Ladder Networks improve semi-supervised hyperspectral image classification.
problem Semi-supervised hyperspectral image classification with limited labeled data.
method Jointly optimizing a supervised and unsupervised cost in a Ladder Network.
result Convolutional Ladder Network achieves state-of-the-art performance with minimal labeled data.
Novel model improves semi-supervised learning with minimal labeled data.
problem Efficiently leveraging unlabeled data for semi-supervised learning.
method Fuses ladder networks and virtual adversarial training (VAT) with layer-wise virtual adversarial noise.
result Near-supervised accuracy achieved with minimal labeled data.
Adversarial noise improves Ladder Network's classification performance.
problem Improving classification performance of neural networks.
method Adversarial noise added to Ladder Network architecture for semi-supervised learning.
result State of the art classification performance achieved.
Recurrent Ladder Networks improve iterative inference and temporal modeling.
problem Complex learning tasks requiring iterative inference and temporal modeling.
method Proposes a recurrent extension of Ladder networks.
result Shows close-to-optimal results on temporal modeling of video data and competitive results on music modeling.
A new inference model improves training of deep VAEs.
problem Training deep VAEs with many layers is difficult.
method Ladder Variational Autoencoder, recursively correcting generative distribution.
result Improves predictive log-likelihood and lower bound.
Mack's estimator improves chain ladder prediction for large exposure insurance models.
problem Uncertainty quantification in compound Poisson loss models.
method Large exposure asymptotics applied to Mack's estimator.
result Chain ladder prediction uncertainty can be quantified without model assumptions.
We combine supervised learning with unsupervised learning in deep neural networks. The proposed model is trained to simultaneously minimize the sum of supervised and unsupervised cost functions by backpropagation, avoiding the need for layer-wise pre-training. Our work builds on the Ladder network proposed by Valpola (…
Characterizes quasiconformally homogeneous ladder surfaces.
problem Characterize quasiconformally homogeneous Riemann surfaces.
method Breaks the problem into four cases and proves one case.
result Every quasiconformally homogeneous ladder surface is quasiconformally equivalent to a regular cover of a closed surface.
A method for analysing the risk of taking a too low reserve level by use of Chain Ladder method is developed. We give an answer to the question of how much safety loading in terms of the Chain Ladder standard error has to be added to the Chain Ladder reserve in order to reach a specified security level in loss reservin…
We examine spaces of connected tri-/univalent graphs subject to local relations which are motivated by the theory of Vassiliev invariants. It is shown that the behaviour of ladder-like subgraphs is strongly related to the parity of the number of rungs: there are similar relations for ladders of even and odd lengths, re…
Study gluing of Lorentzian length spaces and their causal ladder properties.
problem Compatibility of Lorentzian amalgamation with length space properties.
method Conditions for gluing Lorentzian length spaces and criteria for causal ladder preservation.
result Gluing of Lorentzian length spaces yields again a Lorentzian length space under certain conditions.
Talked about the Veech group of a specific surface.
problem Identifying the Veech group of a translation surface of infinite type.
method Analyzing the golden ladder surface.
result Answered a question posed by Hooper and Treviño.
This work defines a new function space for multi-layer neural networks.
problem Characterizing the function space of multi-layer neural networks.
method Defining a neural Hilbert ladder (NHL) as an infinite union of reproducing kernel Hilbert spaces (RKHSs).
result Established theoretical properties of the new function space, including generalization guarantees and dynamics of random fields.
We classify all groups which can occur as the orientation preserving topological symmetry group of some embedding of a Möbius ladder graph in S3.
Pole ladder improves parallel transport in affine spaces, showing exact results in symmetric spaces.
problem Improving numerical stability and accuracy in parallel transport algorithms.
method Developed a third-order parallel transport scheme using pole ladder in affine connection spaces, showing exact results in symmetric spaces.
result Pole ladder is a third-order scheme in general affine connection spaces and is exact in locally symmetric spaces.
New method for individual claims reserving using machine learning.
problem Traditional claims reserving methods are limited in individual claim prediction.
method Restructured data utilization for CL prediction, using multi-period factors.
result Neural networks applied for individual claims reserving.
