In this paper we explore methods to exploit symmetries for ensuring sample efficiency in reinforcement learning (RL), this problem deserves ever increasing attention with the recent advances in the use of deep networks for complex RL tasks which require large amount of training data. We introduce a novel method to dete…
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
48 results for “symmetry exploitation”
Efficient MCMC sampling in Bayesian neural networks by exploiting symmetries.
problem Challenges in Bayesian inference due to high-dimensional, multi-modal posterior density landscapes.
method Exploiting symmetries in the posterior landscape to restrict the parameter space and derive an upper bound on Monte Carlo chains.
result Efficient sampling is possible, offering a promising path for accurate uncertainty quantification in deep learning.
The paper develops tensor learning methods exploiting symmetries of tensor functions.
problem Efficiently handling tensors in various scientific contexts.
method Equivariant machine learning architectures exploiting orthogonal, Lorentz, and symplectic symmetries.
result Equivariant models outperform non-equivariant baselines in time series analysis.
Bayesian optimization gains efficiency by leveraging symmetries through a modified max kernel.
problem Improving Bayesian optimization efficiency for functions with group symmetries.
method Developed a PSD projection of the max kernel to exploit symmetries without violating kernel properties.
result The modified max kernel achieves lower regret compared to existing invariant and non-invariant kernels.
We propose a semantic segmentation model that exploits rotation and reflection symmetries. We demonstrate significant gains in sample efficiency due to increased weight sharing, as well as improvements in robustness to symmetry transformations. The group equivariant CNN framework is extended for segmentation by introdu…
New method approximates curvature from symmetries in deep networks.
problem Hard to approximate curvature in large deep networks.
method Analytically averaging over group actions that leave the loss invariant to construct structured Hessian approximations.
result Structured Hessian approximations from single gradients can be estimated, stored, and inverted.
We exploit the symmetry concepts developed in the companion review of this article to introduce a stochastic version of link reversal symmetry, which leads to an improved understanding of the reciprocity of directed networks. We apply our formalism to the international trade network and show that a strong embedding in …
FGNNs improve game-playing AI by exploiting symmetries.
problem Symmetrical game states are not exploited by current AI.
method Introduces FGNNs for creating group-equivariant neural networks.
result FGNNs improve performance in games like checkers and image segmentation.
We introduce an algorithm that exploits a combinatorial symmetry of an arrangement in order to produce a geometric reflection between two disconnected components of its moduli space. We apply this method to disqualify three real examples found in previous work by the authors from being Zariski pairs. Robustness is show…
Reduces equations for contact mechanical systems on Lie groups by exploiting symmetries.
problem Contact mechanical systems on Lie groups with symmetries.
method Reduction process using Lie group actions and symmetries.
result Euler-Poincaré-Herglotz equations on the reduced phase space.
The Noether theorem is extended to stochastic control problems using contact symmetries.
problem Stochastic optimal control problems.
method Exploiting jet bundles and contact geometry, the authors prove the existence of conserved quantities.
result Optimal control problems admit infinitely many conserved quantities in the form of local martingales.
We give a classification of compact solitons for the pluriclosed flow on complex surfaces. First, by exploiting results from the Kodaira classification of surfaces, we show that the complex surface underlying a soliton must be Kähler except for the possibility of steady solitons on minimal Hopf surfaces. Then, we const…
New scalable GP approximation using Fourier series decomposition.
problem Scalability and accuracy in Gaussian process approximations.
method Harmonic kernel decomposition (HKD) to decompose kernels orthogonally.
result Significantly outperforms standard variational methods in scalability and accuracy.
New equations use Pin(2) symmetry to study spinor and connection solutions.
problem Study of spinor and connection solutions on 4-manifolds.
method Define and analyze Seiberg-Witten-like equations with Rarita-Schwinger operators.
result Moduli space of solutions is non-compact and non-empty under certain conditions.
Method improves deep learning models for datasets with mixed approximate symmetries.
problem Improving deep learning models for datasets with mixed approximate symmetries.
method Regularizer-based approach to build models for datasets with mixed approximate symmetries.
result Our method achieves better accuracy than prior approaches while discovering the approximate symmetry levels correctly.
New insights into -distributions via Legendrian curves.
problem Understanding symmetries of -distributions.
method Exploiting a correspondence between distributions and lines on contact manifolds.
result One-to-one correspondence between equivalence classes of -distributions and Legendrian curves.
New RL method designs 3D molecules with improved symmetry.
problem Lack of 3D information in molecular design.
method Symmetry-aware actor-critic architecture using spherical harmonics.
result Improves generalization and molecule quality.
