Improved exploration in cooperative multi-agent reinforcement learning.
problem Limited expressiveness of Gaussian policies in DecSPG hinders effective exploration.
method Proposes decentralized diffusion policy learning (DDPL) with denoising diffusion probabilistic models.
result Consistently improved performance on various MARL benchmarks.
New algorithms improve contextual bandits with neural networks and energy models.
problem Inefficient exploration in non-linear models for contextual bandits.
method Maximum entropy exploration using neural networks and energy models.
result Both techniques outperform standard algorithms, with energy models best overall.
Graph Energy Matching improves generation quality for molecular graphs.
problem Discrete energy-based models struggle with efficient and high-quality sampling for graph generation.
method Inspired by transport-map optimization, Graph Energy Matching learns a permutation-invariant potential energy to guide sampling.
result GEM matches or surpasses discrete diffusion baselines on molecular graph benchmarks.
EBMs improve sample efficiency and generalization in RL.
problem Improving sample efficiency and generalization in reinforcement learning.
method Developed an online algorithm to train EBMs for model-based planning, leveraging their ability to infer intermediate states.
result EBMs lead to significantly better online learning and state space planning compared to feed-forward networks.
ScoreGrad predicts multivariate time series with energy-based models, achieving state-of-the-art results.
problem Predicting multivariate time series with generative models while considering noise and distribution.
method ScoreGrad uses continuous energy-based generative models with a feature extraction and score matching module.
result ScoreGrad achieves state-of-the-art results on six real-world datasets.
3D object detection improved using energy-based models.
problem Accurate 3D object detection in cluttered environments from sparse LiDAR data.
method Designing a differentiable pooling operator for 3D bounding boxes integrated into a state-of-the-art 3D object detector.
result Our approach consistently outperforms the SA-SSD baseline across all 3DOD metrics on the KITTI dataset.
A deep learning method solves nonlinear filtering problems efficiently.
problem Nonlinear filtering problem
method Deep splitting method combined with energy-based neural network approximation
result Computational efficiency and performance comparable to Kalman and bootstrap filters
Unified model explains AT's generative ability.
problem Understanding the generative ability of AT.
method Contrastive Energy-based Models (CEM).
result Improved sample quality in supervised and unsupervised learning.
Energy Transformer integrates attention, energy models, and associative memory.
problem Lack of clear theoretical foundations in attention mechanisms and straightforward design of energy functions in energy-based models.
method Proposes Energy Transformer, a sequence of attention layers with a specifically engineered energy function.
result Obtained strong results on graph anomaly detection and classification tasks.
New method improves sampling from noisy energy models.
problem Training and sampling challenges in Energy-Based Models.
method Pseudo-Gibbs sampling with moment matching.
result Effective sampling from clean model using noisy DSM-trained model.
EERF improves supervised learning by using data-dependent random features.
problem Improving generalization in supervised learning with fewer random features.
method EERF algorithm based on a data-dependent score function.
result EERF requires fewer random features to achieve a certain generalization error.
Introduces Causal Energy Minimization to understand Transformer layers.
problem Empirical parameterization of Transformer blocks remains largely unexplored.
method Causal Energy Minimization framework that recasts Transformer layers as optimization steps on conditional energy functions.
result Identifies design space for Transformer layers including weight sharing and energy-based interpretations.
The paper develops models to understand sensory coding and cortical topography.
problem Understanding how visual cortical areas' receptive fields and topographic maps relate to environmental statistical structure.
method Energy-based models applied to probability density estimation, constrained by biological constraints.
result The models qualitatively reproduce receptive field and map properties found in vivo.
Energy Matching unifies flow matching and energy-based models for generative modeling.
problem Inability of flow-based models to integrate partial observations and priors.
method Energy Matching framework that integrates flow matching and energy-based models.
result Substantially outperforms existing EBMs on CIFAR-10 and ImageNet generation.
EB-GFN models discrete data with amortized MCMC sampling.
problem Probabilistic modeling of high-dimensional discrete data.
method EB-GFN combines GFlowNets with energy-based models for efficient sampling.
result EB-GFN effectively models various discrete data tasks.
EB-RANSAC uses energy-based model for robust estimation without complex sampling.
problem Robust estimation of parameters in noisy data.
method EB-RANSAC combines RANSAC's sampling scheme with an energy-based model, simplifying the process and reducing hyperparameter requirements.
result EB-RANSAC effectively solves linear regression and maximum likelihood estimation problems.
