Learning energy-based model with variational auto-encoder as amortized sampler
Due to the intractable partition function, training energy-based models (EBMs) by maximum
likelihood requires Markov chain Monte Carlo (MCMC) sampling to approximate the …
likelihood requires Markov chain Monte Carlo (MCMC) sampling to approximate the …
SDDM: score-decomposed diffusion models on manifolds for unpaired image-to-image translation
Recent score-based diffusion models (SBDMs) show promising results in unpaired image-to-
image translation (I2I). However, existing methods, either energy-based or statistically …
image translation (I2I). However, existing methods, either energy-based or statistically …
Energy-guided entropic neural optimal transport
Energy-based models (EBMs) are known in the Machine Learning community for decades.
Since the seminal works devoted to EBMs dating back to the noughties, there have been a …
Since the seminal works devoted to EBMs dating back to the noughties, there have been a …
SAC: Energy-Based Reinforcement Learning with Stein Soft Actor Critic
Learning expressive stochastic policies instead of deterministic ones has been proposed to
achieve better stability, sample complexity, and robustness. Notably, in Maximum Entropy …
achieve better stability, sample complexity, and robustness. Notably, in Maximum Entropy …
Rethinking cross-domain semantic relation for few-shot image generation
Y Gou, M Li, Y Lv, Y Zhang, Y Xing, Y He - Applied Intelligence, 2023 - Springer
Abstract Training well-performing Generative Adversarial Networks (GANs) with limited data
has always been challenging. Existing methods either require sufficient data (over 100 …
has always been challenging. Existing methods either require sufficient data (over 100 …
Cooperative training of fast thinking initializer and slow thinking solver for conditional learning
This paper studies the problem of learning the conditional distribution of a high-dimensional
output given an input, where the output and input may belong to two different domains, eg …
output given an input, where the output and input may belong to two different domains, eg …
CoopInit: Initializing generative adversarial networks via cooperative learning
Numerous research efforts have been made to stabilize the training of the Generative
Adversarial Networks (GANs), such as through regularization and architecture design …
Adversarial Networks (GANs), such as through regularization and architecture design …
Energy-based continuous inverse optimal control
The problem of continuous inverse optimal control (over finite time horizon) is to learn the
unknown cost function over the sequence of continuous control variables from expert …
unknown cost function over the sequence of continuous control variables from expert …
ASCFL: Accurate and speedy semi-supervised clustering federated learning
J He, B Gong, J Yang, H Wang, P Xu… - Tsinghua Science and …, 2023 - ieeexplore.ieee.org
The influence of non-Independent Identically Distribution (non-IID) data on Federated
Learning (FL) has been a serious concern. Clustered Federated Learning (CFL) is an …
Learning (FL) has been a serious concern. Clustered Federated Learning (CFL) is an …
Learning proposals for practical energy-based regression
FK Gustafsson, M Danelljan… - … Conference on Artificial …, 2022 - proceedings.mlr.press
Energy-based models (EBMs) have experienced a resurgence within machine learning in
recent years, including as a promising alternative for probabilistic regression. However …
recent years, including as a promising alternative for probabilistic regression. However …