Global covariance pooling improves deep CNNs' representation and generalization.
problem Capturing richer statistics of deep features for better representation and generalization.
method Integrates global covariance pooling into deep CNNs, addressing challenges with robust covariance estimation and geometry exploitation.
result Proposes MPN-COV Pooling and a Gaussian embedding network, achieving state-of-the-art performance.
Global catastrophe risk pools increase financial resilience by diversifying risk and including more countries.
problem Low- to middle-income countries rely heavily on foreign aid for recovery from extreme weather events, which is slow and uncertain.
method Developed a method to form global catastrophe risk pools that maximize risk diversification and select countries with low bilateral correlations or low shares in the pool risk.
result Global pooling increases risk diversification, lowers countries' shares in the pool risk, and increases the number of countries benefiting from risk pooling.
Compact bilinear pooling approximates covariance features for faster training.
problem Efficiently approximating covariance features for faster training.
method Compact bilinear pooling extended to polynomial approximations of covariance features.
result The proposed method achieves comparable accuracy with fewer dimensions.
Linear and Quadratic Discriminant analysis (LDA/QDA) are common tools for classification problems. For these methods we assume observations are normally distributed within group. We estimate a mean and covariance matrix for each group and classify using Bayes theorem. With LDA, we estimate a single, pooled covariance m…
Develops a novel global pooling framework using optimal transport.
problem Sub-optimal performance in global pooling operations.
method Regularized Optimal Transport (ROT) for generalized global pooling.
result ROTP layers can improve performance in various machine learning scenarios.
Global pooling, such as max- or sum-pooling, is one of the key ingredients in deep neural networks used for processing images, texts, graphs and other types of structured data. Based on the recent DeepSets architecture proposed by Zaheer et al. (NIPS 2017), we introduce a Set Aggregation Network (SAN) as an alternative…
Max-pooling architectures are theoretically analyzed and shown to be globally optimized and generalize well.
problem Theoretical understanding and optimization of max-pooling in deep learning architectures.
method Theoretical analysis of a convolutional max-pooling architecture, focusing on a pattern detection problem.
result Max-pooling architectures can be globally optimized and generalize well, even for highly over-parameterized models.
GSP improves global average pooling for deep metric learning by learning weights and selecting semantic entities.
problem Improving global average pooling for deep metric learning.
method Generalized Sum Pooling (GSP) method that learns weights and selects semantic entities.
result GSP improves metric learning performance on 4 popular benchmarks.
Graph neural network framework learns graph representations from node features and local structures.
problem Lack of hierarchical pooling to preserve graph structure in graph neural networks.
method Introduces a pooling operator based on graph Fourier transform to combine node features and local structures.
result Framework $\m$ improves graph classification performance on 6 benchmarks.
The paper tackles uncertainty quantification in multi-source settings.
problem Uncertainty quantification under covariate shift is challenging in multi-source settings.
method The paper addresses this by proposing two extensions of weighted conformal prediction: merge-based aggregation and data-pooling.
result Theoretical guarantees are provided for the proposed approaches, and experiments validate their effectiveness.
Convolutional neural networks converge quickly with gradient descent.
problem Learning efficient image classifiers with over-parameterized networks.
method Gradient descent for training over-parametrized CNNs with global average-pooling.
result Gradient descent quickly reduces the misclassification risk of CNNs.
Improved covariance matrix estimation for multiple classes with limited data.
problem Estimating covariance matrices for multiple classes with scarce data.
method Coupled regularized sample covariance matrix estimator (RSCM) that combines pooled SCM and scaled identity matrix for regularization.
result The coupled RSCM estimators outperform cross-validation in classification tasks with comparable accuracy but faster computation.
Dynamic Classifier Selection (DCS) techniques have difficulty in selecting the most competent classifier in a pool, even when its presence is assured. Since the DCS techniques rely only on local data to estimate a classifier's competence, the manner in which the pool is generated could affect the choice of the best cla…
Convolution and pooling improve kernel methods in image classification.
problem Understanding the interplay between approximation and generalization in convolutional architectures.
method Characterized RKHS of kernels with convolution, pooling, and downsampling, computed generalization error.
result Convolution and pooling operations trade off approximation with generalization power.
GSANet improves semantic segmentation accuracy with selective and global attention.
problem Semantic segmentation accuracy improvement.
method Global and selective attention mechanism with ASPP and sparsemax.
result GSANet achieves state-of-the-art accuracy on ADE20k and Cityscapes datasets.