New ladder methods improve numerical accuracy in parallel transport on manifolds.
problem Lack of convergence analysis for ladder schemes on manifolds.
method Taylor approximations and iterative constructions of geodesic parallelograms.
result Ladder methods converge quadratically with quadratic speed.
The paper finds pseudo-Anosov-like maps on an infinite ladder surface.
problem Exploring dynamics on infinite surfaces.
method Lifts Penner-type pseudo-Anosov maps from a closed surface to an infinite ladder surface.
result Existence and properties of pseudo-Anosov-like maps on the infinite ladder surface.
VLN generates future video frames efficiently with lateral connections.
problem Efficiently generating future video frames.
method Neural encoder-decoder model with lateral connections, including recurrent and feedforward lateral connections.
result VLN achieves competitive results on the Moving MNIST dataset.
LADDER improves DG by reweighting domain-specific classifiers.
problem Challenges of domain generalization when causal mechanisms vary across domains.
method LADDER learns causal and style representations, reweights classifiers at inference.
result LADDER achieves gains in accuracy on various DG tasks.
The full causal ladder of spacetimes is constructed, and their updated main properties are developed. Old concepts and alternative definitions of each level of the ladder are revisited, with emphasis in minimum hypotheses. The implications of the recently solved ``folk questions on smoothability'', and alternative prop…
A new portfolio weighting strategy outperforms others, following Tukey's ladder.
problem The performance of market capitalization-weighted portfolios.
method Investigated Tukey's transformational ladder for portfolio weights.
result 1/x^2 weighting strategy outperforms all others, with 18% cumulative growth.
Method solves Gaussian graphical models on ladder graphs efficiently.
problem Solving Gaussian graphical models on ladder graphs efficiently.
method Proposes a method that depends on the position of zeros in local covariance matrices.
result Efficiently solves Gaussian graphical models on ladder graphs under certain conditions.
This paper introduces a new market making approach using scaled beta distributions.
problem Inventory management challenges faced by market makers.
method Scaled beta distribution policies for flexible market making actions.
result Flexibility in volume distribution across price intervals improves market making performance.
New causal distances improve evaluation of causal discovery algorithms.
problem Evaluating causal discovery algorithms using graphical distances is limited.
method Defined causal distances based on causal distributions rather than graphical structure.
result Improved evaluation of causal discovery algorithms on synthetic and real-world datasets.
Chain-ladder reserving is sensitive to outliers, leading to unreliable estimates.
problem Sensitivity of loss reserving techniques to outliers.
method Derivation of impact functions for reserves and mean squared errors of prediction under Mack's Model.
result Impact of outliers varies widely in a loss triangle and depends on other cells.
VLAC clusters data hierarchically, outperforming GMM.
problem Clustering with multiple attributes or hierarchies.
method Disentangled latent representations for hierarchical clustering.
result VLAC outperforms Gaussian Mixture Models in clustering accuracy.
The leaderboard in machine learning competitions is a tool to show the performance of various participants and to compare them. However, the leaderboard quickly becomes no longer accurate, due to hack or overfitting. This article gives two pieces of advice to prevent easy hack or overfitting. By following these advice,…
New method simplifies individual claims reserving.
problem Insufficient flexibility and robustness in existing methods.
method Building on classical chain-ladder method, introduces new perspective.
result Advances toward a new standard for micro-level reserving.
Study shows stick numbers for specific graphs and explains a protein structure.
problem Determining the minimum number of sticks for knotless embeddings of graphs.
method Analyzing specific graphs like K4 and K5, and using probability theory for K3,3.
result Minimum stick numbers for K4 and K5, and probability of a specific protein structure.
Proves colored HOMFLYPT polynomial is q-holonomic.
problem Proving the q-holonomic property of colored HOMFLYPT polynomials. method Skew Howe duality and Poincare-Birkhoff-Witt computation of quantum group.
result Existence of (a,q) super-polynomial for knots. Novel power transform unifies various mathematical functions.
problem Normalizing and standardizing datasets.
method Presented a novel power transform.
result Unified various mathematical functions.
Paper proposes robust methods to detect and treat outliers in multivariate loss reserving.
problem Distortion of traditional reserving techniques by outliers in past claims data.
method Two robust bivariate chain-ladder techniques: Adjusted Outlyingness and Bagdistance.
result Improved accuracy in estimating outstanding claim liabilities through robust methods.
