A new method samples CGMY processes efficiently by decomposing their time changes.
problem Sampling CGMY processes with finite or infinite variation.
method Exploiting time change representation, decomposing into two independent components.
result The method is advantageous over existing methods in simulations.
Proposes a method to predict responses from covariates over time.
problem Predicting responses from covariates with changing conditional distributions over time.
method Invariant Subspace Decomposition (ISD) framework that splits the conditional distribution into time-invariant and time-dependent components.
result The decomposition can be used for zero-shot and time-adaptation prediction tasks.
The study examines how different interpolation methods affect the decomposition of life insurance surplus.
problem The impact of different interpolation methods on the decomposition of life insurance surplus.
method The study uses the IASU decomposition method to analyze the effects of different interpolation methods (Lee-Carter and linear) on the surplus decomposition.
result Lee-Carter and linear interpolation yield almost identical decompositions, while constant approximations result in different decompositions.
Proposes tPARAFAC2 for tracking evolving patterns in time-evolving data.
problem Lack of temporal regularization in tensor factorizations for capturing evolving patterns.
method Temporal PARAFAC2 (tPARAFAC2) with temporal regularization.
result tPARAFAC2 accurately captures evolving patterns better than existing methods.
Develops a theory of common decomposition for correlated Brownian motions.
problem Tackles the modeling of correlated Brownian motions in financial applications.
method Uses change of time method to represent correlated Brownian motions as a triplet of processes.
result Shows equivalent conditions for the triplet being independent and proposes a new method for constructing correlated Brownian motions.
OCTen compresses and speeds up online tensor decomposition.
problem Handling dynamic, growing datasets efficiently.
method Compression-based online parallel CP decomposition.
result OCTen achieves similar or better accuracy with up to 40-200% less memory.
CDSSD detects sparse changes in partially observable data streams.
problem Online change detection of sparse changes in partially observable high-dimensional data streams.
method Smooth-sparse decomposition, spike-slab variational Bayesian inference, adaptive sampling via Thompson sampling.
result CDSSD effectively detects sparse changes in partially observable data streams.
RobustSTL decomposes time series robustly to detect anomalies and forecast.
problem Handling complex time series with seasonality fluctuation, trend shifts, and data anomalies.
method RobustSTL uses least absolute deviations regression for trend extraction and non-local seasonal filtering for seasonality extraction.
result RobustSTL outperforms existing solutions in synthetic and real-world time series datasets.
Decomposes portfolio returns into drift and asset price distribution changes.
problem Understanding efficient markets through portfolio returns and asset price distributions.
method Continuous semimartingale price representations and accounting identity.
result Existence of an asset pricing factor emerges from an accounting identity across various economic and financial environments.
DMD separates mixed time series with uncorrelated components.
problem Separating mixed time series with uncorrelated components.
method Dynamic Mode Decomposition (DMD) applied to a data matrix of mixed time series.
result DMD can approximate the mixing matrix of uncorrelated time series.
We propose a probabilistic modeling framework for learning the dynamic patterns in the collective behaviors of social agents and developing profiles for different behavioral groups, using data collected from multiple information sources. The proposed model is based on a hierarchical Bayesian process, in which each obse…
This paper studies subordinate Ornstein-Uhlenbeck (OU) processes, i.e., OU diffusions time changed by Lévy subordinators. We construct their sample path decomposition, show that they possess mean-reverting jumps, study their equivalent measure transformations, and the spectral representation of their transition semigro…
Time-subordinated Brownian motion models improve financial market stochastic distribution.
problem Improving stochastic distribution modeling in financial markets.
method Fourier theory and methodology for time-subordinated Brownian motion models, extending real domain to complex plane.
result Characterization and direct study of stochastic time-change from full process.
The present paper introduces a jump-diffusion extension of the classical diffusion default intensity model by means of subordination in the sense of Bochner. We start from the bi-variate process (X,D) of a diffusion state variable X driving default intensity and a default indicator process D and time change it wi…
New method speeds up CNN inference by storing centroids instead of full filters.
problem Reduction of time and space complexity in CNN inference.
method Centroid filter quantization for convolutional layers.
result 2.9 times better computational gain on ImageNet benchmark.
