Improved off-policy training of diffusion samplers

7 February 2024

Nikolay Malkin

Papers citing "Improved off-policy training of diffusion samplers"

50 / 83 papers shown

Title
On scalable and efficient training of diffusion samplers Minkyu Kim Kiyoung Seong Dongyeop Woo SungSoo Ahn Minsu Kim DiffM 103 0 0 26 May 2025
Importance Weighted Score Matching for Diffusion Samplers with Enhanced Mode Coverage Chenguang Wang Xiaoyu Zhang Kaiyuan Cui Weichen Zhao Yongtao Guan Tianshu Yu DiffM 53 0 0 26 May 2025
Loss-Guided Auxiliary Agents for Overcoming Mode Collapse in GFlowNets Idriss Malek Abhijit Sharma Salem Lahlou 68 0 0 21 May 2025
Ergodic Generative Flows Leo Maxime Brunswic Mateo Clemente Rui Heng Yang Adam Sigal Amir Rasouli Yinchuan Li 109 0 0 06 May 2025
THE-SEAN: A Heart Rate Variation-Inspired Temporally High-Order Event-Based Visual Odometry with Self-Supervised Spiking Event Accumulation Networks Chaoran Xiong Litao Wei Kehui Ma Zhen Sun Yan Xiang Zihan Nan Trieu-Kien Truong Ling Pei 87 7 0 07 Mar 2025
Posterior Inference with Diffusion Models for High-dimensional Black-box Optimization Taeyoung Yun Kiyoung Om Jaewoo Lee Sujin Yun Jinkyoo Park 106 2 0 24 Feb 2025
In-Context Parametric Inference: Point or Distribution Estimators? Sarthak Mittal Yoshua Bengio Nikolay Malkin Guillaume Lajoie 105 0 0 17 Feb 2025
From discrete-time policies to continuous-time diffusion samplers: Asymptotic equivalences and faster training Julius Berner Lorenz Richter Marcin Sendera Jarrid Rector-Brooks Nikolay Malkin OffRL 115 8 0 10 Jan 2025
Efficient Diversity-Preserving Diffusion Alignment via Gradient-Informed GFlowNets Zhen Liu Tim Z. Xiao Weiyang Liu Yoshua Bengio Dinghuai Zhang 164 5 0 10 Dec 2024
Action abstractions for amortized sampling Oussama Boussif Léna Néhale Ezzine J. Viviano Michał Koziarski Moksh Jain Nikolay Malkin Emmanuel Bengio Rim Assouel Yoshua Bengio 69 0 0 19 Oct 2024
Training Neural Samplers with Reverse Diffusive KL Divergence Wenlin Chen Jiajun He Mingtian Zhang David Barber José Miguel Hernández-Lobato DiffM 87 7 0 16 Oct 2024
NETS: A Non-Equilibrium Transport Sampler M. S. Albergo Eric Vanden-Eijnden DiffM 102 20 0 03 Oct 2024
Adaptive teachers for amortized samplers Minsu Kim Sanghyeok Choi Taeyoung Yun Emmanuel Bengio Leo Feng Jarrid Rector-Brooks Sungsoo Ahn Jinkyoo Park Nikolay Malkin Yoshua Bengio 438 7 0 02 Oct 2024
MetaGFN: Exploring Distant Modes with Adapted Metadynamics for Continuous GFlowNets Dominic Phillips F. Cipcigan 73 4 0 28 Aug 2024
Can a Bayesian Oracle Prevent Harm from an Agent? Yoshua Bengio Michael K. Cohen Nikolay Malkin Matt MacDermott Damiano Fornasiere Pietro Greiner Younesse Kaddar 84 7 0 09 Aug 2024
Markovian Flow Matching: Accelerating MCMC with Continuous Normalizing Flows A. Cabezas Louis Sharrock Christopher Nemeth 52 3 0 23 May 2024
Variational Bayesian Last Layers James Harrison John Willes Jasper Snoek BDL UQCV 109 31 0 17 Apr 2024
Discrete Probabilistic Inference as Control in Multi-path Environments T. Deleu Padideh Nouri Nikolay Malkin Doina Precup Yoshua Bengio 151 30 0 15 Feb 2024
Improving Gradient-guided Nested Sampling for Posterior Inference Pablo Lemos Nikolay Malkin Will Handley Yoshua Bengio Y. Hezaveh Laurence Perreault Levasseur BDL 83 10 0 06 Dec 2023
Generative Flow Networks as Entropy-Regularized RL D. Tiapkin Nikita Morozov Alexey Naumov Dmitry Vetrov 69 33 0 19 Oct 2023
Learning Energy Decompositions for Partial Inference of GFlowNets Hyosoon Jang Minsu Kim SungSoo Ahn 64 23 0 05 Oct 2023
Learning to Scale Logits for Temperature-Conditional GFlowNets Minsu Kim Joohwan Ko Taeyoung Yun Dinghuai Zhang Ling Pan W. Kim Jinkyoo Park Emmanuel Bengio Yoshua Bengio AI4CE 79 21 0 04 Oct 2023
Local Search GFlowNets Minsu Kim Taeyoung Yun Emmanuel Bengio Dinghuai Zhang Yoshua Bengio SungSoo Ahn Jinkyoo Park 59 37 0 04 Oct 2023
Diffusion Generative Flow Samplers: Improving learning signals through partial trajectory optimization Dinghuai Zhang Ricky Tian Qi Chen Cheng-Hao Liu Aaron C. Courville Yoshua Bengio 63 46 0 04 Oct 2023
Improved sampling via learned diffusions Lorenz Richter Julius Berner DiffM 81 61 0 03 Jul 2023
