Research
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.

168,742 papers · 148 categories

Trend · papers per month

111223334445 · Jun 202019922001200920172026
48 results for infinite features

Study examines infinite limits of transformer dynamics, identifying key parameterizations.

problem Understanding the training dynamics of transformer models in the feature learning regime.
method Analysis of infinite scaling limits using dynamical mean field theory.
result Identified parameterizations that admit well-defined infinite width and depth limits.

Inf-FS selects features by graph paths, ranking them for infinite feature sets.

problem Feature selection in large datasets with relevance and redundancy.
method Graph-based feature selection with infinite paths, evaluating feature subsets using matrix power series and Markov chains.
result Inf-FS outperforms other methods in various feature selection scenarios.

Transformers handle infinite dimensional inputs effectively by feature extraction and dynamic feature selection.

problem Understanding the approximation and estimation ability of Transformers with infinite dimensional inputs.
method Anisotropic smoothness analysis and feature extraction properties of Transformers.
result Transformers avoid the curse of dimensionality and dynamically select important features.

Bayesian ReLU nets fix asymptotic overconfidence with infinite features.

problem Bayesian ReLU nets can be asymptotically overconfident far from training data.
method Extend finite ReLU BNNs with infinite ReLU features via a Gaussian process.
result The resulting model is asymptotically maximally uncertain far from the data.

We present a supervised-learning algorithm from graph data (a set of graphs) for arbitrary twice-differentiable loss functions and sparse linear models over all possible subgraph features. To date, it has been shown that under all possible subgraph features, several types of sparse learning, such as Adaboost, LPBoost, …

2014-03-20abs ↗pdf ↗

Adaptive kernels from neural networks improve model performance.

problem Improving neural network performance through adaptive kernels.
method Deriving adaptive kernels from infinite-width neural networks using feature learning and gradient flow training.
result Adaptive kernels achieve lower test loss compared to traditional kernels.

Multivariate splines linked to infinitely-wide neural networks with improved numerical performance.

problem Understanding the relationship between multivariate splines and neural networks.
method Showed multivariate splines can be represented as random features in infinitely-wide neural networks with a homogeneous activation function.
result The function space of multivariate splines is a Sobolev space on a Euclidean ball with explicit norm bounds on derivatives.

The study analyzes transfer learning in infinite-width neural networks, improving generalization on target tasks.

problem Improving generalization in neural networks when using pretraining on a source task.
method Developed a theory under gradient flow for infinitely wide networks, analyzing fine-tuning and joint pretraining.
result Summary statistics of randomly initialized networks after pretraining are adaptive kernels that depend on both source and target data.

Study on feature learning dynamics in infinite-depth neural networks, focusing on ResNets.

problem Understanding how features evolve during training in deep neural networks, especially in the large-depth limit.
method Conditional Gaussian representations and SDE system with decoupled backward weights.
result Depth-induced suppression of forward-backward coupling in infinite-depth networks, leading to a decoupled forward-backward SDE system.

This paper shows how deep neural networks can learn rich, independent features that significantly deviate from initialization.

problem Understanding how deep neural networks achieve meaningful feature learning and global convergence.
method Investigation of infinitely wide, LL-layer neural networks using the tensor program framework under Maximal Update parametrization.
result SGD enables these networks to learn linearly independent features that substantially deviate from their initial values, capturing relevant data information.

Deep kernel processes unify various models using Gram matrices and kernel functions.

problem Unified representation of various deep learning models.
method Defining deep kernel processes with progressively transformed Gram matrices and sampling from inverse Wishart distributions.
result Deep Gaussian processes, BNNs, infinite BNNs, and infinite BNNs with bottlenecks can all be written as deep kernel processes.

