Paper proposes new loss functions for training energy networks.
problem Challenges in computing gradients for training energy networks.
method Proposes generalized Fenchel-Young losses for efficient gradient computation.
result Demonstrates the calibration of excess risk for linear-concave energies.
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.
A new method trains discrete EBMs without sampling.
problem Training EBMs on discrete spaces is hard.
method Energy Discrepancy (ED), a contrastive loss.
result ED offers theoretical guarantees for various perturbation types.
Out-of-distribution (OOD) detection approaches usually present special requirements (e.g., hyperparameter validation, collection of outlier data) and produce side effects (e.g., classification accuracy drop, slower energy-inefficient inferences). We argue that these issues are a consequence of the SoftMax loss anisotro…
Study compact Willmore surfaces without complex structure convergence, computing energy loss and geodesic lengths.
problem Compactness of Willmore surfaces without complex structure convergence.
method Compute energy loss in neck and geodesic lengths in Grassmannian G(2,n). result Limit of Gauss map image is a geodesic in G(2,n) with computable length. New theory shows predictive coding makes learning landscape easier to navigate.
problem Understanding the impact of predictive coding's inference procedure on learning efficiency.
method Analyzed the geometry of the energy landscape of deep linear networks, proving many non-strict saddles become strict in the equilibrated energy.
result All highly degenerate (non-strict) saddles of the loss become strict in the equilibrated energy, suggesting a more robust learning landscape.
We consdier in dimension four weakly convergent sequences of approximate biharmonic maos into sphere with bi-tension fields bounded in Lp for some p>1. We prove an energy identity that accounts for the loss of Hessian energies by the sum of Hessian energies over finitely many nontrivial biharmonic maps on $\mathbb…
We use matricial free energy to regularize autoencoders, producing Gaussian-like codes.
problem Generating Gaussian-like codes for autoencoders.
method Define a differentiable loss function based on singular values of the code matrix, minimizing matricial free energy.
result Minimizing matricial free energy results in Gaussian-like codes that generalize.
We establish an energy quantization result for sequences of Willmore surfaces when the underlying sequence of Riemann surfaces is degenerating in the moduli space. we notably exhibit a new residue which quantifies the potential loss of energy in collar regions. Thanks to these residues, we also prove compactness of Wil…
Improves MRI-based brain surface reconstruction with minimal deformation energy loss.
problem Ensuring optimal deformation energy and consistency in learning-based cortical surface reconstruction.
method Design and implementation of a Minimal Energy Deformation (MED) loss in the V2C-Flow model.
result Significant improvements in training consistency and reproducibility without sacrificing reconstruction accuracy and topological correctness.
Many DNN-enabled vision applications constantly operate under severe energy constraints such as unmanned aerial vehicles, Augmented Reality headsets, and smartphones. Designing DNNs that can meet a stringent energy budget is becoming increasingly important. This paper proposes ECC, a framework that compresses DNNs to m…
We consider in dimension four weakly convergent sequences of approximate biharmonic maps to a Riemannian manifold with bi-tension fields bounded in Lp for p>34. We prove an energy identity that accounts for the loss of hessian energies by the sum of hessian energies over finitely many nontrivial biharmonic ma…
Federated learning calibrates insurance indices from renewable energy producers' data.
problem Calibrating parametric insurance indices under heterogeneous renewable energy production losses.
method Federated learning framework using Tweedie GLMs and distributed optimization.
result Federated learning recovers comparable index coefficients under moderate heterogeneity.
A new AI optimization method uses energy-conserving dynamics inspired by Born-Infeld theory.
problem Optimization challenges in non-convex loss functions and machine learning tasks.
method Discretization of Born-Infeld dynamics for energy-conserving Hamiltonian optimization.
result The method avoids high local minima and outperforms traditional methods in shallow valleys.
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.
DiMS sampler explores neural network loss minima via dissipative dynamics.
problem Sampling reparameterization invariant solutions in neural networks.
method Dynamical system based on kinetic energy with dissipative friction.
result DiMS sampler samples exactly from minimum level sets.
