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.

168,742 papers · 148 categories

Trend · papers per month

4018021,2021,603 · Jun 202019922001200920172026
48 results for learning geometry

Paper introduces a generalized Bures-Wasserstein geometry for SPD matrices.

problem Understanding the geometry of SPD matrices for machine learning.
method Proposes a generalized Bures-Wasserstein geometry parameterized by a symmetric positive definite matrix.
result The GBW geometry outperforms the BW geometry in machine learning applications.

In this paper, we evaluate the accuracy of deep learning approaches on geospatial vector geometry classification tasks. The purpose of this evaluation is to investigate the ability of deep learning models to learn from geometry coordinates directly. Previous machine learning research applied to geospatial polygon data …

2018-06-11abs ↗pdf ↗

Model financial dynamics using 2-manifold geometries, revealing the torus as best for cyclical data.

problem Financial forecasting using complex market data.
method Embedding market data onto 2-manifolds (S2, R2, H2, T) guided by uniformization theorem, inferring latent curvature.
result The torus geometry best predicts cyclical financial data, aligning with IS-LM theory.

ICLR 2021 challenge in computational geometry and topology attracted 16 teams.

problem Designing and evaluating computational methods in differential geometry and topology.
method Designing and hosting an open-source competition with repositories Geomstats and Giotto-TDA.
result 16 teams participated in the challenge, showcasing innovative contributions to computational geometry and topology.

This paper proposes a geometry-aware active learning framework for spatiotemporal dynamic systems.

problem Challenges in modeling complex dynamic systems with 3D geometries and time evolution.
method Geometry-aware spatiotemporal Gaussian Process (G-ST-GP) and adaptive active learning strategy.
result The proposed framework outperforms traditional methods in predicting high-dimensional dynamic behaviors.

Training shapes the geometry of neural network feature maps, revealing local area magnification.

problem Understanding how training affects the geometric structure of neural network feature maps.
method Analyzing the Riemannian geometry induced by neural network feature maps at infinite width and after training.
result Training breaks the symmetry of the geometry induced by random neural network feature maps, magnifying local areas along decision boundaries.

GAGA learns a warped metric for geometry-aware data generation and interpolation.

problem Challenges in generating data with meaningful geometry in high-dimensional datasets.
method Combines manifold learning with generative modeling to learn a warped Riemannian metric.
result GAGA improves trajectory inference by 30% in single-cell population-level data.

Paper explores Monge-Ampère in deep learning and quantum geometry.

problem Understanding the Monge-Ampère equation in deep learning.
method Review of Boltzmann learning, connection to optimal transport, insights from quantum geometry, renormalization group flow.
result Space of covariance matrices in learning dynamics coincides with the CAH cone.

A new method integrates autoencoders with geometry regularization for manifold learning.

problem Extracting simplified low-dimensional representations that capture intrinsic geometry in data.
method Integrates autoencoders with a geometric regularization term based on diffusion potential distances.
result The method preserves intrinsic structure, enables out-of-sample extension, and faithful reconstruction.

Natural gradient simplification for deep learning networks.

problem Efficiency in training deep Bayesian networks.
method Analysis of two geometries of Fisher information matrix and development of a method to simplify natural gradient for the second geometry.
result A method to simplify natural gradient for deep networks using an auxiliary recognition model.

GNPs learn operators on non-Euclidean geometries using neural networks.

problem Learning operators on complex geometries like manifolds.
method Geometric Neural Operators (GNPs) that incorporate geometric properties.
result GNPs can estimate metrics, solve PDEs, and learn LB operators on manifolds.

GABI learns geometry from diverse systems to improve Bayesian inference.

problem Bayesian inversion of physical systems with varying geometries.
method Geometric Autoencoders for Bayesian Inversion (GABI) learns geometry-aware priors from large datasets.
result GABI yields comparable predictive accuracy to deterministic methods and well-calibrated uncertainty quantification.

GeoFunFlow tackles inverse problems on complex geometries with efficient learning.

problem Challenges in inverse problems governed by PDEs, especially on irregular geometries.
method Combines geometric function autoencoder and latent diffusion model trained via rectified flow.
result Achieves state-of-the-art reconstruction accuracy and efficient inference.

