We propose semi-random features for nonlinear function approximation. The flexibility of semi-random feature lies between the fully adjustable units in deep learning and the random features used in kernel methods. For one hidden layer models with semi-random features, we prove with no unrealistic assumptions that the m…
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.
169,051 papers · 148 categories
Trend · papers per month
48 results for “deep random features”
Study compares random and learned features in deep Bayesian linear models.
problem Understanding how feature learning affects generalization in deep learning.
method Comparing deep random feature models to deep networks with trained layers.
result Random feature models can display double-descent behavior, while deep networks do not.
Deep random feature models are analyzed for their performance with exact asymptotic expressions.
problem Understanding the performance of deep random feature models.
method Established a novel universality result and used the convex Gaussian Min-Max theorem.
result Exact asymptotic expressions for the performance of deep random feature models are derived.
RFRBoost uses random features to boost deep residual neural networks, improving performance and computational efficiency.
problem Improving performance of deep residual neural networks (RFNNs) while preserving convex optimization benefits.
method Random Feature Representation Boosting (RFRBoost) using boosting theory and random features at each layer.
result RFRBoost significantly outperforms RFNNs and end-to-end trained MLP ResNets in small- to medium-scale tabular datasets.
ADEC addresses feature randomness and drift in autoencoder-based clustering.
problem Clustering autoencoders learn unreliable pseudo-labels, distorting latent space and feature randomness.
method Adversarial training to balance reconstruction loss and clustering objective.
result ADEC outperforms state-of-the-art autoencoder-based clustering methods.
Beyond Signal Propagation: Is Feature Diversity Necessary in Deep Neural Network Initialization?cs.LG
New method shows random, diverse initializations are not essential for deep neural networks.
problem The necessity of random, diverse initializations in deep neural networks.
method Constructed a deep convolutional network with identical features by initializing weights to 0, enabling signal propagation and stable gradients.
result Random, diverse initializations are not necessary for training neural networks.
The study proves Gaussian universality of deep random features learning.
problem Understanding the test error in deep random features learning.
method Proving Gaussian universality of test error in ridge regression and arbitrary convex losses.
result Sharp asymptotic formula for test error in ridge regression setting.
Training only BatchNorm parameters achieves surprisingly high performance in deep networks.
problem Understanding the role and expressive power of affine parameters in BatchNorm.
method Investigating performance when training only BatchNorm parameters and freezing all other weights.
result BatchNorm achieves high performance by learning to disable around a third of random features.
Random Fourier features improve tabular deep learning convergence.
problem Tabular deep learning convergence issues.
method Random Fourier projections as a pre-processing step, projecting inputs into a fixed feature space.
result Random Fourier pre-processing accelerates tabular deep learning convergence.
Deep Regression Ensemblesstat.ML
DRE combines DNN with random feature regression for efficient neural network design.
problem Designing and training deep neural networks (DNN) efficiently and effectively.
method DRE architecture with two-layer neural networks, randomly drawn input and output weights trained with linear ridge regression.
result DRE outperforms state-of-the-art DNN in many data sets with lower computational cost.
A novel model uses ODE-based random features to model nonlinear dynamical systems.
problem Modeling highly nonlinear dynamical systems with uncertainty quantification.
method Compositions of physics-informed random features derived from ODEs, combined with deep Gaussian processes and approximate Bayesian inference.
result The model effectively captures nonlinear behavior in real-world multivariate time series data and achieves comparable performance to other models on benchmark tasks.
Randomized neural networks improve deep RL agents' generalization.
problem Deep RL agents struggle to generalize to new, semantically similar environments.
method Introduce a randomized (convolutional) neural network to perturb input observations.
result Significantly outperforms various regularization and data augmentation methods.
Characterizes test error in learning with deep, structured feature maps.
problem Characterizing test error in learning with deep, structured feature maps.
method Asymptotic analysis of feature covariance and population covariance.
result Closed-form formula for feature covariance in Gaussian rainbow neural networks.
A novel framework combines deep metric learning and conditional random field for hyperspectral image classification.
problem Improving classification performance in hyperspectral image processing with limited labeled data.
method Combines spectrum-based deep metric learning and conditional random field. Uses center loss for spectrum-based features and Gaussian edge potentials for pixel-wise classification.
result Demonstrates advantages in classification accuracy and computation cost compared to classical methods.
Random feature method approximates operators with theoretical guarantees and reduced computation.
problem Approximating operators between infinite dimensional Banach spaces using machine learning.
method Random feature operator learning method with theoretical guarantees and error bounds.
result The random feature method can achieve similar or better test errors than kernel-based methods and neural networks with significantly reduced training times.
The paper analyzes how deep models memorize spurious features.
problem Understanding how deep models memorize spurious features in training data.
method Characterizes spurious feature memorization via model stability and feature alignment.
result Memorization of spurious features weakens as generalization capability increases.