Quantum models face barren plateaus, but specific losses can be trainable.
problem Barren plateaus and loss concentration in quantum generative models.
method Investigated explicit and implicit losses, and their interplay.
result Explicit losses lead to new barren plateaus, while implicit losses can be trainable.
CityTFT models urban building energy using a data-driven approach.
problem Current UBEM methods are time-consuming and based on physics.
method CityTFT uses a TFT framework with an augmented loss function.
result CityTFT predicts energy demands with high accuracy.
EBMs trained with ML are shown to behave like GANs with a self-adversarial loss.
problem Training EBMs with ML is intractable due to intractable unnormalized distributions.
method Replaced MCMC with deterministic gradient descent ODE solutions to study density induced by dynamics.
result EBM training is effectively a self-adversarial procedure rather than ML estimation.
Paper proposes a new method to learn EBMs and their partition function.
problem Intractability of exact MLE for EBMs due to partition function computation.
method Jointly learns an energy model and its log-partition function using neural networks.
result First tractable method for optimizing sparsemax loss in large spaces.
We introduce the "Energy-based Generative Adversarial Network" model (EBGAN) which views the discriminator as an energy function that attributes low energies to the regions near the data manifold and higher energies to other regions. Similar to the probabilistic GANs, a generator is seen as being trained to produce con…
Enhanced Hopfield model boosts memory retrieval capacity.
problem Memory retrieval in modern Hopfield models with limited capacity.
method Introduces a learnable feature map transforming energy function into kernel space, minimizing separation loss for uniform memory distribution.
result Significant reduction in metastable states, enhancing memory capacity and retrieval accuracy.
Deep learning improves solar energy forecasting using physical and data-driven models.
problem Improving short-term solar energy forecasting accuracy.
method Injecting physical knowledge into deep learning models for spatio-temporal forecasting.
result Improved solar energy forecasting models using deep learning and physical criteria.
Paper proposes a risk-averse approach to energy storage price arbitrage using conformal uncertainty quantification.
problem Inherent volatility and uncertainty of real-time electricity prices create financial risks for storage arbitrage.
method Two-layer prediction model with conformal uncertainty quantification for high coverage of real-time price uncertainty.
result The framework achieves good profit margins with minimal losses, demonstrating effectiveness in real-time market.
Paper shows training can improve GCN performance without changing architecture.
problem Training difficulty of GCNs limits their performance.
method Identified and mitigated energy loss during training.
result Significant decrease in training difficulties and notable performance boost.
Paper proves stability of multi-dimensional rarefaction waves in gas dynamics.
problem Challenges in constructing multi-dimensional rarefaction waves in gas dynamics.
method Geometric Weighted Energy Method (GWEM) to overcome derivative losses.
result Established nonlinear stability of multi-dimensional rarefaction waves for compressible Euler equations.
Study compares different scoring rules for machine-learned weather forecasts, finding scale-awareness improves forecast realism.
problem Improving the accuracy of machine-learned probabilistic weather forecasts.
method Comparison of scoring rules (CRPS, fair global energy score, graph energy score) and analysis of their impact on forecast field spectra.
result Scale-awareness improves forecast realism, particularly in the tropics.
Adversarial attacks can fool ML energy theft detection models.
problem Vulnerability of ML-based energy theft detection models to adversarial attacks.
method Design of an adversarial measurement generation algorithm.
result ML models can be significantly fooled by adversarial attacks, reducing their detection accuracy.
The Teichmüller harmonic map flow is a gradient flow for the harmonic map energy of maps from a closed surface to a general closed Riemannian target manifold of any dimension, where both the map and the domain metric are allowed to evolve. Given a weak solution of the flow that exists for all time t≥0, we find a …
Advances in renewable energy generation and introduction of the government targets to improve energy efficiency gave rise to a concept of a Zero Energy Building (ZEB). A ZEB is a building whose net energy usage over a year is zero, i.e., its energy use is not larger than its overall renewables generation. A collection …
EDCompress optimizes energy efficiency of CNN models on edge devices.
problem Low energy consumption for edge devices with diverse dataflow types.
method Energy-aware model compression using reinforcement learning.
result Improves energy efficiency by 20X, 17X, 37X in various networks.
