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.
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.
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.
Proposes a new learning method for RBMs that combines strengths of forward and reverse KLD.
problem Underfitting and mode-collapse issues in RBM learning.
method Ratio divergence learning using target energy.
result Significantly outperforms other learning methods in energy function fitting, mode-covering, and stability.
Future autonomous systems need reliable world models and complex action sequences.
problem Current automated systems lack reliable world models and complex action sequences.
method Introduce energy-based and latent variable models combined in a hierarchical joint embedding predictive architecture (H-JEPA).
result Combining energy-based and latent variable models in H-JEPA can lead to reliable world models and complex action sequences.
VAV method optimizes learning rate for faster, stable SGD convergence.
problem Optimizing learning rate for efficient and stable machine learning models.
method Energy-based self-adaptive learning rate with auxiliary variable r. result VAV method achieves faster convergence and superior stability with larger learning rates.
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.
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.
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.
Machine learning models accurately predict molecular magnetic anisotropy tensors.
problem Accurately modeling molecular magnetic anisotropy tensors.
method Gaussian-moment neural-network approach for machine learning.
result Achieved accuracy of 0.3--0.4 cm−1 for magnetic anisotropy tensor predictions. A new sampler and temperature estimation method enable efficient learning of Boltzmann Machines.
problem Efficient learning of Boltzmann Machines (BMs) is challenging due to high training costs and difficulty in parallelization.
method Proposed a new Boltzmann sampler (Langevin SB, LSB) and an efficient method (Conditional Expectation Matching, CEM) for estimating inverse temperature.
result Established an efficient learning framework (Sampler-Adaptive Learning, SAL) for BMs with greater expressive power than Restricted Boltzmann Machines (RBMs).
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.
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.
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.
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.
We compare and contrast the statistical physics and quantum physics inspired approaches for unsupervised generative modeling of classical data. The two approaches represent probabilities of observed data using energy-based models and quantum states respectively.Classical and quantum information patterns of the target d…
In the past decade, the field of quantum machine learning has drawn significant attention due to the prospect of bringing genuine computational advantages to now widespread algorithmic methods. However, not all domains of machine learning have benefited equally from quantum enhancements. Notably, deep learning and rein…
This paper proposes a multi-grid method for learning energy-based generative ConvNet models of images. For each grid, we learn an energy-based probabilistic model where the energy function is defined by a bottom-up convolutional neural network (ConvNet or CNN). Learning such a model requires generating synthesized exam…
New SMC samplers improve stochastic optimisation efficiency.
problem Optimizing functions with intractable gradients in machine learning and statistics.
method Sequential Monte Carlo (SMC) samplers for stochastic optimisation.
result Significant computational gains achieved with SMC approximations.
This paper studies a training method to jointly estimate an energy-based model and a flow-based model, in which the two models are iteratively updated based on a shared adversarial value function. This joint training method has the following traits. (1) The update of the energy-based model is based on noise contrastive…
Unified view of contrastive and supervised learning improves model performance.
problem Improving model performance in classification, robustness, and detection.
method Hybrid discriminative-generative training of energy-based models.
result Improved performance on classification, robustness, out-of-distribution detection, and calibration.
Paper proposes a method to improve MCMC sampling for energy-based models.
problem MCMC sampling of energy-based models is often not mixing in high-dimensional data.
method Proposes using a flow-based model as a backbone to correct the energy-based model, enabling mixing in latent space.
result MCMC sampling of the corrected EBM in the latent space mixes well and traverses modes in the data space.
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.
EBMs improve continual learning without external memory or regularization.
problem Improving continual learning without external memory or regularization.
method Energy-Based Models with contrastive divergence training objective.
result EBMs outperform baseline methods on various benchmarks.
Neural density estimators are flexible families of parametric models which have seen widespread use in unsupervised machine learning in recent years. Maximum-likelihood training typically dictates that these models be constrained to specify an explicit density. However, this limitation can be overcome by instead using …
Harmoniums model multiple time-to-event variables in survival analysis.
problem Survival analysis with multiple, independently censored time-to-event variables and missing observations.
method Energy-based approach with bi-partite structure (harmoniums).
result Harmoniums capture non-linear patterns between time recordings.
Energy-based models can generate complex images by combining simpler concepts.
problem Generating natural images that satisfy complex logical combinations of concepts.
method Energy-based models combine probability distributions of simpler concepts to generate compositions.
result Energy-based models can generate images that satisfy conjunctions, disjunctions, and negations of concepts.
