Product
Help
Pricing
About
Jobs
Log in
Get started
Keyword
Add to collection
reverse KL divergence
Description:
A directed measure of difference between probability distributions, calculated using the Kullback–Leibler divergence with its arguments reversed.
Related topics:
Generative Adversarial Networks and Image Synthesis (15%),
Topic Modeling (14%),
Reinforcement Learning in Robotics (13%),
Gaussian Processes and Bayesian Inference (8%)
OpenAlex ID:
keywords/reverse-kl-divergence
Dual Discriminator Generative Adversarial Nets
2017
·
Nguyen, Tu Dinh
, Le, Trung
, et al.
·
arXiv (Cornell University)
·
386
PDF
Entropy-Aware On-Policy Distillation of Language Models
2026
·
Jin, Woogyeol
, Min, Taywon
, et al.
·
arXiv (Cornell University)
·
189
PDF
Reverse KL-Divergence Training of Prior Networks: Improved Uncertainty and Adversarial Robustness
2019
·
Gales, Mark
, Malinin, Andrey
·
arXiv (Cornell University)
·
188
PDF
Revisiting On-Policy Distillation: Empirical Failure Modes and Simple Fixes
2026
·
Fu, Yuqian
, Huang, Haohuan
, et al.
·
arXiv (Cornell University)
·
172
PDF
Imitation Learning as f-Divergence Minimization
2021
·
Liyiming Ke
, Sanjiban Choudhury
, et al.
·
Springer proceedings in advanced robotics
·
164
PDF
Aligning Language Models with Preferences through f-divergence Minimization
2023
·
Go, Dongyoung
, Korbak, Tomasz
, et al.
·
arXiv (Cornell University)
·
113
PDF
CRISP: Compressed Reasoning via Iterative Self-Policy Distillation
2026
·
Sang, Hejian
, Xu, Yuanda
, et al.
·
arXiv (Cornell University)
·
77
PDF
The Choice of Divergence: A Neglected Key to Mitigating Diversity Collapse in Reinforcement Learning with Verifiable Reward
2026
·
Li, Long
, Zhou, Zhijian
, et al.
·
International Conference on Learning Representations
·
48
PDF
Improved Analysis of Score-based Generative Modeling: User-Friendly Bounds under Minimal Smoothness Assumptions
2022
·
Chen, Hongrui
, Lee, Holden
, et al.
·
arXiv (Cornell University)
·
48
PDF
Gradients should stay on path: better estimators of the reverse- and forward KL divergence for normalizing flows
2022
·
Lorenz Vaitl
, Kim A Nicoli
, et al.
·
Machine Learning Science and Technology
·
48
PDF
RKLD: Reverse KL-Divergence-based Knowledge Distillation for Unlearning Personal Information in Large Language Models
2024
·
Wang, Bichen
, Zi, Yuzhe
, et al.
·
arXiv (Cornell University)
·
45
PDF
Sequential Neural Posterior and Likelihood Approximation
2021
·
Wiqvist, Samuel
, Frellsen, Jes
, et al.
·
arXiv (Cornell University)
·
43
PDF
Improved Training of Generative Adversarial Networks Using Representative Features
2018
·
Bang, Duhyeon
, Shim, Hyunjung
·
arXiv (Cornell University)
·
43
PDF
Video-OPD: Efficient Post-Training of Multimodal Large Language Models for Temporal Video Grounding via On-Policy Distillation
2026
·
Li, Jiaze
, Yin, Hao
, et al.
·
arXiv (Cornell University)
·
42
PDF
ToDi: Token-wise Distillation via Fine-Grained Divergence Control
2025
·
Seongryong Jung
, Suwan Yoon
, et al.
·
Conference on Empirical Methods in Natural Language Processing (EMNLP)
·
42
PDF
FlowRL: Matching Reward Distributions for LLM Reasoning
2026
·
Zhu, Xuekai
, Cheng, Daixuan
, et al.
·
International Conference on Learning Representations
·
38
OPSDL: On-Policy Self-Distillation for Long-Context Language Models
2026
·
Zhang, Xinsen
, Ding, Zhenkai
, et al.
·
arXiv (Cornell University)
·
35
PDF
KL for a KL: On-Policy Distillation with Control Variate Baseline
2026
·
Oh, Minjae
, Song, Sangjun
, et al.
·
arXiv (Cornell University)
·
32
PDF
Direct Preference Knowledge Distillation for Large Language Models
2024
·
Li, Yixing
, Gu, Yuxian
, et al.
·
arXiv (Cornell University)
·
32
PDF
SUMO: Unbiased Estimation of Log Marginal Probability for Latent Variable Models
2020
·
Luo, Yucen
, Beatson, Alex
, et al.
·
arXiv (Cornell University)
·
30
PDF
Learning Interpolations between Boltzmann Densities
2023
·
Máté, Bálint
, Fleuret, François
·
Transactions on machine learning research
·
29
PDF
The residual generator: An improved divergence minimization framework for GAN
2021
·
Aurele Tohokantche Gnanha
, Wenming Cao
, et al.
·
Pattern Recognition
·
29
KL-Regularized Reinforcement Learning is Designed to Mode Collapse
2026
·
GX-Chen, Anthony
, Prakash, Jatin
, et al.
·
International Conference on Learning Representations
·
27
PDF
VLA-OPD: Bridging Offline SFT and Online RL for Vision-Language-Action Models via On-Policy Distillation
2026
·
Zhong, Zhide
, Yan, Haodong
, et al.
·
arXiv (Cornell University)
·
27
PDF
Align-Then-stEer: Adapting the Vision-Language Action Models through Unified Latent Guidance
2026
·
Zhang, Yang
, Wang, Chenwei
, et al.
·
International Conference on Learning Representations
·
26
Show more works
View as search
Works count:
154
Citation count:
2,583
Year
Topic
Type