Existence of an infinite sequence of harmonic maps between spheres of certain dimensions was proven by Bizon and Chmaj. This sequence shares many features of the Bartnik-McKinnon sequence of solutions to the Einstein-Yang-Mills equations as well as sequences of solutions that have arisen in other physical models. We ap…

1999-12-01abs ↗pdf ↗

New method controls sparse feature updates in deep networks.

problem Understanding sparse feature updates in deep networks during training.
method Iterative linearised training method to control sparse feature updates.
result Iterative linearised training surprisingly performs on par with standard training, requiring less frequent feature learning.

New algorithm improves inference for flexible models with infinite latent features.

problem Inference for models with infinite latent features is computationally challenging and limiting.
method Adaptive slice sampling for posterior inference with general completely random measures.
result Higher effective sample size and predictive performance compared to existing methods.

Infinite mixture models are commonly used for clustering. One can sample from the posterior of mixture assignments by Monte Carlo methods or find its maximum a posteriori solution by optimization. However, in some problems the posterior is diffuse and it is hard to interpret the sampled partitionings. In this paper, we…

2013-10-01abs ↗pdf ↗

Indian Buffet Process based models are an elegant way for discovering underlying features within a data set, but inference in such models can be slow. Inferring underlying features using Markov chain Monte Carlo either relies on an uncollapsed representation, which leads to poor mixing, or on a collapsed representation…

2017-03-09abs ↗pdf ↗

More features and data lead to better model performance in random feature regression.

problem Improving model performance in random feature regression.
method Theoretical analysis of random feature regression, demonstrating the benefits of overparameterization, overfitting, and more data.
result Infinite width RF architectures are preferable to those of any finite width, and training to near-zero training loss is obligatory for near-optimal performance.

Analyzes feature learning in neural networks using a self-consistent dynamical field theory.

problem Feature learning in infinite-width neural networks.
method Constructs deterministic dynamical order parameters as inner-product kernels for hidden unit activations and gradients.
result Reveals the hidden layer activation distribution, neural tangent kernel evolution, and output predictions.

The study reveals a transition in neural network performance from infinite-width to variance-limited behavior as dataset size increases.

problem Understanding the transition from infinite-width to variance-limited behavior in neural networks.
method Empirical study of the transition from infinite-width to variance-limited behavior as a function of sample size and network width.
result The critical sample size \( P^* \) is approximately \( \sqrt{N} \) for polynomial regression with ReLU networks.

Scientific explanation often requires inferring maximally predictive features from a given data set. Unfortunately, the collection of minimal maximally predictive features for most stochastic processes is uncountably infinite. In such cases, one compromises and instead seeks nearly maximally predictive features. Here, …

2017-02-27abs ↗pdf ↗

Paper analyzes error bounds for learning with vector-valued RF, improving existing analyses.

problem Learning with vector-valued random features in infinite-dimensional settings.
method Direct analysis of risk functional, avoiding random matrix theory.
result Strong consistency and minimax optimal convergence rates established.

Wide neural networks can benefit from multi-task learning in their infinite-width limit.

problem The generalization behavior of wide neural networks in multi-task learning settings.
method Optimizing wide ReLU neural networks with L2-regularization promotes multi-task learning in the infinite-width limit.
result An exact quantitative characterization of multi-task learning in the infinite-width limit of wide ReLU neural networks.

We consider Thompson's groups from the perspective of mapping class groups of surfaces of infinite type. This point of view leads us to the braided Thompson groups, which are extensions of Thompson's groups by infinite (spherical) braid groups. We will outline the main features of these groups and some applications to …

2011-05-03abs ↗pdf ↗

Given any closed Kaehler manifold we define, following an idea by Eugenio Calabi, a Riemannian metric on the space of Kaehler metrics regarded as an infinite dimensional manifold. We prove several geometrical features of the resulting space, some of which we think were already known to Calabi. In particular, the space …

2010-04-30abs ↗pdf ↗

Infinite hierarchical contrastive clustering identifies personal environments linked to health outcomes.

problem Identifying meaningful relationships between environmental features and health outcomes on an individual level.
method Contrastive clustering framework with stick-breaking prior and participant-specific prediction loss.
result Model effectively identifies distinct personal environments and groups them into meaningful types linked to health outcomes.