NLGS optimizes latent geometry for better model performance.

problem Improving machine learning model performance by aligning latent space geometry with data structure.
method NLGS uses product manifolds with Gromov-Hausdorff distance for latent geometry search.
result NLGS finds optimal latent geometry with query-efficient Bayesian optimization.

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.

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

problem Deep learning on manifold-valued data lacks reusable modules, specific network architectures, and efficient geometric operations.
method Develops reusable neural modules, manifold-specific network architectures, and geometric designs for broad classes of Lie groups and gyrogroups.
result Generalizes batch normalization and multinomial logistic regression to Riemannian manifolds, including SPD and hyperbolic spaces.

Proposes a scalable framework for extracting data manifold geometry.

problem Efficiently mapping and learning data manifold geometry.
method Score-based pullback Riemannian geometry integrating pullback Riemannian geometry and generative models.
result High-quality geodesics and reliable intrinsic dimension estimation.

New method improves counterfactual distribution learning for high-dimensional outcomes.

problem Counterfactual distribution learning for high-dimensional outcomes with concentrated structure.
method Geometry-adaptive diffusion-guided smoothing estimators combining causal nuisance adjustment and local outcome geometry.
result Geometry-adaptive methods show steeper error decay in semi-synthetic experiments.

The paper analyzes how noise geometry influences the performance of SGD in machine learning.

problem Understanding how noise geometry affects the performance of stochastic gradient descent.
method Developed two metrics to quantify noise alignment strength and analyzed their effects on loss and subspace projection dynamics.
result Noise geometry can be used to guarantee alignment under certain conditions, aiding SGD's ability to escape from sharp minima.

The paper explores deep learning through algebra and geometry, highlighting geometric structures and differential processes.

problem Understanding the geometric and algebraic foundations of deep learning.
method Investigates neural networks from perceptron to transformer, emphasizing geometric structures and differential processes.
result A coordinate-free formulation of backpropagation equations using canonical scalar products on matrix spaces.

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.

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.

Mathematical framework using Riemannian geometry for intelligence and consciousness.

problem Lack of a unified mathematical framework for intelligence and consciousness.
method Conceptualizes intelligence as tokens in a high-dimensional space, using Riemannian geometry to describe structure and dynamics.
result Integrates geometric concepts to offer a unified framework for intelligence and consciousness.

Why and how that deep learning works well on different tasks remains a mystery from a theoretical perspective. In this paper we draw a geometric picture of the deep learning system by finding its analogies with two existing geometric structures, the geometry of quantum computations and the geometry of the diffeomorphic…

2017-10-30abs ↗pdf ↗

Neural Spacetimes learn DAGs by embedding nodes in a spacetime manifold.

problem Learning representations of weighted directed acyclic graphs (DAGs).
method Trainable deep learning-based geometries (Neural Spacetimes) that encode both edge weights and causality.
result Universal embedding theorem for DAGs with sub-cubic parameters and low distortion.

Neural networks' feature geometry evolves like discrete Ricci flow.

problem Understanding neural feature representations and their geometric transformations.
method Approximating input manifold with geometric graphs and analyzing their evolution during training.
result Neural feature geometry evolves like discrete Ricci flow, with nonlinear activations playing a crucial role.

Paper combines geometry and time-series analysis for spatiotemporal data.

problem Multivariate time-series data from multiple sensors.
method Combines manifold learning, Riemannian geometry, and spectral analysis.
result Proposes Riemannian multi-resolution analysis (RMRA) for dynamic mode extraction.

GeoERM learns shared representations on Riemannian manifolds for multi-task learning.

problem Heterogeneous and adversarial tasks in MTL.
method Geometry-aware MTL framework embedding shared representation on Riemannian manifold, optimizing via manifold operations.
result GeoERM improves estimation accuracy and stability, outperforming alternatives.

New method learns shape correspondences robustly from raw geometry.

problem Inaccurate and poor generalization of shape correspondences.
method Learning-based approach with feature-extraction network and functional map representation.
result Robust and accurate shape correspondence learning with less training data.

Develops Riemannian geometry for optimization on manifolds with detailed derivations.

problem Abstract high-level optimization on nonlinear spaces like matrix manifolds.
method Systematic derivation of geometric structures and constructions in coordinates and matrix form.
result Unified treatment of Riemannian geometry for optimization on manifolds.