A new kernel-based CI test improves on existing methods.
problem Testing conditional independence (CI) in a broad range of dependencies.
method Regression-model-agnostic kernel-based CI test using reproducing kernel Hilbert spaces.
result GKCM outperforms state-of-the-art CI tests in simulations.
Study on generalisation in random feature learning and hidden manifold models.
problem Generalisation in high-dimensional learning problems.
method Replica method from statistical physics for asymptotic generalisation performance.
result Closed-form expression for generalisation performance in various high-dimensional settings.
New stability bounds for GD in overparameterised shallow nets without NTK assumptions.
problem Generalisation and excess risk bounds for shallow neural networks.
method Oracle inequalities and stability analysis of GD without kernelisation.
result Oracle type bounds reveal GD's generalisation is controlled by an interpolating network with shortest GD path.
New method for insurance valuation combining hedging and risk minimization.
problem Current insurance valuation methods do not reflect regulatory risk measures.
method Two-step hedging procedure using generalised regression.
result The method produces portfolios neutral to risk measures like VaR or expectiles.
Deep Gaussian processes (DGPs) are multi-layer hierarchical generalisations of Gaussian processes (GPs) and are formally equivalent to neural networks with multiple, infinitely wide hidden layers. DGPs are nonparametric probabilistic models and as such are arguably more flexible, have a greater capacity to generalise, …
Paper uses SLT to improve model selection for SHM.
problem Model selection for SHM using data-based systems.
method Utilizes Statistical Learning Theory to rigorously estimate generalisation.
result Incorporating domain knowledge improves model generalisation.
Improved prediction of soil parameters using Multi-target Stacked Generalisation on EDXRF spectra.
problem Challenges in predicting multiple soil parameters accurately from EDXRF spectra.
method Multi-target Stacked Generalisation (MTSG) method combining multiple regression models.
result MTSG significantly improved prediction accuracy for multiple soil parameters, reducing average error from 0.67 to 0.64.
Study examines robust regression in high dimensions with heavy-tailed data.
problem Analyzing robust regression in high-dimensional settings with heavy-tailed data.
method Sharp asymptotic characterisation of M-estimators and ridge regression in elliptical distributions.
result Ridge regression is optimal and universal for finite second moments but can decay faster without them.
Regularizes ML algorithms for robust multivariate analysis against distribution shifts.
problem Ensuring robustness of multivariate analysis algorithms against distribution shifts.
method Integrates a causal regularisation term into the loss function of multivariate analysis algorithms.
result Demonstrates improved out-of-distribution generalisation with reduced-rank regression and partial least squares.
This paper explains double descent in linear neural networks, identifying new factors.
problem Understanding double descent in linear neural networks.
method Gradient flow derivation and necessary conditions for double descent.
result Singular values of input-output covariance matrix are important for double descent in two-layer models.
Collider regression improves predictive performance in regression tasks.
problem Discarding prior causal knowledge in regression tasks.
method Collider regression framework incorporating probabilistic causal knowledge from collider structures.
result Proves positive generalization benefit and provides closed-form estimators.
We consider a Gaussian process formulation of the multiple kernel learning problem. The goal is to select the convex combination of kernel matrices that best explains the data and by doing so improve the generalisation on unseen data. Sparsity in the kernel weights is obtained by adopting a hierarchical Bayesian approa…
In this paper, a new approach to computing the generalisation performance is presented that assumes the distribution of risks, ρ(r), for a learning scenario is known. From this, the expected error of a learning machine using empirical risk minimisation is computed for both classification and regression problems. A cr…
Kernel methods benefit from enforcing invariance, reducing generalization error.
problem Improving generalization in kernel methods.
method Function space perspective and feature averaging for invariance.
result Strict non-zero generalization benefit for kernel ridge regression with invariant targets.
New damping technique improves deep learning models by reducing noise in flat directions.
problem Improving generalization in deep learning models by reducing estimation noise in flat directions.
method Developed a novel random matrix theory based damping learner to reduce the shrinkage coefficient and improve generalization.
result Significant generalization improvements in logistic regression and deep neural networks experiments.
DL/FBF improves GPSR solutions by selecting compact, generalising expressions.
problem Overfitting and structural bloat in symbolic regression with genetic programming.
method Description length (DL) and fractional Bayes factor (FBF) criteria for selecting compact, generalising expressions.
result DL/FBF post-selection improves test performance compared to AIC/BIC baseline.
