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

238477715953 · Jun 202019922001200920172026
48 results for neural manifold

Paper builds neural networks on matrix manifolds using gyrovector spaces.

problem Lack of concepts in gyrovector spaces for matrix manifolds.
method Generalized gyrovector space concepts for SPD and Grassmann manifolds, proposing new neural network models.
result Demonstrated effectiveness in human action recognition and knowledge graph completion.

We extend manifold capacity to nonlinear neural representations with contextual information.

problem Efficient processing of information through neural representations.
method Theoretical framework leveraging latent directions in input space related to contextual information.
result Derivation of an exact formula for context-dependent manifold capacity.

Riemannian Neural OT maps improve scalability on manifolds.

problem Challenges in extending neural OT to high-dimensional Riemannian manifolds.
method Introduces Riemannian Neural OT (RNOT) maps that avoid discretization and incorporate geometric structure.
result RNOT maps approximate Riemannian OT maps with sub-exponential complexity in the dimension.

Improved neural population modeling using shared features and ensemble detection.

problem Missing shared coding properties in neural latent variable models.
method Feature sharing across tuning curves and soft clustering of neurons.
result More interpretable and better-performing neural population models.

This work proposes a new neural implicit manifold model for more accurate density estimation on manifolds.

problem Current generative models struggle with representing manifolds accurately and learning densities within them.
method Proposes a neural implicit manifold model and a constrained energy-based model to learn manifold-supported distributions.
result The proposed model can learn manifold-supported distributions with complex topologies more accurately than pushforward models.

Researchers extend ResNets to Riemannian manifolds, improving performance over existing methods.

problem Learning on Riemannian manifolds, especially for hierarchical graphs and manifold-valued data.
method Geometrically principled extension of ResNets to general Riemannian manifolds.
result Riemannian ResNets outperform existing manifold neural networks in relevant metrics and training dynamics.

Designs neural networks on matrix manifolds for improved performance in tasks like human action recognition.

problem Designing neural networks for tasks on non-Euclidean manifolds.
method Develops fully-connected and convolutional layers for SPD manifolds, and MLR on SPSD manifolds.
result Demonstrates improved performance in human action recognition and node classification tasks.

Researchers develop neural networks for manifold data with a convergence rate.

problem Analyzing high-dimensional data on non-Euclidean domains.
method Constructing manifold neural networks using spectral decomposition of the Laplace Beltrami operator.
result Established a rate of convergence for the neural network scheme that depends on intrinsic manifold dimension.

Paper investigates hardness of learning neural networks under manifold hypothesis.

problem Hardness of learning neural networks under the manifold hypothesis.
method Extending proofs of hardness in the SQ and cryptographic settings to the geometric setting.
result Learning is hard under input manifolds of bounded curvature but learnable with additional assumptions on manifold volume.

CLAMP uses neural manifold packing to improve self-supervised learning.

problem Improving self-supervised learning for vision tasks.
method CLAMP recasts representation learning as a manifold packing problem, introducing a loss function inspired by particle systems.
result CLAMP achieves competitive performance with state-of-the-art models and separates neural manifolds effectively.

MSA compares neural representations' intrinsic geometry for better understanding.

problem Existing similarity measures fail to capture subtle distinctions between neural network solutions.
method Metric similarity analysis (MSA) using Riemannian geometry.
result MSA can disentangle features of neural computations and compare nonlinear dynamics.

Semi-supervised learning algorithms typically construct a weighted graph of data points to represent a manifold. However, an explicit graph representation is problematic for neural networks operating in the online setting. Here, we propose a feed-forward neural network capable of semi-supervised learning on manifolds w…

2019-08-21abs ↗pdf ↗

Deep neural networks estimate regression functions on manifolds.

problem Estimating regression functions on manifolds from data.
method Fully connected deep neural networks with ReLU activation, analyzing convergence rates.
result Estimates achieve a rate of convergence dependent on manifold dimension, not predictor dimension.

Neural networks learn discrete tasks on continuous data via emergent geometry.

problem Understanding how neural networks perform discrete computations on continuous data.
method Analysis of Riemannian pullback metric across neural network layers.
result Neural networks learn to discretize continuous inputs and perform logical operations on these discretized variables.

NDM incorporates geometric structure into neural networks for better optimization and interpretability.

problem Efficient and interpretable deep learning architectures.
method NDM is a neural network architecture that explicitly incorporates geometric structure into its design, using a Coordinate Layer, Geometric Layer, and Evolution Layer.
result NDM provides intrinsic regularization, enhancing generalization and robustness.

