Novel algorithms scale correspondence analysis to large datasets.
problem Scaling correspondence analysis to large, high-dimensional datasets.
method Interpreting CA in terms of principal inertia components and using deep neural networks for approximation.
result Maximally correlated embeddings of pairs of random variables in CA can be reliably approximated from data using deep neural networks.
Planes and spheres are the only stationary surfaces with constant Gauss curvature.
problem Finding surfaces with constant Gauss curvature that are stationary under a specific energy function.
method Proving the uniqueness of stationary surfaces by considering different curvature conditions.
result Planes and spheres are the only stationary surfaces with constant Gauss curvature.
The classical theory of Riemann ellipsoids is formulated naturally as a gauge theory based on a principal G-bundle P. The structure group G=SO(3) is the vorticity group, and the bundle ${\cal P}=GL_+(3, R})$ is the connected component of the general linear group. The base manifold is the space of positive-defi…
We study the topology of the inertia space of a smooth G-manifold M where G is a compact Lie group. We construct an explicit Whitney stratification of the inertia space, demonstrating that the inertia space is a triangulable differentiable stratified space. In addition, we demonstrate a de Rham theorem for differ…
For a complex projective space the inertia group, the homotopy inertia group and the concordance inertia group are isomorphic. In complex dimension 4n+1, these groups are related to computations in stable cohomotopy. Using stable homotopy theory, we make explicit computations to show that the inertia group is non-trivi…
This paper explains why Adam generalizes worse than SGD by analyzing its components.
problem Understanding why Adam generalizes worse than Stochastic Gradient Descent (SGD).
method Diffusion theoretical framework to disentangle the effects of Adaptive Learning Rate and Momentum.
result Adaptive Learning Rate helps escape saddle points but not select flat minima, while Momentum provides a drift effect to help pass through saddle points.
In this paper, we investigate the attractive properties of the proximal gradient algorithm with inertia. Notably, we show that using alternated inertia yields monotonically decreasing functional values, which contrasts with usual accelerated proximal gradient methods. We also provide convergence rates for the algorithm…
The paper computes inertia groups of certain high-dimensional manifolds.
problem Diffeomorphism classification of (n−1)-connected, smooth, closed, oriented 2n-manifolds. method Surgery theory, modified surgery, and special cases of conjectures.
result Inertia groups always vanish for neq4,8,9 and certain cases of n. This paper deals with certain results on the number of smooth structures on quaternionic projective spaces, obtained through the computation of inertia group and its analogues, which in turn are computed using techniques from stable homotopy theory. We show that the concordance inertia group is trivial in dimension 20,…
Study ramification in knot groups through finite covers and their quotients.
problem Understanding ramification in knot groups and their covers.
method Formalized ramification theory for knot groups, analyzed through finite quotients, profinite completions, and cohomology.
result Characterized ramification and inertia subgroups in knot groups and their covers.
We use the Grauert--Grothendieck complex on differentiable spaces to study basic relative forms on the inertia space of a compact Lie group action on a manifold. We prove that the sheaf complex of basic relative forms on the inertia space is a fine resolution of Bryliski's sheaf of functions on the inertia space.
New insights into BNN optimization redefine latent weights as inertia.
problem Optimizing Binarized Neural Networks (BNNs) with latent weights.
method Interpreted latent weights as inertia and introduced Binary Optimizer (Bop).
result Demonstrated improved performance of Bop on CIFAR-10 and ImageNet.
New simulations advise caution in choosing principal components for multivariate functional data.
problem Inaccurate selection of principal components in multivariate functional data.
method Extensive simulations investigating the reliability of percentage of variance explained thresholds.
result Conventional threshold methods may fail to accurately explain overall variance in multivariate functional data.
Proves triviality of inertia groups in high-dimensional manifolds.
problem Classifying manifolds in the metastable range.
method Understanding the second extended power functor in synthetic spectra.
result Inertia groups of high-dimensional manifolds are trivial.
Principal component regression (PCR) is a two-stage procedure that selects some principal components and then constructs a regression model regarding them as new explanatory variables. Note that the principal components are obtained from only explanatory variables and not considered with the response variable. To addre…
Generalizes PCA to maximize any convex function of components.
problem Finding a principal vector that maximizes a convex function of components.
method Gradient ascent algorithm for solving the generalized PCA problem; fixed points of neural networks for kernel version.
result Solutions can be obtained as fixed points of simple neural networks.
