Describes geometry of positive configurations in limiting buildings.
problem Understanding positive representations and their limits in buildings.
method Uses positivity properties of Hitchin representations and Parreau's compactification.
result Explicitly describes the geometry of preferred apartments in limiting buildings.
Let X be a symmetric space of non-compact type or a locally finite, strongly transitive Euclidean building, and let B denote the geodesic boundary of X. We reduce the study of visual limits of maximal flats in X to the study of limits of apartments in the spherical building B: this defines a natural, geometric compacti…
Deep learning adapts HVAC models to new buildings.
problem Adapting thermal dynamics models to new buildings with limited data.
method Deep supervised domain adaptation (DSDA) using LSTM-based Sequence to Sequence model.
result Deep supervised domain adaptation improves predictive performance over learning from scratch.
Research proves limits on harmonic map orders into Euclidean buildings.
problem Limits on the possible orders of harmonic maps from surfaces to Euclidean buildings.
method Direct analysis of homogeneous maps and related spherical billiards problem.
result The order of harmonic maps is of the form km where k divides ∣W∣. The paper develops a method to predict the latent deterioration phase in limit order books before stress is observed.
problem Limit order books can transition rapidly from stable to stressed conditions, making it difficult to detect the latent deterioration phase.
method The paper formalizes a three-regime causal data-generating process and proposes a trigger-based detector combining MAX aggregation of complementary signal channels, a rising-edge condition, and adaptive thresholding.
result The proposed method achieves mean lead-time of +18.6 timesteps with perfect precision and moderate coverage, outperforming classical change-point and microstructure baselines.
Machine learning reduces wind tunnel testing costs for tall buildings.
problem Limited wind tunnel tests fail to fully reveal interference effects of tall buildings.
method Used machine learning techniques, including GANs, to predict pressure coefficients.
result GANs model based on 30% of dataset accurately predicts pressure coefficients under unseen conditions.
Study G-H limits of surfaces with boundary, focusing on same Euler characteristic.
problem Investigate Gromov-Hausdorff limits of compact surfaces with boundary.
method Focus on surfaces with same Euler characteristic, build on previous work on closed surfaces.
result Complete description and topological properties of limit spaces.
Estimating data limits easier than building algorithms to achieve them.
problem Achieving the fundamental limits of data processing.
method Case studies on binary classification, data compression, and prediction.
result Estimators of limits can be constructed with fewer samples than explicit algorithms to achieve limits.
Method upgrades limit theorems to mixing limit theorems for dynamical systems.
problem Improving limit theorems for dynamical systems.
method General method for upgrading limit theorems to mixing limit theorems.
result Mixing limit theorems for specific subbundles of the Kontsevich-Zorich cocycle.
Paper studies deep learning attacks on online APIs with limited data.
problem Adversarial machine learning threats on online APIs with strict rate limitations.
method Develops an active learning approach to build adversarial classifiers with limited training data.
result Active learning can build adversarial classifiers with small statistical difference from target classifiers using limited data.
This study converts BART to Gaussian process regression, revealing its limitations and potential improvements.
problem Understanding the Gaussian process limit of BART and its implications.
method Deriving and computing BART's prior covariance function, implementing the infinite trees limit as GP regression, and tuning hyperparameters.
result The Gaussian process limit of BART is inferior to standard BART but can be made competitive with proper hyperparameter tuning.
Global homeomorphism constructed from 3D Ricci limit spaces.
problem Global regularity of 3D Ricci limit spaces.
method Local pyramid Ricci flows and partial Ricci flows.
result Global homeomorphism to a smooth manifold.
Fast emulators built with neural search accelerate expensive scientific simulations.
problem Slow execution of accurate simulations limits scientific discovery.
method Neural architecture search to build accurate emulators with limited data.
result Simulations accelerated by up to 2 billion times in various scientific fields.
We consider sequences of open Riemannian manifolds with boundary that have no regularity conditions on the boundary. To define a reasonable notion of a limit of such a sequence, we examine "δ inner regions" which avoid the boundary by a distance δ. We prove Gromov-Hausdorff compactness theorems for sequences of the…
We use Ricci flow to obtain a local bi-Holder correspondence between Ricci limit spaces in three dimensions and smooth manifolds. This is more than a complete resolution of the three-dimensional case of the conjecture of Anderson-Cheeger-Colding-Tian, describing how Ricci limit spaces in three dimensions must be homeom…
Tests if market noise is explained by limit order book variables.
problem Determining if market microstructure noise is fully explained by specific limit order book variables.
method Compares two quasi-maximum likelihood estimators of volatility, one including residual noise and one not, in a nonparametric framework.
result Examines central limit theory of quasi-maximum likelihood estimation in the presence of residual noise.
