Despite recent advances in regularisation theory, the issue of parameter selection still remains a challenge for most applications. In a recent work the framework of statistical learning was used to approximate the optimal Tikhonov regularisation parameter from noisy data. In this work, we improve their results and ext…
On-device research index
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
168,695 papers · 148 categories
Trend · papers per month
48 results for “parameter regularisation”
This work shows how penalising bias terms in norm regularisation leads to sparse solutions.
problem Understanding the relation between parameter norm regularization and the sparsity of neural network solutions.
method Analyzes one hidden ReLU layer networks with unidimensional data, showing the norm required for function representation and the importance of the bias term's norm.
result Penalising the bias terms in regularisation leads to sparse solutions, enforcing the uniqueness and sparsity of the minimal norm interpolator.
We consider a general regularised interpolation problem for learning a parameter vector from data. The well known representer theorem says that under certain conditions on the regulariser there exists a solution in the linear span of the data points. This is the core of kernel methods in machine learning as it makes th…
Effective regularisation of neural networks is essential to combat overfitting due to the large number of parameters involved. We present an empirical analogue to the Lipschitz constant of a feed-forward neural network, which we refer to as the maximum gain. We hypothesise that constraining the gain of a network will h…
A Python package solves source duplication in single channel LVMs using spectral regularisation.
problem Source duplication in LVMs hampers their practical use in single channel applications.
method Spectral regularisation term added to address source duplication issue.
result Spectral regularisation framework enables easier investigation and utilisation of LVMs.
Paper studies particle method for LSV model calibration, proving convergence and error bounds.
problem Calibration of local-stochastic volatility models with open well-posedness question.
method Regularized Euler--Maruyama scheme for particle approximation of McKean--Vlasov dynamics.
result Strong convergence of the Euler--Maruyama scheme with rate 1/2 in step-size.
Unified understanding of three continual learning regularisation methods.
problem Maintaining knowledge of earlier tasks without re-accessing them.
method Three regularisation approaches: Elastic Weight Consolidation (EWC), Synaptic Intelligence (SI), and Memory Aware Synapses (MAS).
result EWC, SI, and MAS are linked to the same theoretical quantity, the square root of the Fisher Information.
Study on neural networks with regularisation and its impact on training dynamics.
problem Understanding the dynamics of neural networks with regularization.
method Established explicit dynamics for neural networks with a regularizing term, linearizing around initialisation.
result The regularisation term modifies the standard NTK dynamics, leading to new insights into network training.
Recent work has established the equivalence between deep neural networks and Gaussian processes (GPs), resulting in so-called neural network Gaussian processes (NNGPs). The behaviour of these models depends on the initialisation of the corresponding network. In this work, we consider the impact of noise regularisation …
This work optimizes RL algorithms using entropy regularisation for continuous-time LQ problems.
problem Designing RL algorithms to balance exploration and exploitation in noisy environments.
method Entropy regularisation in two formulations: exploratory control and proximal policy update.
result Regret of for both learning algorithms over episodes.
Study volumes of Klein surfaces, extending Mirzakhani's recursion.
problem Volumes of moduli spaces of bordered Klein surfaces.
method Generalization of Mirzakhani's recursion, integration over regularised moduli space.
result Explicit formula for Klein bottle moduli space volumes, recursion for arbitrary topologies.
This paper improves inverse problem solving with weakly convex regularisers and proves convergence.
problem Improving solution methods for inverse problems.
method Generalised formulation of convergent regularisation using weakly convex regularisers, and proof of convergence for primal-dual hybrid gradient method.
result Proves convergence of primal-dual hybrid gradient method for variational problems and shows improved performance with IWCNNs.
We consider a general regularised interpolation problem for learning a parameter vector from data. The well known representer theorem says that under certain conditions on the regulariser there exists a solution in the linear span of the data points. This is at the core of kernel methods in machine learning as it makes…
We introduce a framework for Continual Learning (CL) based on Bayesian inference over the function space rather than the parameters of a deep neural network. This method, referred to as functional regularisation for Continual Learning, avoids forgetting a previous task by constructing and memorising an approximate post…
GNIs induce a regulariser that penalizes high-frequency components in neural network activations.
problem Understanding the regularizing effect of Gaussian noise injections on neural network activations.
method Deriving the explicit regularizer by marginalizing out injected noise and analyzing its effect in the Fourier domain.
result GNIs induce a regularizer that produces calibrated classifiers with large margins.
Paper advances sparse regularisation theory for measures with new kernel insights.
problem Estimating sparse measures from noisy observations using continuous sparse regularisation.
method Develops new continuous sparse regularisation theory on measures with Beurling-LASSO, introduces kernel switch analysis.
result Proves the ``sinc-4'' kernel satisfies a technical LPC assumption for error bounds.
