INO learns physical models with momentum conservation laws.
problem Learning physical models without preserving fundamental laws.
method Designing an invariant neural operator that automatically satisfies momentum conservation laws.
result The model learns complex material behaviors and achieves state-of-the-art accuracy and efficiency.
Frame Averaging makes neural networks invariant or equivariant to new symmetries.
problem Designing neural networks that respect symmetries while being expressive and efficient.
method Introduces Frame Averaging (FA) as a systematic framework to adapt architectures to become invariant or equivariant to new symmetries.
result Frame Averaging guarantees exact invariance or equivariance while being simpler to compute than full group averaging.
Physics-informed neural networks improve by measuring effective dimensionality of constraints.
problem Task interference in physics-informed neural networks due to shared parameter space.
method Introduce effective dimensionality (deff) as an operator invariant to quantify constraints. result Effective dimensionality measures unconstrained parameter directions, independent of network architecture.
This research studies affine invariance in continuous-domain convolutional neural networks.
problem Recognizing patterns and features under affine transformations in continuous domains.
method Introduces a new criterion for assessing affine invariance, embeds images into the affine Lie group, and analyzes convolution over this group.
result Extends the scope of geometrical transformations that deep-learning pipelines can handle.
A universal collection of 4 invariants improves neural network accuracy for molecular dynamics.
problem Improving accuracy of neural networks in molecular dynamics.
method Developed a universal collection of 4 smooth scalar invariants on M(3) x M(3) and evaluated their effectiveness in a PONITA neural network architecture.
result Using a universal collection of invariants significantly improves neural network accuracy.
Transformationally invariant processors constructed by transformed input vectors or operators have been suggested and applied to many applications. In this study, transformationally identical processing based on combining results of all sub-processes with corresponding transformations at one of the processing steps or …
MCNO learns PDE solution operators using Monte Carlo sampling.
problem Learning solution operators for PDEs efficiently and flexibly.
method Directly learns kernel function using Monte Carlo sampling of input-output pairs.
result Competitive accuracy with efficient computational cost on 1D PDE benchmarks.
GeONet learns the Wasserstein geodesic without mesh discretization.
problem Computing the Wasserstein geodesic between complex data distributions.
method Mesh-invariant deep neural operator network that learns saddle point optimality conditions.
result GeONet achieves comparable accuracy to standard OT solvers with reduced computational cost.
ISOKANN learns collective variables and effective dynamics for metastable transitions.
problem Understanding metastable transitions in complex molecular systems.
method Integrates Koopman operators with neural networks to extract CVs and effective dynamics.
result Reconstructs coarse-grained kinetics and reproduces transition times across barriers.
VANO uses neural operators for unsupervised learning of functional data.
problem Learning operators between infinite dimensional spaces for functional data.
method Variational Autoencoding Neural Operators (VANO) approach.
result VANO can learn and reconstruct functional data without supervision.
In this paper we propose a generalization of deep neural networks called deep function machines (DFMs). DFMs act on vector spaces of arbitrary (possibly infinite) dimension and we show that a family of DFMs are invariant to the dimension of input data; that is, the parameterization of the model does not directly hinge …
This paper completes the construction of arbitrary order conformally invariant differential operators in higher spin spaces. Jan Slovák has classified all conformally invariant differential operators on locally conformally flat manifolds. We complete his results in higher spin theory by giving explicit expressions for …
New method learns PDE solutions from low-fidelity data.
problem Challenges in learning PDE surrogates with scarce data.
method Flow matching in infinite-dimensional space with conditional neural operators.
result Accurately learns PDE solutions across different resolutions and fidelities.
A new graph neural network framework captures long-range interactions efficiently.
problem Efficiently modeling long-range interactions in graph neural networks for PDEs.
method Proposes a multi-level graph neural network framework using multipole methods.
result Captures interaction at all ranges with only linear complexity, learning discretization-invariant solution operators.
Patch ranking improves CNN performance by focusing on object content, not location.
problem CNNs lack rotation and translation invariance, limiting model capacity.
method Patch ranking before convolution and pooling to encode invariance.
result Patch ranking module improves CNN performance on various tasks.