Deep learning detects building defects from images.
problem Time-consuming, laborious, and expensive traditional building condition assessment.
method Convolutional Neural Networks (CNN) with class activation mapping (CAM) for object localisation.
result Robust model accurately detects and localises building defects.
We show that any grafting ray in Teichmüller space is (strongly) asymptotic to some Teichmüller geodesic ray. As an intermediate step we introduce surfaces that arise as limits of these degenerating Riemann surfaces. Given a grafting ray, the proof involves a Teichmüller ray with a conformally equivalent limit, and bui…
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.
Given a Riemann surface X=(Σ,J) we find an expression for the dominant term for the asymptotics of the holonomy of opers over that Riemann surface corresponding to rays in the Hitchin base of the form (0,0,⋯,tωn). Moreover, we find an associated equivariant map from the universal cover $(\tildeΣ,\tilde{J})…
Autoencoder neural networks reconstruct missing indoor environment data.
problem Missing data in building operation data sets.
method Three different autoencoder neural networks trained to reconstruct missing data.
result Reconstructing variables with average RMSEs of 0.42 °C, 1.30 % and 78.41 ppm.
Study Chabauty limits of subgroups of SL(n,Qp), focusing on parahoric and conjugate subgroups.
problem Classify and understand Chabauty limits of subgroups of SL(n,Qp). method Use various Levi decompositions and Bruhat–Tits buildings to classify limits.
result Found infinitely many non-conjugate Chabauty limits for n≥7. New examples of manifolds with positive scalar curvature and infinitely many poles.
problem Constructing manifolds with positive scalar curvature and understanding their limits.
method Extending previous examples to create new sequences of manifolds.
result Found new examples of manifolds with infinitely many poles and positive scalar curvature.
The paper analyzes SGD in high-dimensional networks, revealing new scaling limits.
problem Understanding SGD dynamics in high-dimensional networks.
method Analyzing the effective dynamics of SGD using recent work on the subject.
result A new correction term emerges at the critical scaling regime, changing the phase diagram.
Transfer learning improves clinical time series prediction with limited data.
problem Training deep RNNs for clinical tasks requires large labeled data and tuning.
method Transfer learning from pre-trained RNNs on multiple tasks to new tasks.
result Features from pre-trained RNNs improve model performance and robustness.
Paper proposes a method to improve building extraction from aerial images by adapting CNN models.
problem Limited generalization of CNN-based segmentation models for unseen images.
method Combines domain transfer and adversarial attack concepts to adapt input images to target images.
result Improves overall IoU and outperforms other methods in cross-dataset experiments.
DSLOB creates synthetic LOB data for benchmarking forecasting algorithms under distributional shifts.
problem Challenges in dealing with out-of-distribution limit order book data.
method Multi-agent market simulator to create labeled synthetic LOB dataset with and without market stress.
result Demonstrates the need for robust forecasting algorithms to handle distributional shifts.
Paper models limit order book with informed traders and market makers.
problem Modeling the limit order book with heterogeneous market participants.
method Agent-based model with four types of participants: informed traders, noise traders, informed market makers, and noise market makers. Based on Glosten-Milgrom and Huang-Rosenbaum-Saliba approaches.
result Derived the static limit order book characteristics and compared them with existing models.
Band-limited training reduces resource usage without sacrificing accuracy.
problem Resource constraints in training Convolutional Neural Networks (CNNs).
method Artificially constraining the frequency spectra of convolutional filters during training.
result CNNs can leverage lower-frequency components effectively, reducing resource usage.
The study examines the asymptotic behavior of extremal length in Teichmüller space.
problem Understanding the asymptotic behavior of extremal length along Teichmüller rays.
method Analyzing the limit of extremal length and deriving formulas for limiting Teichmüller distance and detour metric.
result An explicit formula for the limiting Teichmüller distance and a necessary and sufficient condition for Teichmüller rays to be asymptotic.
A new method builds sparse polynomial chaos expansions for models with dependent inputs.
problem Quantifying uncertainty in models with dependent inputs.
method Data-driven approach to construct orthonormal polynomials recursively based on input correlations.
result Reduces the number of observations and improves numerical stability and computational efficiency.
Paper confirms Thom's conjecture for nonlinear evolutions on manifolds.
problem Thom's gradient conjecture for nonlinear evolution equations.
method Extending and settling the conjecture in infinite dimensional problems using Łojasiewicz, L. Simon, and Kurdyka-Mostowski-Parusinski's foundational works.
result Uniqueness of the limiting direction and characterization of convergence rates for both classical and infinite dimensional settings.
