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

3076149211,228 · Jun 202019922001200920172026
48 results for energy methods

Investigations have been performed into using clustering methods in data mining time-series data from smart meters. The problem is to identify patterns and trends in energy usage profiles of commercial and industrial customers over 24-hour periods, and group similar profiles. We tested our method on energy usage data p…

2016-03-24abs ↗pdf ↗

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.

Paper benchmarks and customizes energy forecasting methods.

problem Energy forecasting challenges and differences from traditional time series.
method Collected large-scale load datasets and renewable energy datasets. Developed feature engineering and customized loss functions.
result Comprehensive evaluation of 21 forecasting methods in energy datasets.

Structured Prediction Energy Networks (SPENs) are a simple, yet expressive family of structured prediction models (Belanger and McCallum, 2016). An energy function over candidate structured outputs is given by a deep network, and predictions are formed by gradient-based optimization. This paper presents end-to-end lear…

2017-03-16abs ↗pdf ↗

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 rr.
result VAV method achieves faster convergence and superior stability with larger learning rates.

New method uses neural networks to improve free energy estimation.

problem Estimating free energy differences using FEP is limited by insufficient overlap between distributions.
method Developed a neural network to parameterize a high-dimensional mapping in configuration space.
result Demonstrated substantial variance reduction in free energy estimates.

Current state-of-the-art discrete optimization methods struggle behind when it comes to challenging contrast-enhancing discrete energies (i.e., favoring different labels for neighboring variables). This work suggests a multiscale approach for these challenging problems. Deriving an algebraic representation allows us to…

2012-10-26abs ↗pdf ↗

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.

Proves energy expression on Poincaré-Einstein spaces.

problem Computing renormalized Yang-Mills energy on Poincaré-Einstein manifolds.
method Generalizes Chang-Qing-Yang method for renormalized volumes and uses scattering theory for Schrödinger operators.
result Agrees with anomaly boundary integrand in seven dimensions.

The present chapter gives an overview on results for discrete knot energies. These discrete energies are designed to make swift numerical computations and thus open the field to computational methods. Additionally, they provide an independent, geometrically pleasing and consistent discrete model that behaves similarly …

2016-03-08abs ↗pdf ↗

Quantum vacuum energy (Casimir energy) is reviewed for a mathematical audience as a topic in spectral theory. Then some one-dimensional systems are solved exactly, in terms of closed classical paths and periodic orbits. The relations among local spectral densities, energy densities, global eigenvalue densities, and tot…

2007-06-19abs ↗pdf ↗

Extends Penrose's method to null shells with pressure and energy flux.

problem Constructing null thin shells with arbitrary gravitational/matter content.
method Derive locally Lipschitz metric and coordinate transformation.
result Example of null shell with non-trivial energy density, flux, and pressure in Minkowski space.

This work develops machine learning for micromagnetic energy minimization.

problem Minimizing Gibbs free energy in full 3D micromagnetic simulations.
method Advanced machine learning techniques, including Physics-Informed Neural Networks (PINNs) and Extreme Learning Machines (ELMs), with reformulated bounds and optimization schemes.
result Competitive performance of machine learning methods compared to traditional numerical approaches.

The paper finds curves minimizing elastic energy pinned at endpoints.

problem Finding curves that minimize elastic energy with fixed endpoints.
method Applying the shooting method to identify and classify critical points.
result Critical points consist of wavelike elasticae, and minimizers have no loops or interior inflection points.

New method trains deep neural networks for non-interacting kinetic-energy functionals in DFT.

problem Lack of exact relationship between electron density and non-interacting kinetic energy.
method Variational principle to regularize machine-learned density functionals.
result Excellent results on kinetic-energy functionals for various systems.

The paper improves energy contract pricing models by incorporating jumps and varying parameters.

problem Inaccurate pricing of energy contracts using the Black-Scholes-Merton model.
method Integrates regime switching and time-changed Levy processes with a two-state Markov chain.
result Improved accuracy in pricing energy contracts through a new model.

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.

ShotgunCSP predicts crystal structures using machine learning, achieving high accuracy with minimal computation.

problem Predicting stable or metastable crystal structures of large systems.
method Noniterative screening using transfer learning and generative models.
result ShotgunCSP achieves 93.3% accuracy in benchmark tests with 90 different crystal structures.

A new method using energy distance for ensemble and scenario reduction.

problem Solving complex dynamic and stochastic programs, especially in energy systems.
method Proposes a new method based on energy distance for ensemble and scenario reduction.
result Reduced scenario sets exhibit better statistical properties for energy distance than Wasserstein distance.

Machine learning software accounts for a significant amount of energy consumed in data centers. These algorithms are usually optimized towards predictive performance, i.e. accuracy, and scalability. This is the case of data stream mining algorithms. Although these algorithms are adaptive to the incoming data, they have…

2018-08-03abs ↗pdf ↗

Study lower bounds on modified K-energy on Fano manifolds with Kähler-Ricci solitons.

problem Lower boundedness of modified K-energy on Fano manifolds.
method Extend Tosatti's method to study Fano manifolds with Kähler-Ricci solitons.
result Establish lower bounds on modified K-energy for Kähler-Ricci solitons.

Graph Laplacians adapt to different manifold dimensions, while Dirichlet energies converge to a tensorized Dirichlet energy.

problem Understanding machine learning methods for data with varying intrinsic dimensions.
method Γ-convergence of graph Dirichlet energies and spectral convergence of graph Laplacians on intersecting manifolds of varying dimensions.
result Normalized Dirichlet energy converges to a tensorized Dirichlet energy that adapts to all dimensions simultaneously.

In Hindsight Experience Replay (HER), a reinforcement learning agent is trained by treating whatever it has achieved as virtual goals. However, in previous work, the experience was replayed at random, without considering which episode might be the most valuable for learning. In this paper, we develop an energy-based fr…

2018-10-02abs ↗pdf ↗

This paper analyzes energy and carbon footprints in distributed and federated learning.

problem High energy costs and carbon emissions in centralized AI methods.
method A novel framework quantifying energy and carbon footprints in vanilla and consensus-based FL methods.
result Optimal bounds and operational points for green FL designs and sustainability assessment.

A neural network model minimizes region-based free energy for faster inference in MRFs.

problem Efficient inference in complex Markov random fields (MRFs).
method Region-based Energy Neural Network (RENN) that directly minimizes region-based free energy.
result RENN outperforms other methods in marginal distribution estimation, partition function estimation, and MRF learning.

Improves energy efficiency of neuromorphic hardware by optimizing memory organization and encoding schemes.

problem Energy inefficiency in neuromorphic hardware, especially in digital accelerators.
method Synthesized controller and memory for different encoding schemes, introduced functional encoding for structured connectivity.
result Functional encoding offers a 58% reduction in energy for weight updates in convolutional layers.

Paper proposes a new method to optimize feature coordinates for better image classification.

problem Improving feature extraction for better machine learning classification.
method Mutual-energy inner product optimization method.
result The method enhances low-frequency features and suppresses high-frequency noise, leading to better classification results.

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.