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.

169,341 papers · 148 categories

Trend · papers per month

61122183244 · Jun 202019922001200920182026
48 results for crown domain

New proof of harmonic map existence from punctured surfaces to crowned hyperbolic targets.

problem Existence of harmonic maps from punctured surfaces to specific hyperbolic targets.
method Using Teichmüller theory and Minsky's work on limiting harmonic maps, constructing the conformal limit and proving existence.
result Existence of harmonic maps from any punctured Riemann surface to a given crowned hyperbolic target.

Efficiently verifies neural networks by handling neuron splits, improving speed and accuracy.

problem Handling neuron split constraints in incomplete neural network verification.
method β-CROWN, which optimizes parameters β to encode neuron splits and uses them in bound propagation.
result β-CROWN significantly speeds up verification while maintaining high accuracy.

New method CROWN-IBP combines IBP and CROWN for efficient verifiable robust neural networks.

problem Training verifiably robust neural networks is challenging and computationally expensive.
method CROWN-IBP combines interval bound propagation and linear relaxation for efficient training.
result CROWN-IBP achieves significant improvements in verifiable robustness on MNIST and CIFAR datasets.

CROWN certifies robustness of neural networks with general activation functions.

problem Certifying robustness of neural networks with general activation functions.
method Bounding activation functions with linear and quadratic surrogates, adaptively selecting surrogates for each neuron.
result Significantly improves certified lower bounds on ReLU networks compared to Fast-Lin.

Study on anti-de Sitter structures on surfaces with punctures.

problem Deformation of anti-de Sitter structures on surfaces with punctures.
method Parameterization of deformation space using Teichmüller spaces and quadratic differentials.
result Two parameterizations of the deformation space of wild globally hyperbolic anti-de Sitter structures.

Generalizes neural network verification by adding arbitrary cutting planes.

problem Handling general cutting plane constraints in neural network verification.
method Generalized bound propagation method (GCP-CROWN) that allows arbitrary cutting plane constraints.
result GCP-CROWN significantly improves neural network verification performance.

SLIC-UAV monitors forest recovery using UAVs and machine learning.

problem Challenges in monitoring forest recovery, especially in logged tropical forests.
method Novel pipeline for UAV imagery analysis, combining crown labelling, species classification, and superpixel segmentation.
result SLIC-UAV achieves high accuracy in species mapping, from 79.3% to 90.5%.

This paper studies deformations of hyperbolic surfaces with special structures.

problem Infinitesimal deformations of hyperbolic surfaces with boundary and ideal vertices.
method Description of the admissible cone of deformations in terms of the arc complex.
result Realization of the admissible cone and its faces as arc complexes for specific surface families.

The paper analyzes constrained optimal portfolios in high dimensions using novel statistical learning techniques.

problem Forming optimal portfolios with constraints in high-dimensional asset spaces.
method CROWN method integrating factor models with nodewise regression for estimation in large dimensions.
result Demonstrates estimation consistency and convergence rates for constrained portfolio weights, risk, and Sharpe Ratio.

Study modular geodesics and wedge domains in non-compactly causal symmetric spaces.

problem Understanding the geometric implementation of modular group in symmetric spaces.
method Analyzing the flow generated by Euler elements and their geometric properties.
result The wedge region W is connected and coincides with the observer domain under certain conditions.

IBP-R improves verified adversarial robustness with simple, effective interval bound propagation.

problem Improving verifiability of adversarially trained networks.
method Coupling adversarial attacks with interval bound propagation for minimized verification gap.
result State-of-the-art verified robustness-accuracy trade-offs for small perturbations on CIFAR-10.

Study profitable optimal mean reversion trading strategies in US equity market.

problem Profitability of optimal mean reversion trading strategies in US equity market.
method Apply maximum likelihood method to construct optimal static pairs trading portfolio matching Ornstein-Uhlenbeck process. Rigorously estimate parameters and generate contrarian trading signals. Optimize thresholds and in-sample period length through multiple tests.
result High Sharpe ratios (above 1.9) achieved in nine good pairs examples, with CCI and HCP achieving a Sharpe ratio of 2.326 during in-sample period and 2.425 in out-of-sample test.

A Morse 2-function is a generic smooth map from a manifold M of arbitrary finite dimension to a surface B. Its critical set maps to an immersed collection of cusped arcs in B. The aim of this paper is to explain exactly when it is possible to move these arcs around in B by a homotopy and to give a library of examples w…

2014-11-06abs ↗pdf ↗

CNN-Cert efficiently certifies robustness of CNNs, achieving significant speed-ups.

problem Verifying robustness of neural networks, especially convolutional neural networks, against adversarial perturbations.
method General and efficient framework that handles various architectures and activation functions, achieving up to 17 and 11 times speed-up compared to state-of-the-art algorithms.
result Achieves similar or better verification bounds compared to state-of-the-art algorithms while being significantly faster.

PROVEN extends neural network robustness verification to probabilistic settings.

problem Quantifying robustness of neural networks under probabilistic noise distributions.
method PROVEN: Probabilistic Verification of Neural Networks (PROVEN) with statistical guarantees.
result PROVEN achieves up to 75% improvement in robustness certification compared to worst-case methods.

The paper proves a grafting theorem for meromorphic projective structures and shows the monodromy map is a local homeomorphism.

problem Understanding projective structures on Riemann surfaces with poles.
method Proves a grafting theorem involving crowned hyperbolic surfaces and uses the monodromy map to a decorated character variety.
result The monodromy map to the decorated character variety is a local homeomorphism.

