Minimal elastic networks minimize energy and length at fixed angles.
problem Finding optimal network configurations under elastic constraints.
method Minimizing a combination of elastic energy and length.
result Existence and regularity of minimizers with prescribed angles.
Local elasticity in neural networks makes predictions resilient to dissimilar updates.
problem Understanding resilience of neural network predictions to updates from dissimilar data.
method Simulation and geometric interpretation using neural tangent kernel.
result Local elasticity persists in neural networks with nonlinear activation functions, not in linear ones.
Unified survey of elastic flow for curves and networks.
problem Understanding the evolution of curves and networks under elastic forces.
method Unified presentation and proof of global existence and convergence for closed curves.
result Global existence and smooth convergence to critical points for closed curves in R^2.
Elastic Gossip distributes neural network training using gossip-like protocols.
problem Distributing neural network training across heterogeneous environments.
method Pairwise-communication using Gossip-like protocols, building on Elastic Averaging SGD.
result Elastic Gossip performs better than Gossiping SGD in experiments, but hyper-parameter search may yield better configurations.
Estimates deformation of elastic objects using neural networks from few observations.
problem Estimating deformation of elastic objects using limited data.
method Learning approach with a neural network to estimate entire deformation from few observations.
result Average estimation error of 0.041 mm for human liver model under significant deformation.
Model for material elasticity and plasticity using networks.
problem Understanding the elasticity and plasticity of materials.
method Developed a mathematical model based on networks, defining tension tensor for periodic graphs.
result The model explains elasticity and plasticity through local moves on graphs.
Network Elastic Net identifies smoking-specific gene expression for lung cancer prognosis.
problem Identifying smoking-specific gene expression biomarkers in lung cancer prognosis.
method Introduces Network Elastic Net, a method that clusters and regresses on graphs based on smoking behavior.
result Shows efficacy of clusters in identifying cancer stages using gene expression and smoking behavior.
Study on minimizing network energy in R^d, introducing degenerate elastic networks.
problem Minimizing network energy in R^d with constraints on curves and junctions.
method Characterizing limits of sequences of networks bounded in energy, providing explicit representation of the relaxed problem.
result Explicit representation of degenerate elastic networks, a new concept involving only given class properties.
Chicle tackles elastic machine learning training by avoiding micro-tasks.
problem Elasticity and load balancing in distributed machine learning training.
method Chicle is a new elastic distributed training framework that exploits machine learning algorithms to implement elasticity and load balancing without micro-tasks.
result Chicle achieves performance competitive with state-of-the-art rigid frameworks while enabling elastic execution and dynamic load balancing.
PIE-PINN estimates elastic properties from noisy, low-res displacement data.
problem Estimating heterogeneous elastic properties from low-resolution, noisy data.
method Probabilistic Physics-Informed Neural Network (PIE-PINN) framework combining B-spline and hierarchical scale model.
result Robust estimation of Young's modulus and Poisson's ratio from noisy, low-resolution displacement data.
Study on local elasticity in neural network training, improving detection of class-specific changes.
problem Improving the detection of class-specific changes in neural network training.
method Comprehensive study of local elasticity, proposing a new definition to address limitations.
result New definition of local elasticity more sharply detects class-specific changes in neural network training.
Cartesian neural network models learn soft tissue mechanical properties without shape assumptions.
problem Model-based methods limit elastography to imaging linear-elastic parameters.
method Data-driven neural network constitutive models (NNCMs) learn stress-strain relationships from force-displacement data.
result NNCMs can characterize mechanical properties and their spatial distribution without prior shape knowledge.
A new ride-hailing subsidy system uses deep causal networks to estimate consumer elasticity.
problem Estimating consumer elasticity with subsidies in ride-hailing industry.
method Introduces a consumer subsidizing system using deep causal networks to address confounding effects.
result Effective in estimating the uplift effect of subsidies without confounding.
Seismic inversion improved using semi-supervised sequence modeling.
problem Lack of geophysical constraints in machine learning seismic inversion.
method Semi-supervised sequence modeling with recurrent neural networks.
result Achieved 98% correlation between estimated and target elastic impedance.
EWC uses quadratic penalties that may double-count earlier task data.
problem Catastrophic forgetting in neural networks.
method Extended derivation of EWC with multiple tasks.
result Quadratic penalties in EWC might double-count earlier task data.
EWC helps prevent forgetting in neural networks by adjusting weights dynamically.
problem Preventing forgetting in neural networks during training.
method EWC adjusts weights dynamically to prevent forgetting.
result EWC effectively prevents catastrophic forgetting in neural networks.