The paper classifies ruled surfaces in Lorentz-Minkowski space that are stationary for the moment of inertia.
problem Classifying ruled surfaces in Lorentz-Minkowski space that are stationary for the moment of inertia.
method Maximum principle applications, classification based on causal character of rulings.
result Planes are the only cylindrical stationary surfaces. For non-cylindrical surfaces, classification depends on the causal character of the rulings.
The paper introduces a method for interpretable principal component analysis of high-dimensional time series.
problem Inconsistent and difficult-to-interpret principal component estimates in high-dimensional regimes.
method Localized sparse principal component analysis of spectral density matrices in frequency domain.
result Efficient algorithm for sparse-localized estimates of principal subspaces.
PCHAL and PCHAR use principal components to speed up HAL and HAR methods.
problem Computational infeasibility in high dimensions for HAL and HAR.
method Outcome-blind principal component reduction of HAL basis.
result Empirical performance comparable to HAL and HAR, with computational gains.
Efficient private matrix analysis algorithms for recent variants.
problem Private analysis of recent matrix updates.
method Identifying sufficient conditions on positive semidefinite matrices.
result First efficient differentially private algorithms for various matrix analysis tasks.
CA-NN uses neural networks to scale correspondence analysis.
problem Scaling correspondence analysis to large datasets.
method Reinterpreting CA as a functional optimization problem over finite variance functions, approximated by neural networks.
result CA-NN enables scalable correspondence analysis.
We introduce the notions of a differentiable groupoid and a differentiable stratified groupoid, generalizations of Lie groupoids in which the spaces of objects and arrows have the structures of differentiable spaces, respectively differentiable stratified spaces, compatible with the groupoid structure. After studying b…
We show that if M and N have the same homotopy type of simply connected closed smooth m-manifolds such that the integral and mod-2 cohomologies of M vanish in odd degrees, then their homotopy inertia groups are equal. Let M2n be a closed (n−1)-connected 2n-dimensional smooth manifold. We show that, f…
We show how to efficiently project a vector onto the top principal components of a matrix, without explicitly computing these components. Specifically, we introduce an iterative algorithm that provably computes the projection using few calls to any black-box routine for ridge regression. By avoiding explicit principal …
A new PCR method using SVD with sparse regularization.
problem Lack of response variable information in traditional PCR.
method One-stage SVD approach with two loss functions and sparse regularization.
result Obtains principal component loadings with response variable information.
Essential principal components simplify spectral analysis with minimal training data.
problem Accurate spectral quantification from complex mixtures.
method Identifying essential principal components and using molar extinction coefficients.
result Near one-to-one projection from principal components to mixture constituents.
A new method for sparse regression using principal components.
problem Wide data with many features and few observations.
method Combines lasso (ℓ1) sparsity with quadratic penalty towards principal components. result Powerful feature selection and group-wise shrinkage.
Paper uses PCA to analyze Chinese sovereign bonds and discusses bond immunization.
problem Analyzing factors affecting Chinese sovereign bond yield changes.
method Applied Principal Component Analysis (PCA) on bond yield data.
result Identified principal factors influencing Chinese sovereign bond yield changes.
Neural network HDP improves virtual inertia control for non-inductive grids.
problem Traditional virtual inertia controllers are not suitable for non-inductive grids.
method Adaptive neural network heuristic dynamic programming (HDP) for optimal control.
result The proposed HDP controller outperforms traditional controllers in virtual inertia control.
The paper uses diffusion approximations to analyze and optimize online principal component estimation.
problem Optimizing online principal component estimation from streaming data.
method Diffusion approximation tools applied to Oja's iteration for principal component analysis.
result The Oja's iteration for the top eigenvector generates a continuous-state discrete-time Markov chain over the unit sphere.
New approach limits regret in non-stationary bandits.
problem Understanding worst case regret in time-varying bandits.
method Belief inertia argument to resist new evidence after changes.
result Linear worst case regret for classical and restarting algorithms.
Principal component regression (PCR) is a widely used two-stage procedure: principal component analysis (PCA), followed by regression in which the selected principal components are regarded as new explanatory variables in the model. Note that PCA is based only on the explanatory variables, so the principal components a…
QAPCA uses quantum annealing for robust PCA.
problem Outliers in data skew L2-norm principal components.
method Quantum annealing for L1-norm optimization.
result QAPCA's reconstruction error is comparable to L1-BF.