The article explores causal structures in symmetric spaces and their relation to AQFT.

problem Understanding causal structures in symmetric spaces and their applications in AQFT.
method Classification of reductive causal symmetric spaces using Euler elements and 3-grading.
result Extraction of real Matsuki crowns and description of stabilizer groups of Euler elements.

Weyl's 1918 geometry proposal revisited in modern physics.

problem Revisiting Weyl's 1918 geometry proposal in modern physics.
method Reconsideration of Weyl's scale gauge in high energy physics and gravitation theory.
result Weyl geometry has regained interest in modern physics, particularly in particle physics and cosmology.

HYDRA prunes robust neural networks to improve both benign and adversarial robustness.

problem Lack of robustness against adversarial attacks and large neural network size in deep learning.
method HYDRA integrates pruning techniques with adversarial training and verifiable robust training objectives.
result HYDRA achieves compressed networks with state-of-the-art benign and robust accuracy.

ECBMs unify concept-based interpretations in deep learning models.

problem Suboptimal final accuracy and lack of concept interaction and conditional dependencies.
method ECBMs use a set of neural networks to define joint energy, enabling concept correction and conditional dependency quantification.
result ECBMs achieve higher accuracy and richer concept interpretations compared to state-of-the-art methods.

Automates perturbation analysis for neural networks, enabling certified robustness on complex architectures.

problem Limited applicability of existing perturbation analysis methods to complex neural network architectures.
method Developed an automatic framework to generalize LiRPA algorithms to any neural network structure, enabling loss fusion and state-of-the-art certified defense results.
result Demonstrated LiRPA based certified defense on Tiny ImageNet and Downscaled ImageNet.

Paper proposes faster certified robust training methods with short warmup.

problem Certified robust training methods require long warmup schedules, making training costly.
method Proposes three improvements: new weight initialization, BN, and regularization.
result Achieves 65.03% verified error on CIFAR-10 and 82.36% on TinyImageNet with short warmup.

Method generates intermediate domains to align source and target domains.

problem Challenges of domain adaptation with significant domain divergence.
method Progressive domain augmentation via domain interpolation and multiple subspace alignment.
result Achieves state-of-the-art performance on multiple domain adaptation tasks.

Proposes a model to improve multi-domain recommender systems.

problem Challenges in transferring knowledge between domains in recommender systems.
method Generative adversarial networks (GANs), Variational Autoencoders (VAEs), and Cycle-Consistency (CC) for weight-sharing.
result Improves performance of multi-domain recommender systems by capturing both similarities and differences among domains.

D2V learns domain-specific embeddings for domain generalization.

problem Learning decision functions across multiple related domains with limited labeled data.
method Proposes a neural network architecture, Domain2Vec (D2V), that learns domain-specific embeddings and uses them for generalization.
result D2V outperforms other algorithms in domain generalization tasks for image classification.

CUDA CTDR tackles unsupervised domain adaptation without domain alignment.

problem Lack of direct methods for unlabeled target domain classification.
method Jointly learns CTDR on source and target distributions using contradistinguish loss and supervised loss.
result CUDA CTDR achieves state-of-the-art results on various domain adaptation datasets.

Method infers domain-specific models without domain semantic descriptors.

problem Poor performance of standard supervised learning methods in unseen domains.
method Introduces latent domain vectors and neural networks for optimization.
result Inference of appropriate domain-specific models without semantic descriptors.

CoDAG combines domain adaptation and generalization for unsupervised continual domain shift learning.

problem Acquiring knowledge in unsupervised continual domain shift learning.
method Complementary Domain Adaptation and Generalization (CoDAG) framework.
result CoDAG outperforms state-of-the-art models in all datasets and evaluation metrics.

DCASE 2022 Task 2 tackles domain shifts in ASD for machine condition monitoring.

problem Domain shifts change acoustic characteristics, affecting ASD performance.
method Domain generalization techniques to detect anomalies across unknown domains.
result Two types of domain generalization techniques were identified and analyzed.

Extends polydisk theorem to Hartogs domains over symmetric domains.

problem Rigidity phenomena in Riemannian manifolds.
method Extension of polydisk theorem to Hartogs domains over arbitrary symmetric domains.
result Dual of a Hartogs domain over a bounded symmetric domain admits no totally geodesic immersion into any compact Riemannian manifold.

Adaptive multi-domain learning reduces parameter count for efficient deep learning.

problem Different domains have varying complexity, leading to inefficient model training.
method Proposes adaptive parameterization to reduce model complexity without sacrificing performance.
result Efficient multi-domain learning solutions with far fewer parameters.

CROSSGRAD learns general classifiers from multi-domain data without adaptation.

problem Learning classifiers that generalize across different domains.
method Cross-gradient training using domain-guided perturbations and Bayesian sampling.
result CROSSGRAD achieves better generalization to unseen domains compared to existing methods.

Proposes novel losses for fine-grained categorical domain adaptation.

problem Fine-grained alignment of categories across domains in unsupervised domain adaptation.
method Joint category-domain classifier with adversarial training losses for both domain and category levels, and vicinal domain adaptation.
result Achieves state-of-the-art performance on benchmark datasets.

Improves unsupervised domain adaptation by mixing source and target domains.

problem Improves unsupervised domain adaptation by mixing source and target domains.
method Enforces training constraints across domains using mixup formulation and feature-level consistency regularizer.
result Significantly improves state-of-the-art performance on image classification and human activity recognition tasks.