Paper optimizes energy-based controller for swinging up a pendulum using entropy search.
problem Finding optimal parameters for energy-based controllers is hard.
method Bayesian optimization (Entropy Search) applied to energy-based controller design.
result Optimal controller improves performance of a swinging pendulum.
New method improves EBMs for regression tasks.
problem Training EBMs for regression is challenging.
method Proposed a simple yet effective extension of noise contrastive estimation.
result Our method achieves state-of-the-art performance on 1D regression and object detection.
Reinterprets classifiers as energy-based models for joint distributions.
problem Improving classifier performance and calibration.
method Interprets discriminative classifiers as energy-based models, trains on unlabeled data, and improves model quality.
result Improves calibration, robustness, and out-of-distribution detection.
Paper proposes CoopFlow, a two-flow generator for energy-based models.
problem Training energy-based models with Langevin flow and normalizing flow.
method CoopFlow trains an energy-based model using a normalizing flow initialization and a short-run Langevin flow revision.
result CoopFlow converges to a moment matching estimator and synthesizes realistic images.
Paper introduces a new method to improve GANs by leveraging the discriminator's energy.
problem Improving the quality of generated samples in GANs.
method Discriminator Contrastive Divergence (DCD) method.
result Significant improvement in generation quality on synthetic and real-world data.
EB-SeqGANs use energy-based models for better recommendation.
problem Creating accurate and efficient mappings for new item recommendations.
method EB-SeqGANs learn a generative model for user-preferred item sequences, interpreting the energy function as a feature function.
result EB-SeqGANs can be seen as a form of maximum-entropy imitation learning.
Versatile model for High Energy Physics events.
problem Modeling complex interactions in high-energy physics data.
method Energy-based probabilistic model with multi-purpose architecture.
result Achieves success in diverse applications like simulation, anomaly detection, and particle identification.
The paper controls complex systems using energy-based methods.
problem Controlling nonlinear infinite-dimensional systems with dissipation.
method Energy-based control using Casimir functionals and energy balancing.
result Demonstrated control of a nonlinear Euler-Bernoulli beam.
A new method combines energy-based models and entropy-regularized optimal transport.
problem Combining energy-based models and optimal transport for generative modeling.
method Energy-guided Entropic Neural Optimal Transport (E-ENT)
result Proves generalization bounds and validates scalability in image translation.
A method to automatically learn proposal distributions for energy-based regression models.
problem Manual design and initial estimate of proposal distributions for energy-based regression models.
method Introduces a method to learn an effective proposal distribution automatically, parameterized by a separate network head, and derives a unified training objective to minimize KL divergence and negative log-likelihood.
result Consistently outperforms conventional MDN training on four real-world regression tasks within computer vision.
Proposes Learnergy, a Python framework for energy-based machine learning.
problem Lack of research and implementations around energy-based systems.
method Built upon PyTorch, Learnergy provides a more friendly environment and faster prototyping.
result Learnergy speeds up computational time using CUDA.
New method learns latent energy models using particle algorithms.
problem Learning latent variable models with energy priors.
method Continuous-time SDEs for MMLE, particle-based discretization.
result Practical algorithm converges to solve MMLE problem.
BiDVL improves EBLVMs for visual tasks by optimizing two variational distributions.
problem Training EBLVMs is challenging due to intractable distributions.
method Bi-level doubly variational learning with two tractable distributions.
result BiDVL achieves impressive image generation and reconstruction performance.
A new loss function ED simplifies training energy-based models without scores.
problem Training energy-based models is computationally expensive.
method Energy Discrepancy (ED) loss function that does not rely on scores or MCMC.
result ED effectively interpolates between score matching and negative log-likelihood.
CEBMs learn flexible latent mappings from data.
problem Learning flexible latent mappings from data.
method CEBMs decompose joint density into tractable posterior over latent variables.
result CEBMs achieve competitive results in image modeling and latent space predictive power.
EBPs model exchangeable data with flexible distributions.
problem Current energy-based models restrict set cardinality and limited distribution forms.
method Introduced Energy-Based Processes (EBPs) that extend energy models to exchangeable data with neural network parameterizations.
result EBPs can express more flexible distributions over sets without cardinality restrictions.