Model, sample, and epoch-wise descents: exact solution of gradient flow in the random feature modelcs.LG
Analyzes the generalization and training errors of the random feature model over time.
problem Understanding the temporal behavior of generalization and training errors in deep learning.
method Uses Cauchy complex integral representations and random matrix methods based on linear pencils.
result Analytical solution of the full time-evolution path of generalization and training errors.
New method debiases feature importance in Random Forests.
problem MDI feature importance measure incorrectly assigns high importance to noisy features.
method Derive a new analytical expression for MDI and propose MDI-oob debiased feature importance measure.
result MDI-oob achieves state-of-the-art performance in feature selection from Random Forests.
New insights on how weight structure affects generalization in deep Gaussian feature models.
problem Understanding how weight structure impacts generalization in deep learning models.
method Using the replica trick from statistical physics to derive learning curves for models with structured Gaussian features.
result Allowing correlations between the rows of the first layer of features can aid generalization, while structure in later layers is generally detrimental.
We propose an empirical measure of the approximate accuracy of feature importance estimates in deep neural networks. Our results across several large-scale image classification datasets show that many popular interpretability methods produce estimates of feature importance that are not better than a random designation …
GP-DRF model handles variable-sized input and learns deep features.
problem Scaling deep Gaussian processes for variable-sized data.
method GP-DRF model combining GPs and DRF layers for efficient inference.
result GP-DRF outperforms standard GP and DRF models across various datasets.
New random feature maps for Laplacian and related kernels.
problem Challenges in approximating the Laplacian kernel and its generalizations.
method Developed random feature maps for Laplacian and related kernels, providing efficient sampling schemes.
result Demonstrated the efficacy of these random feature maps on real datasets.
Random feature approximation speeds up spectral methods and improves learning rates.
problem Improving the efficiency and generalization of spectral methods in large-scale algorithms.
method Combining random feature approximation with spectral regularization methods.
result Optimal learning rates for estimators over various regularity classes, including those not in the RKHS.
MORF improves Forests' performance on manifold data by considering feature indices.
problem Forest methods struggle with structured data like images and text.
method MORF incorporates feature locality by sampling random matrices from manifold-aware distributions.
result MORF outperforms ConvNets and other methods on manifold data.
A new model combines diffusion and random features for better interpretability and comparable performance.
problem Lack of theoretical justification and computational expense in diffusion models, and limited interpretability in random feature models.
method Developed a deep random feature model inspired by diffusion models, derived generalization bounds using score matching.
result The model achieves comparable performance to fully connected neural networks and provides theoretical generalization bounds.
Generalization in Representation Models via Random Matrix Theory: Application to Recurrent Networksmath.ST
We analyze generalization in deep learning models using random matrix theory.
problem Understanding the generalization error in deep learning models with random feature representations.
method Applying Random Matrix Theory to derive asymptotic generalization error formulas for various architectures.
result Linear ESNs are equivalent to ridge regression with exponentially time-weighted input covariance, revealing an inductive bias towards recent inputs.
Deep Gaussian Processes are reinterpreted as deep trigonometric networks for tractable inference.
problem Challenging inference in DGPs due to intractable marginalization in latent function space.
method Viewing DGPs as deep trigonometric networks with Bochner's theorem, and using the wide limit with a bottleneck to translate DGPs into deep trigonometric networks.
result The weight space view yields the same effective covariance functions as obtained in function space, and varying prior distributions over network parameters is equivalent to employing different kernels.
Proves deep networks can learn hierarchical structures efficiently.
problem Understanding how deep networks learn hierarchical structures in data.
method Random Hierarchy Models, gradient-based methods, layerwise training.
result Proves deep networks can efficiently learn hierarchical structures.
Study evaluates consistency of feature attribution in deep learning for multi-omics data.
problem Challenges in interpretability of deep learning models in biological research.
method Investigation of Shapley Additive Explanations (SHAP) on multi-view deep learning models applied to multi-omics data.
result SHAP rankings are sensitive to architecture and random initialization, suggesting caution.
Hyperparameter optimization aims to find the optimal hyperparameter configuration of a machine learning model, which provides the best performance on a validation dataset. Manual search usually leads to get stuck in a local hyperparameter configuration, and heavily depends on human intuition and experience. A simple al…
Subject-specific Deep Neural Networks for Count Data with High-cardinality Categorical Featurescs.LG
Proposes a new DNN framework for count data with high-cardinality features.
problem Real-world data often have correlations and high-cardinality categorical features that traditional DNNs overlook.
method Introduces a hierarchical likelihood learning framework with gamma random effects for Poisson DNNs.
result Improves prediction performance by capturing nonlinear effects and subject-specific cluster effects.
