, often opportunities to learn stronger models by being more data-efficient. To achieve this, one can leverage…

Machine Learning · Statistics 2024-07-19 Bjarne Grimstad , Kristian Løvland , Lars S. Imsland , Vidar Gunnerud