The paper improves Gaussian process regression by optimizing hyperparameters.
problem Hyperparameter tuning for Gaussian process regression models.
method Adaptive sparse variational approximations using variational Bayes.
result Minimax optimal rates of convergence for variational posterior.
This paper presents a cross-country comparison of significant predictors of small business failure between Italy and the UK. Financial measures of profitability, leverage, coverage, liquidity, scale and non-financial information are explored, some commonalities and differences are highlighted. Several models are consid…
Develops PAC-Bayesian framework for physics-informed machine learning.
problem Lack of statistical generalisation understanding for PIML models.
method PAC-Bayesian framework with multi-task perspective, incorporating physical structure.
result High-probability generalisation guarantees with unbounded losses.
Bayesian GPR model predicts extreme stock market losses.
problem Forecasting rare but impactful extreme negative returns in equity markets.
method Developed a Bayesian Generalised Pareto Regression model linking scale parameter to market volatility.
result The Cauchy prior provides the best balance between predictive accuracy and model simplicity.
New PAC-Bayes bounds for unbounded loss functions.
problem Generalization bounds for learning problems with unbounded loss functions.
method Introducing HYPE, a new notion for loss range, and deriving a novel PAC-Bayesian generalization bound.
result PAC-Bayes framework extended to unbounded loss functions.
Enhances time-series regression trees with latent factors for robust financial analysis.
problem Handling predictors with measurement error, trends, seasonality, and missing data.
method Integrates latent stationary factors extracted via state-space methods into time-series regression trees.
result Factor-augmented trees provide a reliable approach for macro-finance problems, exemplified by the lead-lag effect between equity volatility and the business cycle.
The study shows symmetry improves machine learning generalization.
problem Improving machine learning generalization through symmetry.
method Using an averaging operator to prove equivariance reduces test risk.
result Equivariant predictors reduce test risk compared to non-equivariant ones.
The present paper provides a new generic strategy leading to non-asymptotic theoretical guarantees on the Leave-one-Out procedure applied to a broad class of learning algorithms. This strategy relies on two main ingredients: the new notion of Lq stability, and the strong use of moment inequalities. Lq stability e…
Generalised Degrees of Freedom (GDF), as defined by Ye (1998 JASA 93:120-131), represent the sensitivity of model fits to perturbations of the data. As such they can be computed for any statistical model, making it possible, in principle, to derive the number of parameters in machine-learning approaches. Defined origin…
gOMP algorithm selects features for various types of data.
problem Feature selection for scalable molecular data.
method Generalized Orthogonal Matching Pursuit algorithm for multiple types of data.
result gOMP performs similarly or better than LASSO on various datasets.
Paper introduces robust Gaussian process regression without sacrificing computational efficiency.
problem Violation of independent and identically distributed Gaussian observation noise assumption in Gaussian process regression.
method Proves robust and conjugate Gaussian process regression (RCGP) at no additional cost using generalised Bayesian inference.
result RCGP enables exact conjugate closed form updates in all settings where standard GPs admit them.
Study predictive performance of linear regression with random functional covariates.
problem Theoretical predictive performance of linear regression with random functional covariates.
method Theoretical analysis of ridge and ridge-less least-squares regression with random functional covariates.
result Probabilistic bounds on predictive excess risk for random functional covariates.
Simplifies transfer learning with deep neural networks using ridge regression.
problem High computational cost of finetuning deep models for transfer learning.
method Leverage the low-rank property of deep neural networks' feature vectors in kernel ridge regression.
result Successful on supervised and semi-supervised transfer learning tasks.
New findings challenge the use of flatness measures in neural networks.
problem The validity of flatness measures in assessing generalization in neural networks.
method Analysis of Hessian-based flatness norms and their relation to generalization.
result Solutions with large weights and low loss are often sharper than expected, contradicting flatness measures.
Simplifies neural regression by combining two sub-networks for predictions and uncertainties.
problem Neural networks underestimate uncertainty, leading to overly confident predictions.
method Extends IRLS to a two-sub-network approach with shared representations and complementary loss functions.
result Proposed network is simpler to implement and more robust to uncertainty variations.
