Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,695 papers · 148 categories

Trend · papers per month

178356534712 · Jun 202019922001200920172026
48 results for Deep Energy-Based Policies

PQR estimates reward functions from actions and states without assuming state-only rewards.

problem Estimating reward functions from actions and states without state-only assumptions.
method Deep learning approach that sequentially estimates policy, Q-function, and reward.
result PQR uniquely recovers true reward with known transitions and bounds error with unknown transitions.

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.

A new method for learning policies from demonstrations without reinforcement.

problem Learning policies from demonstrations without access to reinforcement signals.
method Energy-based distribution matching (EDM) to learn policy parameters and state marginals.
result EDM yields consistent performance gains over existing algorithms for strictly batch imitation learning.

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.

Model-free deep reinforcement learning has been shown to exhibit good performance in domains ranging from video games to simulated robotic manipulation and locomotion. However, model-free methods are known to perform poorly when the interaction time with the environment is limited, as is the case for most real-world ro…

2018-03-19abs ↗pdf ↗

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.

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.

ADAC uses analogous policies to improve RL exploration without sacrificing stability.

problem Improving RL exploration without compromising stability and expressiveness.
method Disentangled actor-critic approach with analogous pairs of actors and critics.
result Empirical evaluation shows ADAC outperforms alternatives in challenging exploration tasks.

This paper shows ARMs and EBMs are equivalent, revealing ARM lookahead capabilities.

problem Understanding the lookahead capabilities of next-token prediction models.
method Unified view of ARMs and EBMs, establishing a bijection and deriving equivalence.
result ARMs and EBMs are equivalent, revealing ARM lookahead capabilities.

This paper introduces a new neural ODE model for continuous-time sequence generation.

problem Representing and predicting continuous-time sequences with high accuracy.
method A neural emission model and neural ODE define the latent state evolution, with an Energy-based model for prior distribution.
result The model outperforms existing methods in various tasks, including long-horizon predictions.

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.

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.

In this paper, we attack the anomaly detection problem by directly modeling the data distribution with deep architectures. We propose deep structured energy based models (DSEBMs), where the energy function is the output of a deterministic deep neural network with structure. We develop novel model architectures to integ…

2016-05-25abs ↗pdf ↗

We propose a number of new algorithms for learning deep energy models and demonstrate their properties. We show that our SteinCD performs well in term of test likelihood, while SteinGAN performs well in terms of generating realistic looking images. Our results suggest promising directions for learning better models by …

2017-07-04abs ↗pdf ↗

Deep structured-prediction energy-based models combine the expressive power of learned representations and the ability of embedding knowledge about the task at hand into the system. A common way to learn parameters of such models consists in a multistage procedure where different combinations of components are trained …

2019-02-28abs ↗pdf ↗

ECBMs unify concept-based interpretations in deep learning models.

problem Suboptimal final accuracy and lack of concept interaction and conditional dependencies.
method ECBMs use a set of neural networks to define joint energy, enabling concept correction and conditional dependency quantification.
result ECBMs achieve higher accuracy and richer concept interpretations compared to state-of-the-art methods.

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.

Probabilistic SR method speeds up high-fidelity simulations with reliable uncertainty estimates.

problem Lack of reliable uncertainty quantification in deep-learning based SR methods.
method Statistical Finite Element Method and energy-based generative modeling.
result Efficient high-resolution predictions with inherent uncertainty estimates.

Stochastic defense improves natural classifiers against adversarial attacks.

problem Vulnerability of deep networks to adversarial attacks.
method Long-run MCMC sampling with Energy-Based Model for adversarial purification.
result Balancing memoryless and metastable behavior leads to effective purification and robust classification.

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.

New model improves transfer learning and semi-supervised learning.

problem Improving transfer learning and semi-supervised learning performance.
method Developed a new conditional energy-based model (ICE-BeeM) based on nonlinear ICA.
result Identifiable representations learned by ICE-BeeM improve performance in transfer learning and semi-supervised learning 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.

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.

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…

2019-10-28abs ↗pdf ↗

P-OCS detects OOD samples in a low-dimensional subspace, outperforming existing methods.

problem Efficient OOD detection for deep learning models in open-world environments.
method P-OCS operates in the orthogonal complement of the principal subspace, applying a single projected perturbation.
result P-OCS achieves state-of-the-art OOD detection with negligible computational cost and without requiring model retraining.

We study the problem of learning associative memory -- a system which is able to retrieve a remembered pattern based on its distorted or incomplete version. Attractor networks provide a sound model of associative memory: patterns are stored as attractors of the network dynamics and associative retrieval is performed by…

2019-10-07abs ↗pdf ↗

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.

Paper proposes an alternative to set losses for predicting unordered variables without imposing structure.

problem Learning unordered variables with unknown interrelations without imposing structure.
method Viewing set prediction as conditional density estimation and using deep energy-based models with gradient-guided sampling.
result Empirically demonstrates capability to learn multi-modal densities and produce different plausible predictions.

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.

We study the cross-entropy method (CEM) for the non-convex optimization of a continuous and parameterized objective function and introduce a differentiable variant that enables us to differentiate the output of CEM with respect to the objective function's parameters. In the machine learning setting this brings CEM insi…

2019-09-27abs ↗pdf ↗

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.

Unified framework for OOD detection using class ratio estimation.

problem Density-based OOD detection is unreliable for OOD images.
method Unified framework that builds energy-based models and employs differing base distributions, directly estimating the density ratio through class ratio estimation.
result Competitive results on OOD image problems compared to recent work.

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.