This paper tackles sampling issues in latent space EBMs by introducing diffusion-based amortization.
problem Degenerate MCMC sampling quality hinders latent space EBM learning and generation quality.
method Introduces diffusion-based amortization for long-run MCMC sampling.
result The learned amortization of MCMC is a valid long-run MCMC sampler.
Traditional energy-based learning models associate a single energy metric to each configuration of variables involved in the underlying optimization process. Such models associate the lowest energy state to the optimal configuration of variables under consideration, and are thus inherently dissipative. In this paper we…
EMIX minimizes surprise in multi-agent reinforcement learning.
problem Surprise and approximation bias in multi-agent reinforcement learning.
method Energy-based MIXer (EMIX) for minimizing surprise across multiple agents.
result EMIX demonstrates consistent stable performance in challenging StarCraft II scenarios.
This paper proposes the divergence triangle as a framework for joint training of generator model, energy-based model and inference model. The divergence triangle is a compact and symmetric (anti-symmetric) objective function that seamlessly integrates variational learning, adversarial learning, wake-sleep algorithm, an…
Energy-based diffusion models improve molecular sampling and simulation.
problem Inconsistency between diffusion model scores and equilibrium distributions.
method Fokker-Planck regularization to enforce consistency.
result Improved consistency and efficient sampling of biomolecular systems.
Probabilistic models can be defined by an energy function, where the probability of each state is proportional to the exponential of the state's negative energy. This paper considers a generalization of energy-based models in which the probability of a state is proportional to an arbitrary positive, strictly decreasing…
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.
We propose to reinterpret a standard discriminative classifier of p(y|x) as an energy based model for the joint distribution p(x,y). In this setting, the standard class probabilities can be easily computed as well as unnormalized values of p(x) and p(x|y). Within this framework, standard discriminative architectures ma…
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.
This paper proposes a method to train energy-based models using variational auto-encoders for efficient sampling.
problem Training energy-based models by maximum likelihood is challenging due to intractable partition functions and difficult sampling from the model distribution.
method The authors propose using a variational auto-encoder to initialize finite-step MCMC sampling, specifically Langevin dynamics, to train the energy-based model.
result The proposed method enables training energy-based models using maximum likelihood, generating samples comparable to GANs and EBMs.
GEBM combines energy function and base distribution for better generative modeling.
problem Improving generative models with better quality samples and performance.
method Alternating training between energy function and base distribution, using MCMC for sampling.
result GEBMs produce higher quality samples and better performance than GANs.
Persistently trained EBMs generate images and estimate complex densities.
problem Challenges in ML learning for energy-based models, especially non-convergence of MCMC.
method Introduce diffusion data, learn a joint EBM through persistent training with enhanced sampling.
result First simultaneous achievement of stability, post-training image generation, and superior out-of-distribution detection for image data.
Paper proposes an alternative to MCMC for sampling in energy-based models.
problem Difficulty in generating samples from the current energy function in contrastive approaches.
method Viewing the evolution of the modeling distribution as the evolution of the energy function and samples from this distribution along a time-dependent vector field.
result The proposed method efficiently matches the current distribution in a finite time, unlike MCMC.
Recommender systems aim to find an accurate and efficient mapping from historic data of user-preferred items to a new item that is to be liked by a user. Towards this goal, energy-based sequence generative adversarial nets (EB-SeqGANs) are adopted for recommendation by learning a generative model for the time series of…
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 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
STANLEY improves sampling for complex data models.
problem Training Energy-Based models with intractable normalizing constants.
method Anisotropic Langevin Dynamics with gradient-informed covariance.
result Geometrically uniformly ergodic Markov Chain for sampling.
A new method to learn EBM in latent space for better data modeling.
problem Efficiently modeling data with complex structures.
method Joint learning of latent space EBM and top-down network using maximum likelihood and MCMC sampling.
result Simple EBM in latent space captures data regularities effectively and performs well in generation and anomaly detection.
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 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 demonstrations. In this article, we study this fundamental problem in the framework of energy-based model, where the observed expert trajectori…
EBIL simplifies IL by estimating expert energy as reward, achieving effective performance.
problem Recovering optimal policy from expert demonstrations without reward signals.
method EBIL uses a two-stage solution: first estimating expert energy as reward, then learning policy.
result EBIL achieves effective performance and interpretable reward signals.