Graph Neural Networks (GNN) come in many flavors, but should always be either invariant (permutation of the nodes of the input graph does not affect the output) or equivariant (permutation of the input permutes the output). In this paper, we consider a specific class of invariant and equivariant networks, for which we …
Enhanced Yang-Baxter operators give rise to invariants of oriented links. We expand the enhancing method to generalized Yang-Baxter operators. At present two examples of generalized Yang-Baxter operators are known and recently three types of variations for one of these were discovered. We present the definition of enha…
The paper examines scalar fourth-order linear differential operators and their invariants.
problem Equivalence problem of scalar fourth-order linear differential operators.
method Investigation of differential invariants.
result Application of differential invariants to the equivalence problem.
The low displacement rank (LDR) framework for structured matrices represents a matrix through two displacement operators and a low-rank residual. Existing use of LDR matrices in deep learning has applied fixed displacement operators encoding forms of shift invariance akin to convolutions. We introduce a class of LDR ma…
Study natural invariants for differential operators, simplifying their equivalence problem.
problem Equivalence problem of nonlinear differential operators.
method Description of rational natural differential invariants.
result Application of natural invariants to simplify differential operator equivalence.
It is well known that neural networks with rectified linear units (ReLU) activation functions are positively scale-invariant. Conventional algorithms like stochastic gradient descent optimize the neural networks in the vector space of weights, which is, however, not positively scale-invariant. This mismatch may lead to…
The paper studies differential operator invariants and equivalence under Lie pseudogroups.
problem Understanding invariants and equivalence of differential operators under Lie pseudogroups.
method Analysis of invariants, use of n-invariants, and application of local symplectomorphisms as an example.
result Normal forms and solutions to equivalence problems for differential operators.
Study natural invariants for third order nonlinear operators on 2D manifolds.
problem Equivalence problem of third order nonlinear differential operators.
method Description of rational natural differential invariants.
result Application of natural invariants to equivalence problem.
Enhances GNNs by capturing node relationships, outperforming 2-WL test.
problem Inability of conventional GNNs to fully capture node relationships due to permutation invariance.
method Develops permutation-sensitive aggregation mechanism using permutation groups.
result Proves superior expressivity compared to 2-WL test and not less than 3-WL test.
The paper classifies invariant operators and proves a Liouville theorem.
problem Classifying invariant operators and proving Liouville theorem.
method Classified Möbius invariant differential operators and established a Liouville type theorem.
result Established a Liouville type theorem for Möbius invariant equations.
Study presents a method to induce a generalized neural network from joint group invariant functions.
problem Encoding rule of neural network internal data representation.
method Systematic method using joint group invariant function on data-parameter domain.
result Induces a generalized neural network and its inverse operator (ridgelet transform).
Recently, researchers have started applying convolutional neural networks (CNNs) with one-dimensional convolutions to clinical tasks involving time-series data. This is due, in part, to their computational efficiency, relative to recurrent neural networks and their ability to efficiently exploit certain temporal invari…
The study quantifies how many objects can be linearly classified under all views.
problem Understanding the expressivity of group-equivariant representations.
method Generalization of Cover's Function Counting Theorem to quantify separable dichotomies.
result The fraction of separable dichotomies is determined by the fixed space dimension of the group action.
Study invariant operators and vanishing theorems in CR geometry.
problem Analyzing invariant operators and vanishing theorems in CR geometry.
method Investigates Kohn-Dirac operators and derives CR invariant twistor operators.
result Proves vanishing theorems for harmonic spinors and Kohn-Rossi groups.
Study of eta invariant for non-compact manifolds via Dirac-type operators.
problem Defining and studying the relative eta invariant for non-compact manifolds.
method Defined the relative eta function and studied its variation and gluing law.
result Shows the relative eta invariant coincides with a previously defined version.
New calculus for pseudodifferential operators on manifolds with cylindrical ends.
problem Analyzing layer potentials on manifolds with cylindrical ends.
method Introducing and studying two classes of pseudodifferential operators.
result Spectrally invariant property of the 'essentially translation invariant calculus'.
Neural networks learn from ensemble forecasts without considering their order.
problem Improving reliability of probabilistic weather forecasts.
method Permutation-invariant neural networks for postprocessing ensemble forecasts.
result Models achieve state-of-the-art prediction quality in surface temperature and wind gust forecasts.