Thompson sampling for improved exploration in GFlowNets Jarrid Rector-Brooks Kanika Madan Moksh Jain Maksym Korablyov Cheng-Hao Liu Sarath Chandar Nikolay Malkin Yoshua Bengio 65 26 0 30 Jun 2023
Towards Understanding and Improving GFlowNet Training Max W. Shen Emmanuel Bengio Ehsan Hajiramezanali Andreas Loukas Kyunghyun Cho Tommaso Biancalani 43 54 0 11 May 2023
Denoising Diffusion Samplers Francisco Vargas Will Grathwohl Arnaud Doucet DiffM 52 87 0 27 Feb 2023
GFlowNet-EM for learning compositional latent variable models J. E. Hu Nikolay Malkin Moksh Jain Katie Everett Alexandros Graikos Yoshua Bengio CoGe 75 40 0 13 Feb 2023
DynGFN: Towards Bayesian Inference of Gene Regulatory Networks with GFlowNets Lazar Atanackovic Alexander Tong Bo Wang Leo J. Lee Yoshua Bengio Jason S. Hartford BDL 58 24 0 08 Feb 2023
Sample-efficient Multi-objective Molecular Optimization with GFlowNets Yiheng Zhu Jialun Wu Chaowen Hu Jiahuan Yan Chang-Yu Hsieh Tingjun Hou Jian Wu 70 35 0 08 Feb 2023
Better Training of GFlowNets with Local Credit and Incomplete Trajectories L. Pan Nikolay Malkin Dinghuai Zhang Yoshua Bengio 68 68 0 03 Feb 2023
A theory of continuous generative flow networks Salem Lahlou T. Deleu Pablo Lemos Dinghuai Zhang Alexandra Volokhova Alex Hernández-García Léna Néhale Ezzine Yoshua Bengio Nikolay Malkin AI4CE 84 90 0 30 Jan 2023
Learning Interpolations between Boltzmann Densities Bálint Máté Franccois Fleuret 86 28 0 18 Jan 2023
Robust Scheduling with GFlowNets David W. Zhang Corrado Rainone M. Peschl Roberto Bondesan 80 56 0 17 Jan 2023
A-NeSI: A Scalable Approximate Method for Probabilistic Neurosymbolic Inference Emile van Krieken Thiviyan Thanapalasingam Jakub M. Tomczak F. V. Harmelen A. T. Teije 43 38 0 23 Dec 2022
Posterior samples of source galaxies in strong gravitational lenses with score-based priors Alexandre Adam A. Coogan Nikolay Malkin Ronan Legin Laurence Perreault Levasseur Y. Hezaveh Yoshua Bengio DiffM 75 23 0 07 Nov 2022
An optimal control perspective on diffusion-based generative modeling Julius Berner Lorenz Richter Karen Ullrich DiffM 113 92 0 02 Nov 2022
A Variational Perspective on Generative Flow Networks Heiko Zimmermann Fredrik Lindsten Jan-Willem van de Meent C. A. Naesseth 58 35 0 14 Oct 2022
GFlowNets and variational inference Nikolay Malkin Salem Lahlou T. Deleu Xu Ji J. E. Hu Katie Everett Dinghuai Zhang Yoshua Bengio BDL 184 86 0 02 Oct 2022
Learning GFlowNets from partial episodes for improved convergence and stability Kanika Madan Jarrid Rector-Brooks Maksym Korablyov Emmanuel Bengio Moksh Jain A. Nica Tom Bosc Yoshua Bengio Nikolay Malkin 63 98 0 26 Sep 2022
On free energy barriers in Gaussian priors and failure of cold start MCMC for high-dimensional unimodal distributions Afonso S. Bandeira Antoine Maillard Richard Nickl Sven Wang 45 8 0 05 Sep 2022
Convergence of denoising diffusion models under the manifold hypothesis Valentin De Bortoli DiffM 62 168 0 10 Aug 2022
Stochastic Optimal Control for Collective Variable Free Sampling of Molecular Transition Paths Lars Holdijk Yuanqi Du F. Hooft P. Jaini B. Ensing Max Welling 26 27 0 27 Jun 2022
Torsional Diffusion for Molecular Conformer Generation Bowen Jing Gabriele Corso Jeffrey Chang Regina Barzilay Tommi Jaakkola DiffM BDL 91 271 0 01 Jun 2022
Bayesian Structure Learning with Generative Flow Networks T. Deleu António Góis Chris C. Emezue M. Rankawat Simon Lacoste-Julien Stefan Bauer Yoshua Bengio BDL 85 155 0 28 Feb 2022
Generative Flow Networks for Discrete Probabilistic Modeling Dinghuai Zhang Nikolay Malkin Ziqiang Liu Alexandra Volokhova Aaron Courville Yoshua Bengio 52 108 0 03 Feb 2022
Trajectory balance: Improved credit assignment in GFlowNets Nikolay Malkin Moksh Jain Emmanuel Bengio Chen Sun Yoshua Bengio 207 180 0 31 Jan 2022
High-Resolution Image Synthesis with Latent Diffusion Models Robin Rombach A. Blattmann Dominik Lorenz Patrick Esser Bjorn Ommer 3DV 419 15,515 0 20 Dec 2021
Tackling the Generative Learning Trilemma with Denoising Diffusion GANs Zhisheng Xiao Karsten Kreis Arash Vahdat DiffM 98 552 0 15 Dec 2021