Theory for RLHF generalization under reward shift and clipped KL.
problem Theoretical understanding of RLHF generalization, especially with reward shift and clipped KL.
method Developed generalization theory for RLHF, accounting for reward shift and clipped KL.
result Presented generalization bounds for RLHF, suggesting generalization error from sampling, reward shift, and KL clipping.
Improved TD learning with tail averaging and regularization achieves optimal convergence rates.
problem Convergence analysis of TD learning with linear function approximation.
method Tail-averaging and regularization applied to TD learning algorithm.
result Achieves optimal convergence rate in expectation and with high probability.
We introduce a class of regularisable infinite dimensional principal fibre bundles which includes fibre bundles arising in gauge field theories like Yang-Mills and string theory and which generalise finite dimensional Riemannian principal fibre bundles induced by an isometric action. We show that the orbits of regulari…
On the Interpretability of Regularisation for Neural Networks Through Model Gradient Similaritystat.ML
New framework monitors neural network training and reveals regularisation mechanisms.
problem Overfitting in neural networks and the need for explicit regularizers.
method Model Gradient Similarity (MGS) framework to measure and monitor regularisation.
result Explicit regularizers increase Model Gradient Similarity (MGS).
This work uncovers algorithm-dependent regularisation in diffusion models.
problem Understanding and improving generalisation in high-dimensional diffusion models.
method Algorithmic stability and score stability analysis.
result Identifies multiple sources of implicit regularisation unique to diffusion models.
The problem of adversarial examples has highlighted the need for a theory of regularisation that is general enough to apply to exotic function classes, such as universal approximators. In response, we give a very general equality result regarding the relationship between distributional robustness and regularisation, as…
New method prevents deep learning forgetting past by remembering key examples.
problem Catastrophic forgetting in continual learning.
method Functional regularisation using Gaussian Process formulation.
result Achieves state-of-the-art performance on benchmarks.
Implicit regularisation in stochastic gradient descent: from single-objective to two-player gamesstat.ML
Novel approach finds implicit regularisation in two-player games using BEA.
problem Understanding implicit regularisation in two-player games.
method Using backward error analysis to construct continuous-time flows with gradient-eligible vector fields.
result Identifies new implicit regularisation effects in two-player games.
Regularization preserves topological data structure in autoencoders.
problem Ensuring topological data structure preservation in autoencoders.
method Regularization using Legendre nodes to preserve manifold embedding.
result Regularized autoencoders ensure one-to-one embedding of data manifolds.
Regularisation improves ML classifier stability against poisoning attacks.
problem Poisoning attacks degrade ML algorithms' performance; current attacks ignore hyperparameters.
method Proposed a multiobjective bilevel optimisation problem to consider hyperparameter effects.
result regularisation enhances learning algorithm stability and mitigates poisoning attacks.
Investigates gradient descent dynamics and introduces new regularisation methods.
problem Understanding and mitigating gradient descent instabilities and interactions with smoothness regularisation.
method Derives continuous-time flows to account for discretisation drift, constructs learning rate schedules and regularisers.
result New regularisation methods improve performance in reinforcement learning.
Ridge regression analysis under varying sample size and dimensionality.
problem Prediction error analysis in asymptotic ridge regression.
method Characterization of prediction error based on covariance and parameter structure.
result Interpolation can be optimal even with bounded SNR if true parameter coefficients are larger on high-variance directions.
Researchers compare different gradient methods for ridge regression, finding conjugate gradients have similar performance.
problem Comparing statistical properties of different gradient methods in ridge regression.
method Explicit non-standard error decomposition to bound prediction error of conjugate gradient iterates.
result Conjugate gradient iterates share optimality properties with gradient flow and ridge regression up to a constant factor.
(S)GD over Diagonal Linear Networks: Implicit Regularisation, Large Stepsizes and Edge of Stabilitycs.LG
Study on GD and SGD over diagonal networks, focusing on stepsizes and regularisation.
problem Understanding the impact of stochasticity and large stepsizes on gradient descent and SGD solutions.
method Investigation of GD and SGD over diagonal linear networks with macroscopic stepsizes, proving convergence and characterizing solutions.
result Large stepsizes consistently benefit SGD for sparse regression problems, but can hinder GD recovery of sparse solutions, especially in the edge of stability regime.
We propose graph-dependent implicit regularisation strategies for distributed stochastic subgradient descent (Distributed SGD) for convex problems in multi-agent learning. Under the standard assumptions of convexity, Lipschitz continuity, and smoothness, we establish statistical learning rates that retain, up to logari…
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.