The study examines how modernizing settlement infrastructure affects inside money elasticity and network efficiency.
problem Understanding the impact of modernizing settlement infrastructure on inside money elasticity and network efficiency.
method Constructed a panel dataset of 809 reform events across 24 advanced economies, decomposed into economic channels and phases, and used a T2S event-study and synthetic control method.
result Modernizing settlement infrastructure generates network-conditional balance sheet efficiencies, with an estimated +13.4 percent efficiency recovery from 2027-2032.
Paper applies ML to improve fiber nonlinearity modeling and monitoring for EONs.
problem Improving accuracy of fiber nonlinearity models for EONs.
method Uses machine learning to calibrate and combine modeling and monitoring schemes.
result Significant improvement in NLI variance estimation using ML.
We introduce elastic geodesic grids for easy-to-fabricate, deployable structures.
problem Approximating freeform surfaces with deployable structures.
method Geodesic curves on target surfaces, kinematic mechanism, differential geometry.
result Elastic geodesic grids can approximate freeform surfaces easily and deployably.
Physics-informed GANs estimate elastic moduli from mechanical tests.
problem Estimating spatially-varying elastic moduli from measured deformations.
method Physics-informed Generative Adversarial Networks (PI-GANs) with PDE constraints.
result Generated stiffness samples match true distribution statistics.
Study models deep learning training dynamics using locally elastic SDEs to reveal feature separability.
problem Understanding how deep learning models separate features from different classes during training.
method Modeling deep learning training using locally elastic SDEs with a drift term reflecting backpropagation impact.
result Local elasticity in SDEs leads to linear separability of features, resulting in vanishing training loss.
This paper improves neural tangent kernels for better generalization and local elasticity.
problem Performance gap between neural tangent kernels and real-world neural networks.
method Introduces label-aware kernels using Hoeffding decomposition.
result Models trained with proposed kernels simulate NNs better in terms of generalization and local elasticity.
Sparse elasticity reconstruction from local displacements reduces error.
problem Reconstructing elasticity from limited data.
method Sparse elasticity reconstruction theory, local clustering, alternating optimization.
result Higher spatial resolution elasticity distribution estimation.
IC-Network improves CNNs by integrating elastic collision units.
problem Designing more effective basic units in neural networks.
method Developed IC layer and IC block units combining the IC structure with convolution operations.
result Significant performance improvements in existing CNNs, reducing top-1 error from 22.85% to 21.49% on imagenet.
EAD creates L1-distorted adversarial examples to improve DNN security.
problem Vulnerability of deep neural networks to adversarial examples.
method Formulated as an elastic-net regularized optimization problem.
result EAD yields distinct adversarial examples with small L1 distortion. Classifies pinned p-elasticae and finds unique optimality exponents.
problem Classifying and understanding p-elasticae under pinned boundary conditions. method Classification and analysis of p-elasticae, proving uniqueness and existence. result Discovery of a unique exponent p≃1.5728 for full optimality. Analyzes properties of stiffness tensors for elastic wave imaging.
problem Characterizing stiffness tensor fields for elastic wave imaging.
method Finsler-geometric methods applied to anisotropic stiffness tensor fields.
result Conditions for Finsler-geometric methods to be applicable.
Elastic Cash adjusts money supply to stabilize interest rates.
problem Stabilizing interest rates in a decentralized system.
method Modifies supply to keep interest rate fixed by public market.
result Improves elasticity of US Dollar and new cryptocurrencies.
We find a Weierstrass-like formula for 2D elastic maps.
problem Understanding elastic maps between planar domains.
method Develop a Weierstrass representation for critical points of certain energy functionals.
result Elastic maps admit a Weierstrass representation in terms of holomorphic functions.
Proposes using elastic demand to improve forecasting accuracy.
problem Mismatch between planned supply and actual demand due to demand variance.
method Reallocate historical elastic demand to reduce forecasting variance.
result Improves forecasting and supply planning effectiveness.
Characterizes null Lagrangians in Cosserat elasticity.
problem Understanding null Lagrangians in micropolar elasticity.
method Applying Olver and Sivaloganathan's theorem to characterize null Lagrangians.
result Complete characterization of null Lagrangians for three-dimensional bodies and shells.
