English
Related papers

Related papers: Generalized Kullback-Leibler Divergence Loss

200 papers

Universal hypothesis testing refers to the problem of deciding whether samples come from a nominal distribution or an unknown distribution that is different from the nominal distribution. Hoeffding's test, whose test statistic is equivalent…

Information Theory · Computer Science 2017-11-15 Pengfei Yang , Biao Chen

Kullback-Leibler (KL) divergence is one of the most important divergence measures between probability distributions. In this paper, we prove several properties of KL divergence between multivariate Gaussian distributions. First, for any two…

Information Theory · Computer Science 2023-01-24 Yufeng Zhang , Wanwei Liu , Zhenbang Chen , Ji Wang , Kenli Li

Normalizing flows can generate complex target distributions and thus show promise in many applications in Bayesian statistics as an alternative or complement to MCMC for sampling posteriors. Since no data set from the target posterior…

Machine Learning · Statistics 2021-07-19 Marylou Gabrié , Grant M. Rotskoff , Eric Vanden-Eijnden

Knowledge distillation (KD) is one of the prominent techniques for model compression. In this method, the knowledge of a large network (teacher) is distilled into a model (student) with usually significantly fewer parameters. KD tries to…

Machine Learning · Computer Science 2023-01-31 Aref Jafari , Mehdi Rezagholizadeh , Ali Ghodsi

Despite the success of two-stage few-shot classification methods, in the episodic meta-training stage, the model suffers severe overfitting. We hypothesize that it is caused by over-discrimination, i.e., the model learns to over-rely on the…

Machine Learning · Computer Science 2023-07-10 Siqi Hui , Sanping Zhou , Ye deng , Jinjun Wang

Benefiting from well-trained deep neural networks (DNNs), model compression have captured special attention for computing resource limited equipment, especially edge devices. Knowledge distillation (KD) is one of the widely used compression…

Machine Learning · Computer Science 2024-06-06 Jinyin Chen , Xiaoming Zhao , Haibin Zheng , Xiao Li , Sheng Xiang , Haifeng Guo

Crossmodal knowledge distillation (KD) aims to enhance a unimodal student using a multimodal teacher model. In particular, when the teacher's modalities include the student's, additional complementary information can be exploited to improve…

Computer Vision and Pattern Recognition · Computer Science 2025-04-01 Chenqi Guo , Mengshuo Rong , Qianli Feng , Rongfan Feng , Yinglong Ma

Diffusion models are a new class of generative models that revolve around the estimation of the score function associated with a stochastic differential equation. Subsequent to its acquisition, the approximated score function is then…

Statistics Theory · Mathematics 2024-09-13 Giovanni Conforti , Alain Durmus , Marta Gentiloni Silveri

Learning interpretable and human-controllable representations that uncover factors of variation in data remains an ongoing key challenge in representation learning. We investigate learning group-disentangled representations for groups of…

Machine Learning · Computer Science 2021-10-26 Linh Tran , Amir Hosein Khasahmadi , Aditya Sanghi , Saeid Asgari

The need for scalable and expressive models in machine learning is paramount, particularly in applications requiring both structural depth and flexibility. Traditional deep learning methods, such as multilayer perceptrons (MLP), offer depth…

Machine Learning · Computer Science 2024-08-01 Shrenik Zinage , Sudeepta Mondal , Soumalya Sarkar

Learning to sample from intractable distributions over discrete sets without relying on corresponding training data is a central problem in a wide range of fields, including Combinatorial Optimization. Currently, popular deep learning-based…

Machine Learning · Computer Science 2025-08-25 Sebastian Sanokowski , Sepp Hochreiter , Sebastian Lehner

General Continual Learning (GCL) aims at learning from non independent and identically distributed stream data without catastrophic forgetting of the old tasks that don't rely on task boundaries during both training and testing stages. We…

Computer Vision and Pattern Recognition · Computer Science 2023-01-02 Zhong Ji , Jin Li , Qiang Wang , Zhongfei Zhang

Knowledge Distillation (KD) aims to distill the knowledge of a cumbersome teacher model into a lightweight student model. Its success is generally attributed to the privileged information on similarities among categories provided by the…

Computer Vision and Pattern Recognition · Computer Science 2021-03-05 Li Yuan , Francis E. H. Tay , Guilin Li , Tao Wang , Jiashi Feng

Knowledge distillation, i.e., one classifier being trained on the outputs of another classifier, is an empirically very successful technique for knowledge transfer between classifiers. It has even been observed that classifiers learn much…

Machine Learning · Computer Science 2021-05-28 Mary Phuong , Christoph H. Lampert

We present a method for explaining the image classification predictions of deep convolution neural networks, by highlighting the pixels in the image which influence the final class prediction. Our method requires the identification of a…

Artificial Intelligence · Computer Science 2018-01-26 Housam Khalifa Bashier Babiker , Randy Goebel

Knowledge distillation (KD) is a standard route to compress Large Language Models (LLMs) into compact students, yet most pipelines uniformly apply token-wise loss regardless of teacher confidence. This indiscriminate supervision amplifies…

Computation and Language · Computer Science 2025-11-18 Haiduo Huang , Jiangcheng Song , Yadong Zhang , Pengju Ren

Knowledge Distillation (KD) is a common knowledge transfer algorithm used for model compression across a variety of deep learning based natural language processing (NLP) solutions. In its regular manifestations, KD requires access to the…

Computation and Language · Computer Science 2021-01-01 Ahmad Rashid , Vasileios Lioutas , Abbas Ghaddar , Mehdi Rezagholizadeh

The primary goal of training in early convolutional neural networks (CNN) is the higher generalization performance of the model. However, as the expected calibration error (ECE), which quantifies the explanatory power of model inference,…

Computer Vision and Pattern Recognition · Computer Science 2023-02-01 Seungbum Hong , Jihun Yoon , Bogyu Park , Min-Kook Choi

Bayesian neural networks (BNNs) are state-of-the-art machine learning methods that can naturally regularize and systematically quantify uncertainties using their stochastic parameters. Kullback-Leibler (KL) divergence-based variational…

Machine Learning · Computer Science 2024-12-10 Ponkrshnan Thiagarajan , Susanta Ghosh

Deep Learning (DL) is considered the state-of-the-art in computer vision, speech recognition and natural language processing. Until recently, it was also widely accepted that DL is irrelevant for learning tasks on tabular data, especially…

Machine Learning · Computer Science 2021-06-30 Karim Lounici , Katia Meziani , Benjamin Riu