In this paper we propose a general derivative pricing framework which employs decoupled time-changed (DTC) Lévy processes to model the underlying asset of contingent claims. A DTC Lévy process is a generalized time-changed Lévy process whose continuous and pure jump parts are allowed to follow separate random time scal…
We analyse the dependence of stock return cross-correlations on the sampling frequency of the data known as the Epps effect: For high resolution data the cross-correlations are significantly smaller than their asymptotic value as observed on daily data. The former description implies that changing trading frequency sho…
MOSAIC detects change points in dynamic networks with low-rank and sparse changes.
problem Detecting change points in dynamic networks with specific structural properties.
method Eigen-decomposition-based test with screened signals and residual-based adjustment.
result MOSAIC achieves minimax-optimal detection and testing rates.
Decomposes returns of bottom-ranked assets, finds excess returns.
problem Excess returns of bottom-ranked assets not explained by existing models.
method Decomposes returns into rank crossovers and relative price changes.
result Excess returns of bottom-ranked assets are driven by relative price changes, not rank.
The article uses Karhunen-Loève decomposition and Filtered Historical Simulation to manage volatility risk in interest rate options.
problem Managing volatility risk in interest rate options with changing implied volatilities.
method Karhunen-Loève decomposition and Filtered Historical Simulation.
result The projections on principal components provide a more accurate prediction of Value at Risk (VaR).
The paper analyzes sensitivities of cash flows using PDEs and Hansen-Scheinkman decomposition.
problem Large-time sensitivities of cash flows in quantitative finance.
method PDE representation of pricing operator with Hansen-Scheinkman decomposition.
result Detailed convergence rates of sensitivities are provided.
Decomposable-Net compresses neural networks without retraining for various sizes.
problem Performance degradation when changing model size after training.
method Decomposes weight matrices via SVD and adjusts ranks for different sizes.
result Maintains and improves performance across multiple model sizes.
This paper continues the study of decompositions of a smooth 4-manifold into two handlebodies with handles of index ≤2. Part I gave existence results in terms of spines and chain complexes over the fundamental group of the ambient manifold. Here we assume that one side of a decomposition has larger fundamental gro…
For a functionally generated portfolio, there is a natural decomposition of the relative log-return into the log-change in the generating function and a drift process. In this note, this decomposition is extended to arbitrary stock portfolios by an application of Fisk-Stratonovich integration. With the extended methodo…
NeSGD efficiently updates tensor-based features for online model learning in multi-way data.
problem Incremental updates of tensor-based features and model coefficients for evolving data distributions.
method Online NeSGD for CP decomposition of tensor data.
result Proposed NeSGD method significantly improves classification accuracy and adapts to changing data distributions.
The study examines statistical properties of market price and liquidity responses.
problem Understanding the statistical properties of market price and liquidity responses.
method Utilized singular value decomposition to analyze interconnections and statistical characteristics of responses.
result Traded volumes play a critical role in price changes induced by liquidity changes.
Stochastic discount factor (SDF) processes in dynamic economies admit a permanent-transitory decomposition in which the permanent component characterizes pricing over long investment horizons. This paper introduces an empirical framework to analyze the permanent-transitory decomposition of SDF processes. Specifically, …
This paper finds a new method for decomposing insurer profits and losses.
problem Nonlinear balance sheets make it hard to attribute changes to risk factors.
method An axiomatic approach leading to infinitesimal sequential updating (ISU) decompositions.
result ISU decompositions are more general and applicable beyond insurance.
The paper proves a Markov theorem for links in 3-manifolds using braid groups.
problem Equivalence of links in 3-manifolds under ambient isotopy.
method Using plat closures and surface braid groups, the paper translates link equivalence into algebraic equivalence.
result Explicit constructions for Heegaard genus 1 manifolds (lens spaces and S2imesS1). Method detects phase transitions in financial markets using eigenvalue decomposition.
problem Detecting tipping points and fluctuation patterns in financial markets.
method Eigenvalue decomposition and eigen-entropy from cross-correlation matrix.
result Market events undergo phase separation and order-disorder transitions.
Paper breaks down risk contribution into inherent and correlation risk components.
problem Understanding the sources of risk in portfolio contributions.
method Leave-one-out decomposition approach to separate inherent and correlation risk contributions.
result The decomposition reveals distinct contributions of position volatility and correlation to portfolio risk.