We study how finite Bayesian neural networks adapt their hidden representations.

problem Understanding how finite Bayesian neural networks differ from infinite ones.
method We analyze the asymptotics of learned feature kernels for various network architectures.
result The leading finite-width corrections to feature kernels have a universal form.

A framework for quantifying uncertainty in feature importance values.

problem Stable interpretation of feature importance values in machine learning models.
method A novel method based on pairwise comparisons of feature importance values to produce confidence intervals for feature ranks.
result The method produces simultaneous confidence intervals for feature ranks, enabling selection of top-k important features.

UCRL2-VTR achieves nearly optimal regret for learning MDPs with linear function approximation.

problem Learning infinite-horizon average-reward MDPs with linear function approximation.
method UCRL2-VTR algorithm with Bernstein-type bonus.
result Achieves a regret of ildeO(dDT) ilde{O}(d\sqrt{DT}) with matching lower bound.

Analysis of deep neural networks under various learning rules reveals dynamics of feature and prediction learning.

problem Understanding how different learning rules affect feature and prediction dynamics in deep neural networks.
method Analysis of infinite-width deep networks trained with gradient descent and various learning rules.
result The evolution of the output function is governed by an effective neural tangent kernel (eNTK), which varies depending on the learning rule and training regime.

Study of deep linear neural networks with proportional width and depth.

problem Lack of descriptive power in Gaussian limit of deep linear neural networks.
method Proportional infinite-width infinite-depth limit for deep linear neural networks.
result Characterization of limiting distribution as a nontrivial mixture of Gaussians.

Study on fluctuations in neural network kernels and predictions, focusing on finite width effects.

problem Characterizing fluctuations in finite width neural networks.
method Dynamical mean field theory analysis of wide but finite feature learning neural networks.
result Fluctuations in kernels and predictions are dynamically coupled, leading to reduced variance in feature learning regimes.

The paper provides risk bounds for learning many response functions using linear regression.

problem Learning many response functions from a single dataset.
method Ordinary least squares regression in a high-dimensional feature space.
result Convergence guarantees on worst-case excess prediction risk for infinite response functions with finite VC dimension.

Matrix factorisation methods decompose multivariate observations as linear combinations of latent feature vectors. The Indian Buffet Process (IBP) provides a way to model the number of latent features required for a good approximation in terms of regularised reconstruction error. Previous work has focussed on latent fe…

2017-04-13abs ↗pdf ↗

Large learning rates work surprisingly well in standard parameterization, contrary to theory.

problem Theoretical limits of large learning rates do not match practical network behavior.
method Fine-grained analysis of learning rates and network behavior under cross-entropy loss.
result There are two distinct sub-regimes of unstable learning rates, with a controlled divergence regime where features continue to evolve.

Extends Seeley's theorem for Bastiani's differential calculus in infinite dimensions.

problem Extending differential calculus results to infinite-dimensional spaces.
method Follows Seeley's approach but extends to continuous differentials and families of operators.
result Constructs families of extension operators for continuous differentials.

A new neural network model reduces features in high-dimensional sequential data.

problem Exponential growth in features of truncated signature transform in high-dimensional data.
method Proposes a neural network model inspired by Convolutional Neural Networks to address feature growth.
result Reduces the number of features efficiently in a data-dependent way.

Distributions over exchangeable matrices with infinitely many columns, such as the Indian buffet process, are useful in constructing nonparametric latent variable models. However, the distribution implied by such models over the number of features exhibited by each data point may be poorly- suited for many modeling tas…

2012-09-05abs ↗pdf ↗

In this paper we consider a problem of searching a space of predictive models for a given training data set. We propose an iterative procedure for deriving a sequence of improving models and a corresponding sequence of sets of non-linear features on the original input space. After a finite number of iterations N, the n…

2013-12-19abs ↗pdf ↗