English
Related papers

Related papers: Robust Bi-Tempered Logistic Loss Based on Bregman …

200 papers

The logarithmic divergence is an extension of the Bregman divergence motivated by optimal transport and a generalized convex duality, and satisfies many remarkable properties. Using the geometry induced by the logarithmic divergence, we…

Optimization and Control · Mathematics 2022-09-08 Amanjit Singh Kainth , Ting-Kam Leonard Wong , Frank Rudzicz

Knowledge distillation transfers knowledge from a high capacity teacher to a compact student using a mixture of hard and soft losses. On imbalanced data, a fixed weighting between hard and soft losses becomes brittle the learning process.…

Machine Learning · Computer Science 2026-05-20 Anh B. H. Nguyen , Ba Tho Phan , Viet Cuong Ta

Bayesian neural learning feature a rigorous approach to estimation and uncertainty quantification via the posterior distribution of weights that represent knowledge of the neural network. This not only provides point estimates of optimal…

Machine Learning · Computer Science 2018-11-13 Rohitash Chandra , Konark Jain , Ratneel V. Deo , Sally Cripps

Neural networks trained on distilled data often produce over-confident output and require correction by calibration methods. Existing calibration methods such as temperature scaling and mixup work well for networks trained on original…

Computer Vision and Pattern Recognition · Computer Science 2023-09-18 Dongyao Zhu , Bowen Lei , Jie Zhang , Yanbo Fang , Ruqi Zhang , Yiqun Xie , Dongkuan Xu

Stochastic Gradient Descent (SGD) based methods have been widely used for training large-scale machine learning models that also generalize well in practice. Several explanations have been offered for this generalization performance, a…

Machine Learning · Computer Science 2021-02-11 Yikai Zhang , Wenjia Zhang , Sammy Bald , Vamsi Pingali , Chao Chen , Mayank Goswami

This paper investigates the use of extended Kalman filtering to train recurrent neural networks with rather general convex loss functions and regularization terms on the network parameters, including $\ell_1$-regularization. We show that…

Machine Learning · Computer Science 2022-11-03 Alberto Bemporad

In many scenarios, one uses a large training set to train a model with the goal of performing well on a smaller testing set with a different distribution. Learning a weight for each data point of the training set is an appealing solution,…

Machine Learning · Statistics 2023-10-27 Anastasia Ivanova , Pierre Ablin

There has been great interest in enhancing the robustness of neural network classifiers to defend against adversarial perturbations through adversarial training, while balancing the trade-off between robust accuracy and standard accuracy.…

Machine Learning · Computer Science 2022-10-24 Chester Holtz , Tsui-Wei Weng , Gal Mishne

Normalization techniques play an important role in supporting efficient and often more effective training of deep neural networks. While conventional methods explicitly normalize the activations, we suggest to add a loss term instead. This…

Machine Learning · Computer Science 2018-11-22 Etai Littwin , Lior Wolf

A key task in Bayesian machine learning is sampling from distributions that are only specified up to a partition function (i.e., constant of proportionality). One prevalent example of this is sampling posteriors in parametric distributions,…

Machine Learning · Computer Science 2020-09-10 Rong Ge , Holden Lee , Andrej Risteski

Robust loss functions are essential for training deep neural networks with better generalization power in the presence of noisy labels. Symmetric loss functions are confirmed to be robust to label noise. However, the symmetric condition is…

Machine Learning · Computer Science 2021-06-08 Xiong Zhou , Xianming Liu , Junjun Jiang , Xin Gao , Xiangyang Ji

Often when multiple labels are obtained for a training example it is assumed that there is an element of noise that must be accounted for. It has been shown that this disagreement can be considered signal instead of noise. In this work we…

Computation and Language · Computer Science 2019-01-28 John P. Lalor , Hao Wu , Hong Yu

The use of deep neural networks in real-world applications require well-calibrated networks with confidence scores that accurately reflect the actual probability. However, it has been found that these networks often provide over-confident…

Computer Vision and Pattern Recognition · Computer Science 2023-05-24 Linwei Tao , Minjing Dong , Chang Xu

Training deep neural networks using a large batch size has shown promising results and benefits many real-world applications. However, the optimizer converges slowly at early epochs and there is a gap between large-batch deep learning…

Machine Learning · Computer Science 2020-02-06 Zhouyuan Huo , Bin Gu , Heng Huang

It has been shown that gradient descent can yield the zero training loss in the over-parametrized regime (the width of the neural networks is much larger than the number of data points). In this work, combining the ideas of some existing…

Optimization and Control · Mathematics 2019-11-05 Lei Li

Recent work across many machine learning disciplines has highlighted that standard descent methods, even without explicit regularization, do not merely minimize the training error, but also exhibit an implicit bias. This bias is typically…

Machine Learning · Computer Science 2020-06-22 Ziwei Ji , Miroslav Dudík , Robert E. Schapire , Matus Telgarsky

In neural machine translation (NMT), the computational cost at the output layer increases with the size of the target-side vocabulary. Using a limited-size vocabulary instead may cause a significant decrease in translation quality. This…

Computation and Language · Computer Science 2018-07-31 Katsuki Chousa , Katsuhito Sudoh , Satoshi Nakamura

Resistance spot welding is the dominant joining process for the body-in-white in the automotive industry, where the weld nugget diameter is the key quality metric. Its measurement requires destructive testing, limiting the potential for…

Machine Learning · Computer Science 2026-01-27 Jan A. Zak , Christian Weißenfels

Statistical inference can be seen as information processing involving input information and output information that updates belief about some unknown parameters. We consider the Bayesian framework for making inferences about dynamical…

Statistics Theory · Mathematics 2022-01-17 Artur O. Lopes , Silvia R. C. Lopes , Paulo Varandas

Despite being the standard loss function to train multi-class neural networks, the log-softmax has two potential limitations. First, it involves computations that scale linearly with the number of output classes, which can restrict the size…

Machine Learning · Computer Science 2016-05-30 Alexandre de Brébisson , Pascal Vincent