Model predicts limit order book dynamics based on market participant interactions.
problem Understanding and predicting the dynamics of the limit order book in financial markets.
method Agent-based model with informed, noise, and market maker traders; deduces limit order book from interactions.
result Link between price dynamics, trade proportions, volume, spread, and equilibrium state.
A new method combines simple binary classifiers to build complex multiclass classifiers, achieving performance limits in a Gaussian setting.
problem Building a sophisticated multiclass classifier from simple binary decisions.
method Combining O(logK) simple binary classifiers to form a K-class classifier. result Explicit performance bounds across various decoding and dimensional regimes for a stylized Gaussian setting.
Enhances counterfactual explanations with more valid and informative saliency maps.
problem Lack of valid counterfactual explanations in existing models.
method Introduces a modified approach to CELS model by removing mask normalization.
result Demonstrates higher validity and more informative counterfactual explanations.
Paper improves model compression techniques without significant loss in performance.
problem Challenges in deploying large deep neural networks due to their size.
method Proposes principled approaches to improve model compression via rate distortion theory and novel objective functions.
result Proves the optimality of the proposed scheme for compressing one-hidden-layer ReLU neural networks.
Functional central limit theorem for kernel gradient flow and infinitesimal gradient boosting
problem Fluctuations of boosting processes around their deterministic limit
method Stochastic perturbation analysis of ODEs in Banach spaces
result Rescaled deviations converge to a Gaussian process
Paper proposes PI-DAE for missing data imputation in buildings using physics constraints.
problem Missing data in building energy modeling.
method Physics-informed Denoising Autoencoders (PI-DAE) with multivariate and univariate configurations.
result Enhanced interpretability and robustness to missing data rates.
Constructs knots from 3-manifolds with specified geometric limits.
problem Build knots from 3-manifolds with specific geometric properties.
method Constructs explicit families of knots converging to specified 3-manifolds.
result Constructs knots from geometrically finite 3-manifolds with one end.
ML improves flood forecasting by leveraging local data.
problem Human calibration, limited data, and computational difficulty.
method Transfer learning and ML for high-dimensional scenarios.
result ML systems achieve timely and accurate flood prediction.
A new VAE model identifies and estimates treatment effects with limited overlap.
problem Identifying and estimating treatment effects when subjects with certain features belong to a single treatment group.
method Developed a latent variable model to estimate a prognostic score, which is sufficient for treatment effects. The model is a new type of VAE called β-Intact-VAE.
result The model identifies individualized treatment effects and provides TE error bounds.
Unified model identifies and locates thoracic abnormalities with limited annotations.
problem Accurate identification and localization of thoracic abnormalities require large annotated datasets, which are expensive to acquire.
method Unified model that simultaneously identifies and localizes abnormalities using limited location annotations.
result Unified model significantly outperforms baseline in classification and localization tasks.
Simulates realistic execution and costs in limit order books.
problem Realistic simulation of limit order books for large-tick assets.
method Tractable representation of spread and volume imbalance; calibrated event timing; feedback mechanism for market impact.
result Simulator yields realistic behavior and sensitivity to execution parameters.
Energy is a limited resource which has to be managed wisely, taking into account both supply-demand matching and capacity constraints in the distribution grid. One aspect of the smart energy management at the building level is given by the problem of real-time detection of flexible demand available. In this paper we pr…
Finite-precision learning of anh networks is limited by the Monte Carlo rate.
problem Learning anh neural networks under finite precision method Using iterated anh activations to construct localized bump functions result No adaptive randomized algorithm can achieve higher convergence rate than Monte Carlo rate in finite precision
Paper proposes new methods for improving interatomic potentials.
problem Limitations of conventional SO(2) Linear architectures in MLIPs.
method Direct Cartesian construction, recursive Clebsch-Gordan construction, Edge Complex Product Basis, Radial Rotary Complex Attention.
result TECE-OAM-RRA-1.0 achieves SOTA performance on Matbench Discovery.
Blockchain trading faces limits due to time-consuming settlement, exposing arbitrageurs to price risk.
problem Time-consuming settlement in blockchain trading limits arbitrage opportunities.
method Analysis of Bitcoin network and order book data.
result Cross-exchange price differences coincide with high settlement latency and low default risk.
In this paper, we introduce an algorithm for performing spectral clustering efficiently. Spectral clustering is a powerful clustering algorithm that suffers from high computational complexity, due to eigen decomposition. In this work, we first build the adjacency matrix of the corresponding graph of the dataset. To bui…