New Adam optimizer generalized for manifold training of neural networks.

problem Lack of clear physical intuition and difficulty in generalizing Adam optimizer to manifolds.
method Leverages the global tangent space representation of manifolds to perform Adam optimizer steps.
result Significant speed-ups in transformer training with orthogonality constraints.

New bounds for neural networks on curved manifolds improve generalization.

problem Existing generalization theories fail to account for non-Euclidean manifold structures.
method Derive covering number bounds incorporating manifold-specific properties like curvature.
result Sharp Rademacher complexity bounds for neural networks on compact manifolds.

GEM learns a manifold for cross-modal data, capturing structure without modality dependence.

problem Modality-specific neural models limit flexibility and custom architecture.
method Casts learning as manifold inference, enforcing coverage, linearity, and isometry.
result GEM learns latent structure across image, shape, audio, and cross-modal domains.

Neural and numerical methods approximate G2-structures on Calabi-Yau manifolds.

problem Approximating G2-structures on Calabi-Yau manifolds.
method Three stages: Ricci-flat metric computation, numerical approximations, and neural architecture training.
result Validated neural architecture for learning G2-structures and their metrics.

Deep neural networks excel at learning the training data, but often provide incorrect and confident predictions when evaluated on slightly different test examples. This includes distribution shifts, outliers, and adversarial examples. To address these issues, we propose Manifold Mixup, a simple regularizer that encoura…

2018-06-13abs ↗pdf ↗

PNDEs project neural dynamics onto constraint manifolds, improving accuracy and stability.

problem Learning dynamics from data without violating known constraints.
method Projecting the learned vector field onto the tangent space of the constraint manifold.
result PNDEs outperform existing methods in learning constrained dynamical systems.

Study shows how correlations between neural activity affect classification capacity.

problem Understanding how correlations between neural activity impact classification performance.
method Calculated the capacity of neural activity on spherical manifolds with and without correlations between centroids and axes.
result Introducing correlations between neural activity centroids pushes spheres closer together, while correlations between axes shrink their radii, revealing a duality between correlations and geometry in classification.

A new method for reducing model complexity using neural active manifolds.

problem Uncertainty quantification in computationally expensive models.
method Autoencoders and surrogate models to discover a neural active manifold.
result Neural active manifolds reduce model variance in multifidelity sampling.

Neural networks' performance scales with data size, explained by data manifold dimensionality.

problem Understanding the scaling of neural network performance with the number of parameters.
method Explained by the intrinsic dimension of the data manifold, confirmed through teacher/student framework and various datasets.
result The scaling exponent α is approximately 4 divided by the intrinsic dimension d of the data manifold.

The paper uses Cartan moving frames to analyze data manifolds and neural network outputs.

problem Understanding the geometry and explainability of neural network outputs.
method Employing Cartan moving frames to study the Riemannian structure of data manifolds and their curvature.
result The relationship between neural network outputs and the geometry of inputs is exploited for explainable AI.

Study reveals how neural network smoothness affects their vulnerability to adversarial attacks.

problem Understanding adversarial vulnerability in deep learning networks.
method Analysis of manifold smoothness and generalization capability of deep neural networks trained with local errors.
result High generalization accuracy requires a fast power-law decay of eigen-spectrum of hidden representations.

This paper improves causal inference using deep neural networks for low-dimensional covariates.

problem Improving causal inference with deep learning for high-dimensional covariates.
method Doubly robust off-policy learning with deep neural networks on low-dimensional manifolds.
result Nonasymptotic regret bounds for finite- and continuous-action scenarios, converging at a fast rate depending on intrinsic manifold dimension.

Neural Bayes simplifies computing complex stats for unsupervised learning.

problem Computing mutual information and optimal labeling of disjoint manifolds in unsupervised learning.
method Parameterization using neural networks to express statistical quantities in closed form.
result Neural Bayes enables efficient computation of mutual information and optimal labeling of disjoint manifolds.

Unified framework for Riemannian deep learning across manifold-valued representations.

problem Deep learning on manifold-valued representations often relies on Euclidean approximations or costly geometric operations.
method Develops reusable neural modules, manifold-specific network architectures, and geometric designs.
result Generalizes batch normalization and multinomial logistic regression to broader classes of manifolds.

Deep networks can perfectly classify two low-dimensional manifolds on a sphere with large depth and width.

problem Binary classification of two low-dimensional submanifolds on a sphere.
method Analysis of a deep fully-connected neural network trained to separate two submanifolds of the unit sphere.
result Randomly-initialized gradient descent can perfectly classify the two manifolds with high probability when the network depth is large relative to certain geometric and statistical properties of the data.