EarnMore uses masked stock representations to train RL agents for customizable stock pools efficiently.
problem Training RL agents for customizable stock pools (CSPs) is computationally expensive and unstable.
method EarnMore introduces a mechanism to mask out stocks outside the target pool, learns meaningful stock representations, and uses a re-weighting mechanism to focus on favorable stocks.
result EarnMore significantly outperforms state-of-the-art baselines in profit metrics with over 40% improvement.
Bayesian framework for federated learning of neural networks without data pooling.
problem Scattered data across servers in federated learning problems.
method Bayesian nonparametric framework for neural networks, inference approach.
result Synthesize a more expressive global network with a single communication round.
A new framework for time series forecasting that adapts to varying patterns.
problem Forecasting multivariate time series with predictive heterogeneity.
method Validation-driven clustering framework that applies specialization based on out-of-sample predictive performance.
result Improves robustness to heavy-tailed errors and local anomalies.
Lie groupoid equivariant neural networks are a new type of neural network.
problem Designing neural networks that respect the structure of Lie groupoids.
method Introducing Lie groupoid equivariant convolutions and layers, and showing their equivalence to Lie algebroid-equivariant networks.
result Lie groupoid equivariant neural networks are equivalent to certain Lie algebroid-equivariant networks.
NDP improves GNN efficiency by coarsening graphs without losing structure.
problem Efficiently summarize graph data for deep learning models.
method Node Decimation Pooling (NDP) reduces graph density while preserving topology.
result NDP achieves comparable performance to state-of-the-art pooling methods but with improved efficiency.
Homotopy equivalence between formalities with different covariant derivatives.
problem Formality of Dolgushev depends on covariant derivative choice.
method Proved homotopy equivalence of L∞-morphisms twisted by gauge equivalent elements. result Globalized formalities with different covariant derivatives are homotopic.
Improved portfolio optimization method yields better risk-adjusted returns.
problem Optimizing global minimum variance portfolios with reduced risk.
method k-fold boosted k−BAHC covariance cleaning procedure for correlation matrices. result Our method outperforms other filtering methods in Sharpe ratios, despite higher turnover.
This paper optimizes multi-currency AMMs to reduce forex trading costs.
problem Lack of direct liquid markets for currency pairs.
method Constant-mean AMM architecture, hierarchical agglomerative clustering algorithm.
result Optimized multi-currency pools reduce trading costs by ~13%.
The paper analyzes the generalization error of min-norm interpolators in transfer learning with limited test samples.
problem Characterizing the generalization error of min-norm interpolators in transfer learning with limited test samples.
method Characterizes the bias and variance of pooled min-ℓ2-norm interpolation under covariate shift and model shift. result Shows that adding data can hurt when SNR is low and is beneficial at higher SNR levels under certain conditions.
Improved global minimum-variance portfolios using cross-validation for high-dimensional covariance estimation.
problem Ill-conditioned sample covariance matrix in high-dimensional data leads to suboptimal portfolios.
method Cross-validation technique to select tuning parameters for efficient covariance matrix estimation methods.
result Data-driven tuning parameters improve out-of-sample performance of global minimum-variance portfolios.
New CNN initialization scheme derived from modern architectures.
problem Stability of CNN model parameters initialization.
method Derived new initialization scheme from modern CNN architectures.
result New initialization method outperforms de facto standard schemes.
The study analyzes how covariance estimation errors affect the global minimum-variance portfolio under heavy-tailed distributions.
problem The impact of covariance estimation errors on the global minimum-variance portfolio under heavy-tailed distributions.
method Characterization of covariance-estimation error's effect on GMVP suboptimality, derivation of regret identity and bound, application to heavy-tailed returns.
result The decision geometry of GMVP regret is invariant to a (p-1)-dimensional projection of the error matrix, with invariance to the covariance-scale direction as an exact special case.
This work compresses reinforcement learning models for Atari games, improving localization.
problem Expensive deep neural networks in reinforcement learning.
method Model compression, global max-pooling, Actor-Mimic, weakly supervised localization.
result Compression reduces model size to 3% of original, enabling object localization.
Bayesian optimization improves efficiency with semi-supervised learning.
problem Efficiently find global optima of expensive functions.
method Density ratio estimation combined with semi-supervised learning.
result Improved accuracy in identifying global optima with unlabeled data.
The estimation of covariance matrices of gene expressions has many applications in cancer systems biology. Many gene expression studies, however, are hampered by low sample size and it has therefore become popular to increase sample size by collecting gene expression data across studies. Motivated by the traditional me…
Clustering stocks reduces estimation error in global minimum variance portfolio.
problem High estimation error in covariance matrix estimation.
method Bounded clustering to limit maximum cluster size.
result Reduction in out-of-sample volatility and gap between in-sample and out-of-sample volatility.