New supervised and unsupervised NFLTs for elliptical distributions.
problem Understanding unsupervised No Free Lunch Theorems for elliptical distributions.
method Proved two equally optimal strategies for elliptical distributions, inspired PRIM-based bump-hunting algorithms.
result Optimal strategies for selecting principal components based on variance or volume.
Let M2n denote a closed (n−1)-connected smoothable topological 2n-manifold. We show that the group C(M2n) of concordance classes of smoothings of M2n is isomorphic to the group of smooth homotopy spheres Θ2n for n=4 or 5, the concordance inertia group Ic(M2n)=0 for $…
Two new PCA variants improve financial data analysis.
problem Numerical instability and nonstationarity in PCA for finance.
method Iterated and exponentially weighted moving PCA variants using Ogita-Aishima iteration.
result Improved stability and adaptability in financial data analysis.
Improved estimation of multiple principal components using manifold optimization and iterative deflation techniques.
problem Estimating multiple principal components efficiently and orthogonally.
method Extended SFPCA using manifold optimization and iterative deflation techniques.
result Alternative deflation schemes improve signal extraction and component estimation.
CPCR mitigates bias in PCR for overparameterized models.
problem Bias in Principal Component Regression (PCR) for overparameterized models.
method Calibrated Principal Component Regression (CPCR) learns a low-variance prior in the PC subspace and calibrates the model in the original feature space.
result CPCR outperforms standard PCR in overparameterized settings, improving prediction across multiple problems.
This paper analyzes how errors accumulate in PCA's deflation method.
problem Error accumulation in PCA's deflation method.
method Mathematical analysis of inexact Hotelling's deflation method in two scenarios.
result Characterization of error propagation in PCA's deflation method.
Paper presents a faster classical algorithm for principal component regression.
problem Efficiently solving principal component regression problems.
method Uses quantum-inspired linear algebra techniques.
result Achieves polylogarithmic runtime, significantly faster than state-of-the-art.
We study sparse principal component analysis for high dimensional vector autoregressive time series under a doubly asymptotic framework, which allows the dimension d to scale with the series length T. We treat the transition matrix of time series as a nuisance parameter and directly apply sparse principal component…
The paper computes smooth structures on a specific product manifold.
problem Computing the number of smooth structures on a product manifold.
method Using known low-dimensional computations of stable homotopy groups of spheres, the paper determines the inertia group of the product manifold.
result The paper establishes a diffeomorphism classification of all smooth manifolds homeomorphic to CP3imesSk for 1≤k≤7. The computation of the sparse principal component of a matrix is equivalent to the identification of its principal submatrix with the largest maximum eigenvalue. Finding this optimal submatrix is what renders the problem NP-hard. In this work, we prove that, if the matrix is positive semidefinite and its …
The dynamic nature of air quality chemistry and transport makes it difficult to identify the mixture of air pollutants for a region. In this study of air quality in the Houston metropolitan area we apply dynamic principal component analysis (DPCA) to a normalized multivariate time series of daily concentration measurem…
In this dissertation, the main goal is visualisation of financial time series. We expect that visualisation of financial time series will be a useful auxiliary for technical analysis. Firstly, we review the technical analysis methods and test our trading rules, which are built by the essential concepts of technical ana…
The paper uses PCA and HMM to forecast stock returns outperforming buy-and-hold.
problem Predicting stock returns accurately.
method Applied PCA to covariance matrix of S&P 500 stocks, used HMM on principal components, and forecasted stock returns.
result The model outperforms buy-and-hold strategy in terms of annualized Sharpe ratio.
Study explores K-means clustering of variables and its relation to PCA.
problem Exploring the relationship between K-means clustering of variables and PCA.
method Apply PCA to original data and K-means to transposed data, quantify variable contributions to principal components.
result Identifies how variable clusters contribute to principal components identified by PCA.
The Wall surgery obstruction groups have two interesting geometrically defined subgroups, consisting of the surgery obstructions between closed manifolds, and the inertial elements. We show that the inertia group In+1(π,w) and the closed manifold subgroup Cn+1(π,w) are equal in dimensions n+1≥6, for any…