Study on Lawson surfaces' first Laplace eigenvalue using symmetry and algebraic methods.
problem Yau's conjecture on first eigenvalue of minimal hypersurfaces in the sphere.
method Symmetry-based approach exploiting discrete reflection symmetries and algebraic structure of reflection groups.
result Equality λ1(ξ_{m,k})=2 for Lawson surfaces with m and k even.
We propose a spectral curve describing torus knots and links in the B-model. In particular, the application of the topological recursion to this curve generates all their colored HOMFLY invariants. The curve is obtained by exploiting the full Sl(2, Z) symmetry of the spectral curve of the resolved conifold, and should …
We consider robust covariance estimation with group symmetry constraints. Non-Gaussian covariance estimation, e.g., Tyler scatter estimator and Multivariate Generalized Gaussian distribution methods, usually involve non-convex minimization problems. Recently, it was shown that the underlying principle behind their succ…
HexaConvcs.LG
The effectiveness of Convolutional Neural Networks stems in large part from their ability to exploit the translation invariance that is inherent in many learning problems. Recently, it was shown that CNNs can exploit other invariances, such as rotation invariance, by using group convolutions instead of planar convoluti…
In this paper we provide a new method for establishing the rotational symmetry of the solutions to a couple of very classical overdetermined problems arising in potential theory, in both the exterior and the interior punctured domain. Thanks to a conformal reformulation of the problems, we obtain Riemannian manifolds w…
Data augmentation can achieve the same statistical benefits as full augmentation up to an approximation error.
problem Data augmentation in learning problems
method Using Fourier analysis and representation theory of finite groups
result Partial data augmentation achieves the same minimax rates as full augmentation
This work reveals symmetries in quantum circuits and develops a noise-aware optimization method.
problem Understanding and optimizing the cost landscape of parametrized quantum circuits.
method Analytical proof of symmetries and their resilience to noise, followed by the development of SYMH optimization method.
result Symmetries in PQCs lead to degeneracy in the cost landscape and can be exploited to improve optimization under noise.
Symmetric observations don't necessarily imply symmetric causal explanations.
problem Inferring causal models from observed correlations is challenging and computationally intensive.
method An explicit example using a tripartite probability distribution over binary events.
result Symmetries in observations cannot be used to reduce the hypothesis space of causal models.
The paper introduces MDP homomorphic networks for faster reinforcement learning.
problem Current reinforcement learning approaches do not exploit symmetries in the joint state-action space.
method Equivariant neural networks with group-structured symmetries (reflections, rotations).
result MDP homomorphic networks converge faster than unstructured baselines on various tasks.
Develops non-parametric tests for group symmetry in data.
problem Lack of statistical tests for group symmetry in data.
method Formulates and implements non-parametric tests for distributional symmetry under specified groups.
result Develops tests for conditional invariance/equivariance and applies them to real-world data.
Akbulut has recently shown that an infinite family of Cappell-Shaneson homotopy 4-spheres is diffeomorphic to the standard 4-sphere. In the present paper, a strictly larger family is shown to be standard by a simpler method. This new approach uses no Kirby calculus except through the relatively simple 1979 paper of Akb…
Geometric Causal Modelsstat.ML
Develops geometric causal models for causal inference from dependent data.
problem Causal inference from structured, dependent data (e.g., spatial, network, molecular).
method Geometric causal models (GCMs) exploiting symmetries of data generating process, combining group theory, ergodic theory, and Bayesian inference.
result Establishes identification and estimation of causal effects from dependent data.
The study identifies exceptions to fiber-preserving symmetry in ODEs and systems.
problem Identifying exceptions to fiber-preserving symmetry in ODEs and systems.
method Lie's classification of Lie algebras of vector fields, absolute and relative scalar differential invariants, conditional and vector-valued relative invariants, prolongations of actions.
result Examples of scalar ODEs and systems with symmetry groups not fiber-preserving.
Researchers prove Seifert-Weber dodecahedral space is an L-space.
problem Proving the Seifert-Weber dodecahedral space is an L-space.
method Relating Floer homology and spectral geometry of hyperbolic three-manifolds, exploiting symmetry and arithmetic structure.
result Small eigenvalues on coexact 1-forms must have large multiplicity in Seifert-Weber dodecahedral space.
Analyzes symmetries in neural networks to predict learning dynamics.
problem Understanding the dynamics of neural network parameters during training.
method Unified theoretical framework based on symmetries and conservation laws.
result Symmetries impose geometric constraints on gradients and Hessians, leading to conservation laws.