Tensor regression networks achieve high compression rate of neural networks while having slight impact on performances. They do so by imposing low tensor rank structure on the weight matrices of fully connected layers. In recent years, tensor regression networks have been investigated from the perspective of their comp…
Model improves covariance estimation from shared and distinct datasets.
problem Limited sample sizes and shared covariance structure across related datasets.
method Spiked covariance model with shared subspace, closed-form pooling weight, and asymptotic guarantees.
result Improves estimation of high-dimensional covariance matrices from related datasets.
Designing a covariance function that represents the underlying correlation is a crucial step in modeling complex natural systems, such as climate models. Geospatial datasets at a global scale usually suffer from non-stationarity and non-uniformly smooth spatial boundaries. A Gaussian process regression using a non-stat…
Gradients help find global optima in complex functions.
problem Finding global optima in functions with many local minima.
method A principle for generating search directions from non-local quadratic approximants based on gradients.
result The proposed algorithm and CMA-ES perform better than random reinitialized BFGS.
Study reveals how attention helps in signal recovery from sequence models using random matrix theory.
problem Signal recovery from sequence models with attention mechanisms.
method Analysis of sample covariance matrices constructed from pooled sequence representations with attention weights.
result Optimal attention weights maximize signal-to-noise ratio and improve signal recovery.
New model optimizes feature alignment, improving statistical and computational efficiency.
problem Statistical and computational challenges in feature alignment.
method Covariance alignment model, Gromov-Wasserstein algorithm.
result Gromov-Wasserstein algorithm is minimax optimal and practical for covariance alignment.
New algorithms solve feature-sparsity constrained PCA problem.
problem Feature selection and PCA simultaneously for low-rank covariance.
method Two algorithms: Algorithm 1 for low-rank covariance, Algorithm 2 for general covariance.
result Global convergence and approximation guarantees for new algorithms.
A new covariance estimator reduces dimensionality in high-dimensional undersized samples.
problem Challenges in estimating covariance matrices for high-dimensional data with fewer samples.
method Maximum Entropy Covariance (MEC) estimator that combines covariance matrices from different response categories.
result MEC estimator improves efficiency in dimension reduction methods like SIR and SAVE.
We consider the problem of analyzing the heterogeneity of clustering distributions for multiple groups of observed data, each of which is indexed by a covariate value, and inferring global clusters arising from observations aggregated over the covariate domain. We propose a novel Bayesian nonparametric method reposing …
GLSKF improves tensor completion by capturing both global and local variations.
problem Tensor completion with missing entries, especially in data with spatial or temporal side information.
method Integrates smoothness-constrained low-rank factorization with a locally correlated residual process.
result GLSKF achieves superior performance and scalability on real-world datasets.
Convolutional neural networks (CNNs) have achieved remarkable performance in many applications, especially in image recognition tasks. As a crucial component of CNNs, sub-sampling plays an important role for efficient training or invariance property, and max-pooling and arithmetic average-pooling are commonly used sub-…
Migration crisis, climate change or tax havens: Global challenges need global solutions. But agreeing on a joint approach is difficult without a common ground for discussion. Public spheres are highly segmented because news are mainly produced and received on a national level. Gain- ing a global view on international d…
Convolutional neural networks (CNN) have achieved state of the art performance on both classification and segmentation tasks. Applying CNNs to microscopy images is challenging due to the lack of datasets labeled at the single cell level. We extend the application of CNNs to microscopy image classification and segmentat…
We study generalized electric/magnetic duality in Abelian gauge theory by combining techniques from locally covariant quantum field theory and Cheeger-Simons differential cohomology on the category of globally hyperbolic Lorentzian manifolds. Our approach generalizes previous treatments using the Hamiltonian formalism …
We present a novel and hierarchical approach for supervised classification of signals spanning over a fixed graph, reflecting shared properties of the dataset. To this end, we introduce a Convolutional Cluster Pooling layer exploiting a multi-scale clustering in order to highlight, at different resolutions, locally con…
The paper proposes using network science to improve portfolio optimization by reducing noise in covariance estimation.
problem Noise in covariance estimation leads to suboptimal portfolio performance.
method The paper introduces SR-IFN, a network-based method to filter out noise from empirical covariance, enhancing portfolio optimization.
result The SR-IFN network improves portfolio performance by selecting peripheral, diversified assets and inversely weighting them based on centrality.
Bayesian optimization improves with nonstationary covariance functions.
problem Stationary covariance functions fail to capture prior information in high dimensions.
method Proposes nonstationary covariance functions to encode prior information and adaptively promote local exploration.
result Nonstationary covariance functions increase sample efficiency in high dimensions.