Study on how noise and variation-norm regularisation help shallow ReLU networks use fewer neurons.
problem Understanding how shallow ReLU networks use a finite number of neurons in the infinitely wide limit.
method Analysis of two regularisation strategies: noise injection and variation-norm.
result Both regularisation methods minimize functions with a finite number of neurons, regardless of overparametrisation.
Improved RL training for DMs reduces mode collapse and preserves diversity.
problem Mode collapse and training instability in RL fine-tuned diffusion models.
method Dynamic hierarchical RL training with sliding-window parameter regularisation.
result Models trained with HRF achieve better preservation of diversity in downstream tasks.
This work proposes a novel autoencoder for fusing visible and infrared images.
problem Challenging task to combine spatial and spectral information from visible and infrared images.
method Spatially constrained adversarial autoencoder with residual architecture and adversarial regularizer.
result Generates a more realistic fused image with enhanced spatial and spectral information.
Local mass perspective on Bayesian inference
problem Measuring distributional discrepancy in Bayesian inference
method Introducing Mass Index and Regularised Extended KL
result Proving inequalities for comparing local small-ball masses
Training an artificial neural network involves an optimization process over the landscape defined by the cost (loss) as a function of the network parameters. We explore these landscapes using optimisation tools developed for potential energy landscapes in molecular science. The number of local minima and transition sta…
New insights into how neural networks learn features, especially when they are very wide.
problem Understanding how gradient flow in wide neural networks selects solutions, especially in the feature-learning regime.
method Axiomatizing the canonical regularizer as a function-space energy and lift, and deriving geodesic ridge for the feature-learning regime.
result Gradient flow in feature-learning networks biases towards ridge regularization, distorting the inductive bias and damaging pretrained networks.
Study characterizes learning from heavy-tailed data in high dimensions using superstatistical methods.
problem Characterizing learning from heavy-tailed data in high-dimensional settings.
method Empirical risk minimization with double-stochastic processes and superstatistical analysis.
result Analytical characterization of separability transition and generalization performance.
Bayesian neural networks improve uncertainty quantification with unlabelled data.
problem Over-confidence in predictions on covariate-shifted data.
method Approximate Bayesian inference using posterior regularisation with pseudo-labels from unlabelled data.
result Significant improvement in uncertainty quantification accuracy on covariate-shifted data.
We show that many standard results of Lorentzian causality theory remain valid if the regularity of the metric is reduced to . Our approach is based on regularisations of the metric adapted to the causal structure.
Regularising for invariance to data augmentation improves machine learning models.
problem Improving generalization in machine learning models through data augmentation.
method Explicit regularisation to encourage invariance at the level of individual model predictions.
result Explicit regularisation improves generalization and equalizes performance differences between objectives.
Prevalidated ridge regression simplifies logistic regression for high-dimensional data.
problem Efficient probabilistic classification in high-dimensional data with logistic regression.
method Developed a prevalidated ridge regression model that matches logistic regression's performance but is more computationally efficient.
result Prevalidated ridge regression achieves similar classification error and log-loss to logistic regression for high-dimensional data.
Method estimates uncertainty in CT reconstructions.
problem Lack of accurate uncertainty estimates in deep-learning CT reconstructions.
method Linearised deep image prior with conjugate Gaussian-linear model error bars and Gaussian surrogate for TV regularisation.
result Method provides superior calibration of uncertainty estimates.
Unified theory for adaptive image convolutions using metric perspectives.
problem Fixed kernels in convolutions limit adaptability in image processing.
method Metric perspective on images as 2D manifolds with local distances, proposing metric convolutions.
result Metric convolutions provide better generalisation and competitive performance.
New ADMM method for PARAFAC2 tensor decomposition with flexible regularization.
problem Challenges in applying regularisation to the evolving mode of PARAFAC2.
method Alternating Direction Method of Multipliers (AO-ADMM) for PARAFAC2 tensor fitting.
result The proposed ADMM-based approach accurately recovers underlying components from simulated data.
The paper studies -positive currents and line bundles on complex manifolds.
problem Understanding -positive currents and their properties on complex manifolds.
method Introducing -plurisubharmonic functions, proving vanishing theorems, and regularisation theorems using viscosity solutions.
result Global and local regularisation theorems for -semi-positive currents.
Convolutional neural networks (CNNs) often perform well, but their stability is poorly understood. To address this problem, we consider the simple prototypical problem of signal denoising, where classical approaches such as nonlinear diffusion, wavelet-based methods and regularisation offer provable stability guarantee…