Invariances to translation, rotation and other spatial transformations are a hallmark of the laws of motion, and have widespread use in the natural sciences to reduce the dimensionality of systems of equations. In supervised learning, such as in image classification tasks, rotation, translation and scale invariances ar…
In this note, Black--Scholes implied volatility is expressed in terms of various optimisation problems. From these representations, upper and lower bounds are derived which hold uniformly across moneyness and call price. Various symmetries of the Black--Scholes formula are exploited to derive new bounds from old. These…
Weaved helices form mechanically stable 3D structures.
problem Creating stable 3D structures from helical elements.
method Exploiting screw symmetry and invariant cylindrical rod packing to form triply periodic arrangements.
result Demonstrated nineteen triply periodic arrangements of interwoven helices.
Develops approximately equivariant neural processes for better data modeling.
problem Real-world data often breaks exact equivariance; how to model this?
method General approach to creating approximately equivariant architectures, applicable to any model and symmetry group.
result Approximately equivariant neural processes outperform non-equivariant and strictly equivariant models in regression tasks.
Study optimal transport on simplex boundary, proving transport map and potential regularity.
problem Regularity of transport map and potential on simplex boundary.
method Boundary regularity results for optimal transport maps, exploiting simplex symmetries.
result Regularity properties of transport map and its convex potential.
CNN improves neutrino event reconstruction in IceCube DeepCore.
problem Difficulties in distinguishing muon neutrinos and reconstructing inelasticity at GeV scale energies.
method 2D Convolutional Neural Network exploiting time and depth translational symmetry.
result CNN model outperforms conventional methods for flavor identification and inelasticity reconstruction.
A variety of lifted inference algorithms, which exploit model symmetry to reduce computational cost, have been proposed to render inference tractable in probabilistic relational models. Most existing lifted inference algorithms operate only over discrete domains or continuous domains with restricted potential functions…
Smoothly slice links in math.GT
The paper shows links with 2 components are not smoothly slice in a specific 4-manifold.
problem Tackles the smooth sliceness of 2-component links in a specific 4-manifold.
method Uses classical topological and smooth obstructions, along with constructive arguments exploiting symmetries.
result Demonstrates the existence of infinitely many integer homology 3-spheres with specific properties.
We develop numerical algorithms for solving the Einstein equation on Calabi-Yau manifolds at arbitrary values of their complex structure and Kahler parameters. We show that Kahler geometry can be exploited for significant gains in computational efficiency. As a proof of principle, we apply our methods to a one-paramete…
Symmetric and antisymmetric kernels for machine learning problems in quantum physics and chemistryquant-ph
Derives symmetric and antisymmetric kernels for quantum physics and chemistry applications.
problem Efficiently handling symmetries and antisymmetries in machine learning for quantum physics and chemistry.
method Symmetrizing and antisymmetrizing conventional kernels, analyzing feature space dimensions, proving kernel properties, proposing Slater determinant representation.
result Efficient evaluation of antisymmetric Gaussian kernels even in high-dimensional state spaces, significant reduction in training data size.
Spherical data is found in many applications. By modeling the discretized sphere as a graph, we can accommodate non-uniformly distributed, partial, and changing samplings. Moreover, graph convolutions are computationally more efficient than spherical convolutions. As equivariance is desired to exploit rotational symmet…
Asians and cash dividends: Exploiting symmetries in pricing theorycond-mat.stat-mech
In this article we present new results for the pricing of arithmetic Asian options within a Black-Scholes context. To derive these results we make extensive use of the local scale invariance that exists in the theory of contingent claim pricing. This allows us to derive, in a natural way, a simple PDE for the price of …
We provide bounds on the first Betti number and structure results for the fundamental group of horizon cross-sections for extreme stationary vacuum black holes in arbitrary dimension, without additional symmetry hypotheses. This is achieved by exploiting a correspondence between the associated near-horizon geometries a…
RCNPs extend equivariant neural processes to higher dimensions, improving performance on tasks with inherent symmetries.
problem Inherently equivariant tasks in spatio-temporal modeling, Bayesian Optimization, and continuous control.
method Relational Conditional Neural Processes (RCNPs) that extend equivariances to higher dimensions.
result Empirically competitive performance on tasks with equivariances.
Researchers compute mod 2 Seiberg-Witten invariants for spin structures and families.
problem Computing mod 2 Seiberg-Witten invariants for spin structures and families.
method Using Pin(2)-symmetry and localisation in equivariant cohomology, the researchers enhance and compute the invariants.
result The mod 2 Seiberg-Witten invariants are computed for spin structures and families, confirming the simple type conjecture mod 2.
New neural network architecture for auction design exploiting permutation symmetry.
problem Designing incentive-compatible auctions that maximize expected revenue.
method Constructed a permutation-equivariant neural network architecture.
result Permutation-equivariant architectures can perfectly recover optimal mechanisms.