In this article, we investigate differential operators on the Siegel-Jacobi space that are invariant under the natural action of the Jacobi group. These invariant differential operators play an important role in the arithmetic theory of Jacobi forms of higher degree. We present some explicit invariant differential oper…
Study invariant operations on Fedosov manifolds.
problem None explicitly stated in the abstract.
method Analysis of tensor-valued operations on Fedosov manifolds.
result Spaces of homogeneous natural tensors are finite dimensional linear representations of the symplectic group.
Transforms improve CNNs' invariance to image transformations.
problem Current CNN models lack robustness to spatial transformations.
method Randomly transform feature maps during training to learn invariant representations.
result Significant improvements on benchmark tasks, including image recognition and retrieval.
New universal invariant operators are introduced in a class of geometries which include the quaternionic structures and their generalisations as well as 4-dimensional conformal (spin) geometries. It is shown that, in a broad sense, all invariants and invariant operators arise from these universal operators and that the…
We seek to improve deep neural networks by generalizing the pooling operations that play a central role in current architectures. We pursue a careful exploration of approaches to allow pooling to learn and to adapt to complex and variable patterns. The two primary directions lie in (1) learning a pooling function via (…
BGG-operators form sequences of invariant differential operators and the first of these is overdetermined. Interesting equations in conformal geometry described by these operators are those for Einstein scales, conformal Killing forms and conformal Killing tensors. We present a deformation procedure of the tractor conn…
Study Schiffer operators on Riemann surfaces, linking conformal and topological invariants.
problem Investigate Schiffer operators on Riemann surfaces and their connections to conformal and topological invariants.
method Develop calculus for Schiffer and Cauchy operators, derive index theorems, and characterize kernels and images.
result Derive index theorems for Schiffer operators, connecting conformal invariants to topological invariants.
The paper studies chambered invariants of real Cauchy-Riemann operators on Riemann surfaces.
problem Counting pseudo-holomorphic curves in symplectic Calabi-Yau 3-folds.
method Constructs three chambered invariants: nBl, n1,2, n2,1, defined by counting solutions to ADHM vortex equations and pseudo-holomorphic sections of bundles. result Conjectures a relationship between n1,2 and n2,1 and symplectic invariants. Multiple instance learning (MIL) is a variation of supervised learning where a single class label is assigned to a bag of instances. In this paper, we state the MIL problem as learning the Bernoulli distribution of the bag label where the bag label probability is fully parameterized by neural networks. Furthermore, we …
The paper addresses instability in CNNs' first layer by proving max pooling's shift invariance.
problem Instability in CNNs' first layer, leading to sensitivity to small input shifts.
method Establishing conditions for max pooling's shift invariance and deriving a measure of stability.
result Max pooling approximates a nearly shift-invariant complex modulus under certain conditions.
We consider two approaches to isotopy invariants of oriented links: one from ribbon categories and the other from generalized Yang-Baxter operators with appropriate enhancements. The generalized Yang-Baxter operators we consider are obtained from so-called gYBE objects following a procedure of Kitaev and Wang. We show …
Proves formal self-adjointness of certain differential operators.
problem Verifying conjectures about differential operators.
method Proving formal self-adjointness through mathematical proof.
result Proves two conjectures about differential operators.
Study generalizes Picard iteration for nonlinear PDEs, deriving bounds on error.
problem Generalize Picard iteration for nonlinear parabolic PDEs.
method Formulate Picard iteration as abstract state-transition model, derive generalization error bounds.
result Picard depth reduction reduces Picard truncation error without increasing estimation error.
This paper introduces CloudLSTM, a new branch of recurrent neural models tailored to forecasting over data streams generated by geospatial point-cloud sources. We design a Dynamic Point-cloud Convolution (DConv) operator as the core component of CloudLSTMs, which performs convolution directly over point-clouds and extr…
We identify Melrose's suspended algebra of pseudodifferential operators with a subalgebra of the algebra of parametric pseudodifferential operators with parameter space R. For a general algebra of parametric pseudodifferential operators, where the parameter space may now be a cone Γ⊂Rp, we construct a uniq…
Classifies curved bidifferential operators on manifolds.
problem Classify bidifferential operators on curved spaces.
method Complete classification using Laplacian and conformal invariance.
result Constructs a large class of conformally invariant differential operators.