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.
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.
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.
The use of unsupervised data in addition to supervised data in training discriminative neural networks has improved the performance of this clas- sification scheme. However, the best results were achieved with a training process that is divided in two parts: first an unsupervised pre-training step is done for initializ…
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.
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 (…
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.
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.
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.
We used the Ladder Network [Rasmus et al. (2015)] to perform Hyperspectral Image Classification in a semi-supervised setting. The Ladder Network distinguishes itself from other semi-supervised methods by jointly optimizing a supervised and unsupervised cost. In many settings this has proven to be more successful than o…
We classify all groups which can occur as the orientation preserving topological symmetry group of some embedding of a Möbius ladder graph in S3.
Parallel transport is an important step in many discrete algorithms for statistical computing on manifolds. Numerical methods based on Jacobi fields or geodesics parallelograms are currently used in geometric data processing. In this last class, pole ladder is a simplification of Schild's ladder for the parallel transp…
Semi-supervised learning (SSL) partially circumvents the high cost of labeling data by augmenting a small labeled dataset with a large and relatively cheap unlabeled dataset drawn from the same distribution. This paper offers a novel interpretation of two deep learning-based SSL approaches, ladder networks and virtual …
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.
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…
We present the Video Ladder Network (VLN) for efficiently generating future video frames. VLN is a neural encoder-decoder model augmented at all layers by both recurrent and feedforward lateral connections. At each layer, these connections form a lateral recurrent residual block, where the feedforward connection repres…
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.
We propose a recurrent extension of the Ladder networks whose structure is motivated by the inference required in hierarchical latent variable models. We demonstrate that the recurrent Ladder is able to handle a wide variety of complex learning tasks that benefit from iterative inference and temporal modeling. The arch…
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.
Variational Autoencoders are powerful models for unsupervised learning. However deep models with several layers of dependent stochastic variables are difficult to train which limits the improvements obtained using these highly expressive models. We propose a new inference model, the Ladder Variational Autoencoder, that…
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.
We prove that the HOMFLYPT polynomial of a link, colored by partitions with a fixed number of rows is a q-holonomic function. Specializing to the case of knots colored by a partition with a single row, it proves the existence of an (a,q) super-polynomial of knots in 3-space, as was conjectured by string theorists. …
Novel power transform unifies various mathematical functions.
problem Normalizing and standardizing datasets.
method Presented a novel power transform.
result Unified various mathematical functions.
Over the past half-century, the empirical finance community has produced vast literature on the advantages of the equally weighted S\&P 500 portfolio as well as the often overlooked disadvantages of the market capitalization weighted Standard and Poor's (S\&P 500) portfolio (see \cite{Bloom}, \cite{Uppal}, \cite{Jacobs…
New method uses neural nets in Hilbert space for option pricing on flow forwards.
problem Pricing options on flow forwards with neural networks in Hilbert space.
method Optimization problem in Hilbert space solved by a novel feedforward neural network architecture.
result Excellent numerical efficiency and superior performance over classical methods.
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,…
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.
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.
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.
This note explains when neural networks can be seen as Gaussian processes.
problem Understanding the relationship between neural networks and Gaussian processes.
method Formulating a Gaussian process regression based on neural network outputs and analyzing the resulting posterior mean functions.
result The posterior mean functions of neural networks follow a Gaussian process in certain cases, providing an interpretation of reproducing kernel Hilbert spaces.
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 shows how multi-task learning in neural networks is similar to kernel regression and Hilbert spaces.
problem Understanding the solutions to multi-task shallow ReLU neural network learning problems.
method Analyzing the properties of solutions to multi-task shallow ReLU neural network learning problems, proving uniqueness and equivalence to minimum-norm interpolation problems in Hilbert spaces.
result The solutions to multi-task neural network interpolation problems are almost always unique and coincide with the solution to a minimum-norm interpolation problem in a Sobolev (Reproducing Kernel) Hilbert Space.
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.
In clustering we normally output one cluster variable for each datapoint. However it is not necessarily the case that there is only one way to partition a given dataset into cluster components. For example, one could cluster objects by their colour, or by their type. Different attributes form a hierarchy, and we could …
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). HOPE uses Hilbert space to deconstruct deep network representations.
problem Deconstructing learned representations in deep networks is challenging.
method Introduces Hilbert Operator for Progressive Encoding (HOPE) to deconstruct network weights.
result HOPE provides an unbiased approach to network compression and fine-tuning.
RNNs are reinterpreted as kernel methods using neural ODEs.
problem Improving generalization and stability of RNNs.
method Connecting RNNs to neural ODEs and reproducing kernel Hilbert spaces.
result RNNs can be viewed as linear functions of a specific feature set.
Poor approximators found in neural networks and random feature models.
problem Understanding why certain neural networks and models perform poorly in approximating functions.
method Established a scale separation of Kolmogorov width type and applied it to neural networks and random feature models.
result Reproducing kernel Hilbert spaces and two-layer neural networks are poor L2-approximators for certain functions. 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.
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.
GCNNs on homogeneous spaces use vector bundles and Hilbert spaces.
problem Learning data on homogeneous spaces with global symmetry.
method Analysis of G-equivariant convolutional layers on homogeneous G/K spaces, using vector bundles and reproducing kernel Hilbert spaces. result A precise criterion for expressing G-equivariant layers as convolutional layers, leading to stronger results for some groups. This research explores complex-valued neural networks and their implementation.
problem The challenges of implementing complex-valued neural networks and their potential for non-complex data.
method Detailed theory and implementation of CVNN, including Wirtinger calculus, complex backpropagation, and modules like complex layers and activation functions. Python implementation using cvnn toolbox.
result Demonstrates the potential of CVNN for non-complex data through simulations.
Neural operators achieve fast convergence rates for solving PDEs.
problem Solving partial differential equations (PDEs) efficiently.
method Two-layer neural operators with gradient descent analysis in RKHS.
result Fast convergence rates are minimax optimal for early-stopped GD.
This study examines the practical equivalence of Laplace and neural tangent kernels.
problem Understanding the practical equivalence of Laplace and neural tangent kernels.
method The study matches the kernels exactly and by matching posteriors of a Gaussian process. It also analyzes the kernels in R^d and experiments with them in regression tasks.
result The Laplace and neural tangent kernels are practically equivalent.