Approximate 3D elastic curves with exact constraints
problem Designing and approximating 3D elastic curves
method Numerically stable method for recovering 11 parameters
result Fast and stable approximation of arbitrary curves
New algorithm selects genes for cancer classification using adaptive elastic net and conditional mutual information.
problem Selecting informative genes for microarray cancer classification.
method Adaptive Elastic Net with Conditional Mutual Information (AEN-CMI).
result AEN-CMI achieves the best classification performance with fewer genes.
Neural networks struggle with certain geometric problems, but not all.
problem Neural networks' limitations in modeling certain geometric problems.
method Illustration through specific examples and analysis of integral functionals.
result There is no energy gap between Barron functions and Lipschitz functions for a large class of integral first-order functionals.
Blog post discusses various implementations of Fisher Information for EWC in continual learning.
problem Improving Elastic Weight Consolidation (EWC) results by optimizing Fisher Information computation.
method Empirically compares different implementations of Fisher Information for EWC.
result Many reported EWC results can be improved by changing Fisher Information computation methods.
Stable discretizations for elastic flow on Riemannian manifolds.
problem Discretizing elastic flow on curved spaces.
method Conformally flat Riemannian manifolds discretization.
result Robust and quadratic convergence of the method.
The paper studies rigidity and continuity in nonlinear elasticity on manifolds and hypersurfaces.
problem Rigidity and continuity properties of elastic bodies in non-Euclidean settings.
method Geometric rigidity estimates, asymptotic rigidity of elastic membranes, simplified geometric proof of continuous dependence.
result Established geometric rigidity estimate and proved asymptotic rigidity of elastic membranes.
Study preserves planar and graphical properties of curves under elastic flow.
problem Maintaining planar and graphical properties of non-compact curves under elastic flow.
method Extended recent work on adapted elastic energy to derive thresholds for planar and graphical embeddedness.
result Derived new Li--Yau type inequality for complete planar curves.
The paper studies the free elastic flow of closed curves and finds their asymptotic shape converges to a circle.
problem Challenges in studying the asymptotic behavior of the free elastic flow for closed curves.
method Analysis of the free elastic flow as an L2-gradient flow for Euler's elastic energy. result An appropriate rescaling of initial curves geometrically close to circles converges to a unique round circle.
Motivated by the problem of finding an explicit description of a developable narrow Moebius strip of minimal bending energy, which was first formulated by M. Sadowsky in 1930, we will develop the theory of elastic strips. Recently E.L. Starostin and G.H.M. van der Heijden found a numerical description for an elastic Mo…
Study on migrating elastic flows of curves across half-planes.
problem Migrating elastic flows of curves from upper to lower half-planes.
method Analytical and numerical construction of migrating elastic flows.
result Construction of various migrating elastic flows.
Study gauge freedoms in elastic wave equations and Dirichlet-to-Neumann map.
problem Recover stiffness tensor and density from Dirichlet-to-Neumann map.
method Analyze invariance under coordinate transformations and gauge freedoms.
result Present gauge freedoms in the Dirichlet-to-Neumann map for Riemannian elastic wave equation.
Solves curve migration problem with elastic flows.
problem Curve migration problem with natural boundary conditions.
method Constructing migrating elastic flows.
result Extends previous work to purely local flow.
Structure learning in random fields has attracted considerable attention due to its difficulty and importance in areas such as remote sensing, computational biology, natural language processing, protein networks, and social network analysis. We consider the problem of estimating the probabilistic graph structure associ…
New insights into stability of special curves on spheres.
problem Stability of closed p-elastic curves on spheres. method Analytical proof and construction of curves.
result All closed spherical p-elastic curves for p∈(0,1) are unstable. Paper analyzes shapes of brain arterial networks using statistical methods.
problem Quantifying and comparing shapes of brain arterial networks.
method Mathematical representation of BAN shapes as elastic shape graphs, development of Riemannian metrics and geometrical tools.
result Age has a clear, quantifiable effect on BAN shapes, with increased variance in shapes as age increases.
Symmetric elastic knots are found for certain classes with dihedral symmetry.
problem Finding elastic knots with specific symmetries.
method Minimizing bending energy under dihedral symmetry constraints.
result Existence of dihedral symmetric elastic knots, including a figure-eight union for the trefoil.
Study of elastic models in non-Euclidean spaces via Γ-convergence.
problem Elasticity in non-Euclidean ambient spaces with incompatible local rest distances.
method Γ-convergence to derive a limit elastic model, relating minimum energy to curvature discrepancy.
result Linearized version of a conjecture in elasticity confirmed, linking energy to curvature.