Study existence of harmonic and Dirac-harmonic maps from degenerating surfaces.
problem Existence of harmonic and Dirac-harmonic maps from degenerating surfaces.
method Using the Sacks and Uhlenbeck scheme, analyze a sequence of maps from degenerating surfaces to non-positive curved manifolds.
result Existence of limiting harmonic and Dirac-harmonic maps under certain conditions.
Deep neural networks improve free energy calculations for peptide conformations.
problem Challenges in developing suitable mappings for free energy perturbation.
method Adapted machine learning approach to train deep neural networks for mapping between Boltzmann distributions.
result Accurate free energy differences calculated between thermodynamic states with spring centers separated by 1 Å and sometimes 2 Å.
Gaussian process regression loses locality in high dimensions, affecting molecular energy surface fitting.
problem Loss of locality in high-dimensional Gaussian process regression.
method Analysis of Matern family kernels and multi-zeta basis functions.
result The property of locality disappears in high dimensions, impacting regression quality.
A neural flow method minimizes Willmore energy for 2-surfaces in 3D space.
problem Minimizing Willmore energy for closed oriented 2-surfaces in 3D space.
method Introducing neural Willmore flow to model and minimize the Willmore energy using neural architectures.
result The neural flow reproduces expected round sphere and Clifford torus for genus 0 and 1 surfaces, respectively, and finds minimal Willmore surfaces for genus 2.
Paper proposes energy objective for training normalizing flows without determinants.
problem Challenges in training normalizing flows due to Jacobian determinants.
method Introduces energy objective based on proper scoring rules, determinant-free.
result Energy objective supports novel model families and competitive performance.
Low-bit training framework reduces energy consumption in CNNs.
problem Reducing energy consumption in convolutional neural networks.
method Low-bit training framework using MLS tensor format with dynamic quantization.
result Achieves superior trade-off between accuracy and bit-width.
In this paper we develop a statistical arbitrage trading strategy with two key elements in hi-frequency trading: stop-loss and leverage. We consider, as in Bertram (2009), a mean-reverting process for the security price with proportional transaction costs; we show how to introduce stop-loss and leverage in an optimal t…
Improves generative models for cost-sensitive decisions.
problem Generative models lack awareness of decision costs.
method Integrates a decision loss into the training objective.
result Improves cost-sensitive forecast accuracy.
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.
Develops algorithms for personalized ranking in recommender and energy systems.
problem Designing algorithms for personalized ranking in dynamic systems.
method Proposes SAROS for recommender systems and a fault detection algorithm for power systems.
result SAROS outperforms traditional methods in both recommender and energy systems.
We implement a differentiable Neural Architecture Search (NAS) method inspired by FBNet for discovering neural networks that are heavily optimized for a particular target device. The FBNet NAS method discovers a neural network from a given search space by optimizing over a loss function which accounts for accuracy and …
Convolutional neural networks (CNNs) have been increasingly deployed to edge devices. Hence, many efforts have been made towards efficient CNN inference in resource-constrained platforms. This paper attempts to explore an orthogonal direction: how to conduct more energy-efficient training of CNNs, so as to enable on-de…
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.
We study the Bondi-Sachs rockets with nonzero cosmological constant. We observe that the acceleration of the systems arises naturally in the asymptotic symmetries of (anti-) de Sitter spacetimes. Assuming the validity of the concepts of energy and mass previously introduced in asymptotically flat spacetimes, we find th…
Energy trees handle complex data structures with multiple variable types.
problem Handling intricate data structures with various types of covariates.
method Energy trees, a regression and classification model, use energy statistics to accommodate structured covariates of different types.
result Energy trees maintain statistical foundations, interpretability, and robustness to overfitting.
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.
Two synthetic likelihood methods learn EBM of likelihood from simulator data for SBI.
problem Conduct inference from experimental observations using high-fidelity simulators.
method Learn conditional EBM of likelihood using synthetic data conditioned on parameters.
result Learned likelihood combined with prior yields posterior estimate for sampling.