We propose a novel deep learning paradigm of differential flows that learn a stochastic differential equation transformations of inputs prior to a standard classification or regression function. The key property of differential Gaussian processes is the warping of inputs through infinitely deep, but infinitesimal, diff…
The paper analyzes fluctuations in ensemble models in high-dimensional settings.
problem Understanding statistical fluctuations in ensemble models in high-dimensional settings.
method Develops a rigorous theory for the study of fluctuations in ensemble of generalised linear models.
result Provides a complete description of the asymptotic joint distribution of the empirical risk minimizer for convex losses in high-dimensional settings.
We tackle the problem of collaborative filtering (CF) with side information, through the lens of Gaussian Process (GP) regression. Driven by the idea of using the kernel to explicitly model user-item similarities, we formulate the GP in a way that allows the incorporation of low-rank matrix factorisation, arriving at o…
The paper generalizes Cartan Geometry using Polacek and Siegel's approach.
problem Formulating sigma model dynamics in a covariant way.
method Using Polacek and Siegel's generalised curvature and torsion approach within the generalised metric formalism.
result Almost all higher generalised tensors correspond to covariant derivatives of the generalised Riemann tensor.
Maps of infectious disease---charting spatial variations in the force of infection, degree of endemicity, and the burden on human health---provide an essential evidence base to support planning towards global health targets. Contemporary disease mapping efforts have embraced statistical modelling approaches to properly…
Enhances robustness of MOGP regression for multiple correlated outputs.
problem Model misspecification and outliers in MOGP regression.
method Extends RCGP framework to multi-output setting.
result Provable robust MOGP with joint correlation capture.
Constructs a unique Levi-Civita connection for generalised metrics.
problem Non-uniqueness of generalised Levi-Civita connections.
method Geometrically constructs a canonical generalised Levi-Civita connection.
result Decomposes the generalised Riemann curvature tensor in terms of classical geometric data.
Bayesian framework tackles measurement error in covariates.
problem Misleading inference due to corrupted covariates.
method Bayesian Nonparametric Learning framework robust to misspecification.
result General framework for Classical and Berkson error models.
The paper applies generalised geometry to semi-Riemannian immersions and hypersurfaces.
problem Analyzing semi-Riemannian immersions and hypersurfaces using generalised geometry.
method Develops the pullback of generalised metrics and divergence operators, introduces generalised exterior curvature, and derives Gauß-Codazzi equations.
result Establishes the constraint equations for the initial value formulation of the generalised Einstein equations.
Paper generalizes teacher-student model for realistic data.
problem Capturing learning curves for realistic datasets.
method Introduces a Gaussian covariate generalization of the teacher-student model.
result Generalized model captures learning curves for various realistic data sets.
ICCNLS models complex relationships as convex and concave components.
problem Complex input-output relationships with affine ambiguity.
method Sub-gradient constrained affine functions, global orthogonality constraints, L1, L2, and elastic net regularisation.
result Improved predictive accuracy and model simplicity compared to conventional methods.
We propose the supervised hierarchical Dirichlet process (sHDP), a nonparametric generative model for the joint distribution of a group of observations and a response variable directly associated with that whole group. We compare the sHDP with another leading method for regression on grouped data, the supervised latent…
ecpc R-package improves high-dimensional prediction with co-data.
problem High-dimensional prediction with more variables than samples.
method Adaptive ridge penalised models with co-data, including continuous co-data.
result Improved variable selection and prediction performance.
New RNN model forecasts unseen time series with little training data.
problem Lack of data for RNNs to generalize well in time series forecasting.
method Proposes a novel RNN-based model that learns shared feature embeddings over quantised time series.
result Accurately forecasts unseen time series with minimal training data.
New approach to T-duality using Courant algebroids.
problem Developing a new framework for T-duality.
method Relational description of Courant algebroids and weakened isometries.
result Existence and uniqueness of T-dual backgrounds.
Defines T-duality and generalised Ricci flow relations using Courant algebroid relations.
problem Establishing compatibility between T-duality and generalised Ricci flow.
method Introducing Courant algebroid relations, invariant divergence operators, and generalised isometries.
result T-duality is compatible with generalised Ricci flow, and T-dual solutions are also solutions of generalised Ricci flow.
We define (p,q) hermitian geometry as the target space geometry of the two dimensional (p,q) supersymmetric sigma model. This includes generalised Kähler geometry for (2,2), generalised hyperkähler geometry for (4,2), strong Kähler with torsion geometry for (2,1) and strong hyperkähler with torsion geometry f…