English
Related papers

Related papers: Decoupled Kullback-Leibler Divergence Loss

200 papers

In the loss function of Variational Autoencoders there is a well known tension between two components: the reconstruction loss, improving the quality of the resulting images, and the Kullback-Leibler divergence, acting as a regularizer of…

Neural and Evolutionary Computing · Computer Science 2020-02-19 Andrea Asperti , Matteo Trentin

We consider model-based reinforcement learning in finite Markov De- cision Processes (MDPs), focussing on so-called optimistic strategies. In MDPs, optimism can be implemented by carrying out extended value it- erations under a constraint…

Machine Learning · Computer Science 2011-09-22 Sarah Filippi , Olivier Cappé , Aurélien Garivier

Information-theoretic measures such as the entropy, cross-entropy and the Kullback-Leibler divergence between two mixture models is a core primitive in many signal processing tasks. Since the Kullback-Leibler divergence of mixtures provably…

Machine Learning · Computer Science 2017-02-01 Frank Nielsen , Ke Sun

Deep neural networks (DNNs) have improved NLP tasks significantly, but training and maintaining such networks could be costly. Model compression techniques, such as, knowledge distillation (KD), have been proposed to address the issue;…

Computation and Language · Computer Science 2023-11-08 Manas Mohanty , Tanya Roosta , Peyman Passban

We consider the problem of estimating probability density functions based on sample data, using a finite mixture of densities from some component class. To this end, we introduce the $h$-lifted Kullback--Leibler (KL) divergence as a…

Machine Learning · Statistics 2024-12-24 Mark Chiu Chong , Hien Duy Nguyen , TrungTin Nguyen

Knowledge Distillation (KD) has emerged as a crucial technique for compressing Large Language Models (LLMs). Although existing cross-tokenizer KD methods have made notable progress, their effectiveness remains constrained by suboptimal…

Computation and Language · Computer Science 2026-02-26 Duc Trung Vu , Pham Khanh Chi , Dat Phi Van , Linh Ngo Van , Sang Dinh , Trung Le

Continual learning, involving sequential training on diverse tasks, often faces catastrophic forgetting. While knowledge distillation-based approaches exhibit notable success in preventing forgetting, we pinpoint a limitation in their…

Machine Learning · Computer Science 2024-05-17 Zenglin Shi , Pei Liu , Tong Su , Yunpeng Wu , Kuien Liu , Yu Song , Meng Wang

Inferring and comparing complex, multivariable probability density functions is fundamental to problems in several fields, including probabilistic learning, network theory, and data analysis. Classification and prediction are the two faces…

Information Theory · Computer Science 2017-03-30 David J. Galas , T. Gregory Dewey , James Kunert-Graf , Nikita A. Sakhanenko

In this paper, we consider the problem of improving the inference latency of language model-based dense retrieval systems by introducing structural compression and model size asymmetry between the context and query encoders. First, we…

Computation and Language · Computer Science 2023-06-05 Daniel Campos , Alessandro Magnani , ChengXiang Zhai

Large-scale contrastive learning models can learn very informative sentence embeddings, but are hard to serve online due to the huge model size. Therefore, they often play the role of "teacher", transferring abilities to small "student"…

Artificial Intelligence · Computer Science 2023-01-31 Chaochen Gao , Xing Wu , Peng Wang , Jue Wang , Liangjun Zang , Zhongyuan Wang , Songlin Hu

Very deep models for speaker recognition (SR) have demonstrated remarkable performance improvement in recent research. However, it is impractical to deploy these models for on-device applications with constrained computational resources. On…

Sound · Computer Science 2022-12-07 Zhiyuan Peng , Xuanji He , Ke Ding , Tan Lee , Guanglu Wan

Deep neural network (DNN) model compression for efficient on-device inference is becoming increasingly important to reduce memory requirements and keep user data on-device. To this end, we propose a novel differentiable k-means clustering…

Machine Learning · Computer Science 2022-02-22 Minsik Cho , Keivan A. Vahid , Saurabh Adya , Mohammad Rastegari

Despite the deep neural networks (DNN) has achieved excellent performance in image classification researches, the training of DNNs needs a large of clean data with accurate annotations. The collect of a dataset is easy, but it is difficult…

Computer Vision and Pattern Recognition · Computer Science 2019-08-19 Qian Zhang , Feifei Lee , Ya-Gang Wang , Qiu Chen

Knowledge Distillation (KD) has developed extensively and boosted various tasks. The classical KD method adds the KD loss to the original cross-entropy (CE) loss. We try to decompose the KD loss to explore its relation with the CE loss.…

Computer Vision and Pattern Recognition · Computer Science 2022-08-23 Zhendong Yang , Zhe Li , Yuan Gong , Tianke Zhang , Shanshan Lao , Chun Yuan , Yu Li

Many policy optimization approaches in reinforcement learning incorporate a Kullback-Leilbler (KL) divergence to the previous policy, to prevent the policy from changing too quickly. This idea was initially proposed in a seminal paper on…

Machine Learning · Computer Science 2024-03-19 Lingwei Zhu , Zheng Chen , Matthew Schlegel , Martha White

The deepening penetration of renewable resources into power systems entails great difficulties that have not been surmounted satisfactorily. An issue that merits special attention is the short-term planning of power systems under net load…

Optimization and Control · Mathematics 2020-12-15 Ogun Yurdakul , Fikret Sivrikaya , Sahin Albayrak

As a distributed learning paradigm, Federated Learning (FL) faces the communication bottleneck issue due to many rounds of model synchronization and aggregation. Heterogeneous data further deteriorates the situation by causing slow…

Machine Learning · Computer Science 2024-05-24 Zhijie Xie , S. H. Song

We derive the Kullback-Leibler divergence for the normal-gamma distribution and show that it is identical to the Bayesian complexity penalty for the univariate general linear model with conjugate priors. Based on this finding, we provide…

Statistics Theory · Mathematics 2016-11-07 Joram Soch , Carsten Allefeld

Diffusion bridges are a promising class of deep-learning methods for sampling from unnormalized distributions. Recent works show that the Log Variance (LV) loss consistently outperforms the reverse Kullback-Leibler (rKL) loss when using the…

Machine Learning · Computer Science 2025-11-12 Sebastian Sanokowski , Lukas Gruber , Christoph Bartmann , Sepp Hochreiter , Sebastian Lehner

Knowledge distillation typically minimizes the Kullback-Leibler (KL) divergence between teacher and student logits. However, optimizing the KL divergence can be challenging for the student and often leads to sub-optimal solutions. We…

Computer Vision and Pattern Recognition · Computer Science 2025-06-17 Yuchen Guan , Runxi Cheng , Kang Liu , Chun Yuan