New method uses deep neural networks to interpolate spatiotemporal data.
problem Scalable interpolation of spatiotemporal data from growing earth observation systems.
method Bayesian deep learning with random feature expansions.
result Competitive or superior results compared to existing methods.
Random feature maps improve forecasting of chaotic dynamical systems.
problem Forecasting chaotic dynamical systems with high accuracy.
method Data-driven random feature maps with tanh activation, skip connections, and localization.
result Effective forecasting skill for dynamical systems with dimensions up to 512.
Deep kernel learning improves performance on complex tasks.
problem Limited flexibility of classical kernel methods for complicated tasks.
method Random Fourier Features (RFF) integrated into deep architecture.
result Significantly boosts flexibility and richness of kernel machines.
Study shows mixtures of nonlinearities can improve deep learning performance.
problem Improving deep learning performance with large datasets and complex models.
method Analyzed random feature regression with features for a random weight matrix and random bias vector .
result Mixture of nonlinearities can improve both training and test errors over a single nonlinearity.
Enhances graph neural networks with random walks to improve performance.
problem Limited input to graph neural networks, especially for molecular data.
method Random walk data processing to enrich graph neural network input.
result Shallow network outperforms deep GNNs using only node features.
The composition of multiple Gaussian Processes as a Deep Gaussian Process (DGP) enables a deep probabilistic nonparametric approach to flexibly tackle complex machine learning problems with sound quantification of uncertainty. Existing inference approaches for DGP models have limited scalability and are notoriously cum…
Framework combines random features with CDEs for efficient time-series learning.
problem Efficient training of time-series models with strong inductive bias.
method Random Fourier CDEs and Random Rough DEs using continuous-time reservoirs and log-ODE discretization.
result Unified perspective on random-feature reservoirs and path-signature theory.
Proposes Neural Random Subspace for deep learning.
problem Combining random subspace method with deep learning.
method Neural Random Subspace (NRS) integrating deep learning and random subspace.
result Achieves superior performance on 35 datasets and improves recognition tasks.
Deep networks learn hierarchical data by invariant representations.
problem How many examples are needed for deep networks to learn hierarchical data?
method Random Hierarchy Model: synthetic tasks inspired by language and images hierarchy.
result Deep networks learn by invariant representations and require a detectable number of correlations between low-level features and classes.
Framework explains how dual deep networks learn features from unlabeled data.
problem Understanding self-supervised learning with dual deep networks.
method Theoretical framework and hierarchical latent tree model.
result Deep ReLU networks learn latent variables through contrastive SSL.
New algorithm trains deep neural networks without global optimization.
problem Training deep neural networks efficiently and without global optimization.
method Uses random complex exponential activation functions and Markov Chain Monte Carlo sampling.
result Consistently attains theoretical approximation rate for residual networks.
GeFs use deep generative models to enhance prediction robustness and uncertainty.
problem Lack of principled methods to manipulate uncertainty in decision trees and random forests.
method Exploits Generative Forests (GeFs), a deep probabilistic model that extends Random Forests to represent full joint distributions.
result GeFs are uncertainty-aware classifiers capable of measuring robustness and detecting out-of-distribution samples.
Survey on random features for kernel approximation, focusing on algorithms, theory, and practical applications.
problem Efficiently approximating kernel methods for large-scale problems.
method Random features techniques to speed up kernel methods.
result Need for a high number of random features for good approximation quality.
Lower bound proves ridgeless regression performs poorly near interpolation threshold.
problem Proving performance of ridgeless regression near interpolation threshold.
method Distribution-independent lower bound for mean squared error in noisy ridgeless linear regression.
result Lower bound implies ridgeless regression performs poorly near interpolation threshold.
ARMED models improve deep learning interpretability and generalize better on clustered data.
problem Clustered data leads to spurious associations and poor model fitting.
method Adversarial regularization and mixed effects subnetworks.
result ARMED models outperform conventional methods in accuracy and generalization.
Deep Learning as Neural Low-Degree Filtering: A Spectral Theory of Hierarchical Feature Learningcs.LG
Deep learning explained through spectral filtering of hierarchical features.
problem Understanding how deep neural networks learn useful representations from data.
method Neural Low-Degree Filtering (Neural LoFi) as a stylized limit of gradient-based training.
result Predicts how representations are selected layer by layer and explains emergence of concepts.
Disordered Dynamics in High Dimensions: Connections to Random Matrices and Machine Learningcond-mat.dis-nn
Overview of high-dimensional dynamical systems and their applications to machine learning.
problem Characterizing behavior of high-dimensional dynamical systems driven by random matrices.
method Cavity method arguments, path integrals, dynamical mean field theory (DMFT), and random matrix resolvents.
result Connections between random matrix resolvents and DMFT response, and non-monotonic loss curves in training.