CGDL improves open set recognition by learning conditional Gaussian distributions.
problem Handling unknown samples in real-world recognition tasks.
method Conditional Gaussian Distribution Learning (CGDL) with probabilistic ladder architecture.
result CGDL significantly outperforms baseline methods on standard image datasets.
We describe the geometrical ladder of equations for Abelian bundles and gerbes, as well as higher generalisations, in terms of the cohomology of an operator that combines de Rham and Cech cohomology.
The paper explores Finsler-type objects and their variational problems on spacetimes.
problem Generalizing Einstein equations to the Finsler setting.
method Study of the ladder of Finsler-type objects and their variational problems.
result Application of the ladder structure to variational proposals for Finsler spacetimes.
The paper introduces a test to distinguish spatial graphs based on their knot diagrams.
problem Distinguishing isotopic spatial graphs from diagrams.
method Using the writhe of knot diagrams from cycles in the graph.
result A necessary condition for distinguishing isotopic spatial graphs.
This paper finds minimal sets of generators for mapping class groups of specific surfaces.
problem Finding minimal sets of generators for mapping class groups of infinite-type surfaces.
method Analyzing specific surfaces S(n) to determine minimal sets of generators. result Minimal sets of generators for Map(S(n)) are identified for n≥8 (3 elements), n≥3 (4 elements), and S(1) (2 elements). DHRL learns interpretable features from visual data.
problem Limited use of deep learning in basic research for interpretable features.
method Generative model chaining, ladder network architecture, latent space regularization.
result DHRL generates disentangled hierarchical features from small datasets.
The intention of this paper is to estimate a Bayesian distribution-free chain ladder (DFCL) model using approximate Bayesian computation (ABC) methodology. We demonstrate how to estimate quantities of interest in claims reserving and compare the estimates to those obtained from classical and credibility approaches. In …
The paper tackles data scarcity in deep learning by generating new samples using RBM and VAE.
problem Data scarcity in deep learning scenarios.
method Used Restricted Boltzmann Machines (RBM) and Variational Auto-encoders (VAE) as generative models to increase the training set.
result RBM outperformed VAE in generating new samples for training a classifier with good generalization capabilities.
New theory explains contrastive learning via overlapping augmented views.
problem Lack of theoretical understanding of contrastive learning.
method Augmentation overlap perspective to improve downstream performance.
result Asymptotically closed bounds for downstream performance under weaker assumptions.
Paper proposes a new reserving model using machine learning techniques.
problem Managing uncertainties in premium sufficiency and reserves for future claims.
method Stacked model combining Gradient Boosting, Random Forest, Artificial Neural Networks, and log-normal approach.
result The proposed model improves traditional reserving techniques, leading to more accurate reserving risk assessment.
A new algorithm for parallel transport on shape spaces is presented and compared to existing methods.
problem Statistical analysis of shape data, especially in time series and optimization.
method Pole ladder algorithm for parallel transport on Kendall shape spaces, compared to integration methods.
result The pole ladder algorithm is a more efficient method for parallel transport.
A new filtration of the spaces of tri-/univalent graphs B_m^u that occur in the theory of finite-type invariants of knots and 3-manifolds is introduced. Combining the results of the two preceding articles, the quotients of this filtration are modeled by spaces of graphs with two types of edges and four types of vertice…
Paper derives and applies a parallel transport equation on Lie groups.
problem Efficiently solving parallel transport on Lie groups with left-invariant metrics.
method Derives a parallel transport equation in Lie algebra, applies it to SE(3), and compares to existing methods.
result Stable and efficient parallel transport implementation on Lie groups.
The paper studies mapping class groups of cyclic covers and their liftable counterparts.
problem Understanding the structure of liftable mapping class groups for cyclic covers.
method Analyzes the liftable mapping class groups of regular cyclic covers and derives explicit generating sets.
result The family of self-normalizing subgroups {LModpk(Sg)}k≥2 forms an infinite family in Mod(Sg). Simplified A-polynomial calculation for twisted knots.
problem Calculating A-polynomials for twisted knots.
method Observation of exchange relations in cluster algebra and proof of Laurent phenomenon.
result Simplified method for calculating A-polynomials for twisted knots.