A new method learns hierarchical EBM models with diffusion schemes.
problem Challenges in learning EBM models with multi-modal distributions.
method Proposes a diffusion probabilistic scheme to learn EBM models in hierarchical latent spaces.
result Demonstrates superior performance on various tasks with diffusion-learned EBM.
A new approach to distill unnormalized EBM for energy-based seq2seq models.
problem Training unnormalized EBM for energy-based seq2seq models is challenging.
method Relating the problem to distributional RL, proposing a general distillation approach.
result General approach applicable to any sequential EBM, illustrated on GAM experiments.
New sampler tackles complex discrete energy landscapes efficiently.
problem Stagnation in gradient-based discrete samplers for non-convex settings.
method DREXEL sampler with Replica Exchange and Adjusted Metropolis.
result Proves samplers satisfy detailed balance and converge to target distribution.
Improves sample quality of generative models using energy-based methods.
problem Low sample quality in generative models.
method Constructs an energy function on latent space, trains an energy-based model, and generates improved samples.
result Significant improvement in sample quality with minimal computational overhead.
EBR improves NMT by re-ranking samples drawn from MLE-trained models.
problem Discrepancy between MLE and BLEU score in neural machine translation.
method Train an energy-based model to mimic BLEU score, then use it for re-ranking.
result EBR consistently improves NMT performance by +4 BLEU points on IWSLT'14 German-English.
Bidirectional bounds stabilize training of energy-based models.
problem Training energy-based models is difficult and prone to instability.
method Propose bidirectional bounds linking to gradient penalty and Jacobi-determinant estimator.
result Significant stabilization and high-quality density estimation achieved.
Paper trains two models to improve synthesis quality and unsupervised learning.
problem Improving synthesis quality and unsupervised learning.
method Joint training of an energy-based model and a flow-based model using adversarial value function.
result Significant improvement in synthesis quality of the flow model.
This paper improves image generation models using a multi-grid method.
problem Improving image generation models.
method A multi-grid method for learning energy-based generative ConvNet models.
result The multi-grid method outperforms traditional models.
New method trains energy-based models faster and more stably.
problem Training efficiency and stability of energy-based models.
method EBFlow with score-matching objectives.
result EBFlow achieves significant speedup and better performance.
Proposes a neural generator network for efficient energy-based model learning.
problem Challenges in maximum likelihood estimation of energy-based models.
method Uses a neural generator network to approximate the log-likelihood gradient and maximizes entropy of generated samples.
result Generates sharp images with competitive Inception and FID scores, and is robust to mode collapse.
Energy-based model learns cost functions from expert demonstrations for optimal control.
problem Learning unknown cost functions from expert demonstrations for optimal control.
method Maximum likelihood estimation via analysis by synthesis, combining Langevin dynamics with optimization and cooperative learning.
result The method can learn suitable cost functions for optimal control tasks.
RNE provides a flexible framework for diffusion models, enabling inference-time control and energy-based training.
problem Insufficient knowledge of marginal densities in diffusion models.
method Introduces Radon-Nikodym Estimator (RNE) to reveal the connection between marginal densities and transition kernels.
result RNE delivers strong results in inference-time control and energy-based diffusion training.
The paper explores a non-convergent MCMC method for EBM learning.
problem Learning energy-based models using traditional methods is challenging.
method The paper uses a non-convergent, non-mixing, and non-persistent short-run MCMC to learn EBM parameters.
result The learned short-run MCMC can generate realistic images and reconstruct/interpolate between images.
This paper prioritizes experience replay in robotics using energy-based principles.
problem Randomly replaying experience in HER leads to inefficient learning.
method Developed an energy-based framework to prioritize hindsight experience in robotic manipulation tasks.
result EBP outperforms state-of-the-art approaches in robotic manipulation tasks.
Unified framework for training generator, energy model, and inference model.
problem Training of generator, energy model, and inference model in a unified probabilistic formulation.
method Divergence Triangle framework integrating variational learning, adversarial learning, wake-sleep algorithm, and contrastive divergence.
result Unified training of generator, energy model, and inference model without costly Markov chain Monte Carlo methods.
Efficiently samples and learns densities with symmetries using equivariant methods.
problem Efficiently sampling and learning densities with symmetries.
method Equivariant Stein Variational Gradient Descent (SVGD) and equivariant energy based models.
result Improves and scales up training of energy based models.