Given a topological orientable surface of finite or infinite type equipped with a pair of pants decomposition P and given a base complex structure X on S, there is an associated deformation space of complex structures on S, which we call the Fenchel-Nielsen Teichmüller space associated to the pair $(\…
We report on time-varying network connectedness within three banking systems: North America, the EU, and ASEAN. The original method by Diebold and Yilmaz is improved by using exponentially weighted daily returns and ridge regularization on vector autoregression (VAR) and forecast error variance decomposition (FEVD). We…
With the network methods and random matrix theory, we investigate the interaction structure of communities in financial markets. In particular, based on the random matrix decomposition, we clarify that the local interactions between the business sectors (subsectors) are mainly contained in the sector mode. In the secto…
Modelling financial time series as a time change of a simpler process has been proposed in various forms over the years. One of such recent approaches is called volatility homogenisation decomposition, and has been designed specifically to aid the forecasting of price changes on financial markets. The authors of this m…
In this note, we consider the rigidity of the focal decomposition of closed hyperbolic surfaces. We show that, generically, the focal decomposition of a closed hyperbolic surface does not allow for non-trivial topological deformations, without changing the hyperbolic structure of the surface. By classical rigidity theo…
In this paper we discuss the change in contact structures as their supporting open book decompositions have their binding components cabled. To facilitate this and applications we define the notion of a rational open book decomposition that generalizes the standard notion of open book decomposition and allows one to mo…
SRMD uses random features for efficient time-frequency analysis.
problem Efficiently analyzing time-series data with low computational cost.
method Sparse Random Mode Decomposition (SRMD) constructs a sparse approximation to the spectrogram.
result SRMD outperforms other methods in signal representation, outlier removal, and mode decomposition.
Analyzing multivariate time series data is important to predict future events and changes of complex systems in finance, manufacturing, and administrative decisions. The expressiveness power of Gaussian Process (GP) regression methods has been significantly improved by compositional covariance structures. In this paper…
Unified framework detects change-points and estimates parameters in nonlinear systems with regime switching.
problem Detecting change-points and estimating parameters in nonlinear dynamical systems with regime transitions.
method Residual-loss anomaly analysis of physics-informed neural networks, two-stage strategy.
result The method outperforms traditional approaches in change-point localization and parameter estimation accuracy.
Develops a method to estimate the shadow riskless rate from empirical data.
problem No risky asset in market, need for a shadow riskless rate.
method PCA, SVD, regularization to estimate SRR from correlated geometric Brownian motion.
result Estimates the shadow riskless rate from empirical datasets.
A new method shrinks a complex structure without much change.
problem Understanding the geometry of Bing's wild involution.
method Producing a counterintuitive construction to shrink the Bing decomposition without much change.
result A method to shrink a complex structure (Bing's decomposition) without much change.
New models predict future events with uncertainty.
problem Predicting future events in asynchronous sequences with uncertainty.
method Two new architectures, WGP-LN and FD-Dir, modeling time-dependent distributions.
result Models outperform other approaches in various datasets.
Core-Halo solves large-scale fixed-point problems by decentralizing updates.
problem Large-scale fixed-point equations with block dependencies.
method Core-Halo decomposition separates write ownership from read-only context, aligning with block-dependence structure.
result Core-Halo achieves near-centralized performance while retaining parallelism.
This paper addresses the problem of online learning in a dynamic setting. We consider a social network in which each individual observes a private signal about the underlying state of the world and communicates with her neighbors at each time period. Unlike many existing approaches, the underlying state is dynamic, and…
New method models matrix time series using tensor CP-decomposition.
problem Modeling matrix time series with reduced complexity.
method One-pass estimation via generalized eigenanalysis and refined projection.
result Component coefficient vectors estimated consistently with certain rates.
Develops MENT for interpreting and detecting changes in network trajectories.
problem Distortion of network geometry and invalidation of temporal comparisons in dynamic network analysis.
method Develops Multiscale Euclidean Network Trajectories (MENT) framework based on second-moment geometry.
result Validates and interprets network trajectories through isotropic normalization and orthogonal transformations.
Existing MAP inference algorithms for determinantal point processes (DPPs) need to calculate determinants or conduct eigenvalue decomposition generally at the scale of the full kernel, which presents a great challenge for real-world applications. In this paper, we introduce a class of DPPs, called BwDPPs, that are char…