Develops AMITE for analyzing neural network nonlinearities.
problem Addressing difficulties in verification, explainability, and security in neural network analysis.
method Analytically modified integral transform expansion (AMITE) for neural network nonlinearities.
result First to provide six mutually exclusive desired expansion properties.
Neural networks solve SPDEs using Wiener chaos expansion.
problem Solving stochastic partial differential equations (SPDEs) numerically.
method Using neural networks in the truncated Wiener chaos expansion.
result Approximation rates for learning SPDE solutions with noise.
New method recovers signals from compressed measurements using generative networks with contractive layers.
problem Signal recovery from compressed measurements with generative network priors.
method Developed a new matrix concentration inequality (R2WDC) to relax expansivity conditions for generative networks.
result Signals in the range of a Gaussian generative network can be recovered from few linear measurements with contractive layers.
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 paper provides non-asymptotic Edgeworth expansions for neural network outputs.
problem Approximating deviations of finite-width neural networks from their Gaussian limit.
method Multidimensional Edgeworth expansions of arbitrary order for neural network outputs.
result Established a bound on the total variation distance between neural network output and its Edgeworth approximation.
Proves DCNNs with expansive convolution are strongly universally consistent.
problem Theoretical consistency of deep convolutional neural networks (DCNNs).
method Empirical risk minimization on DCNNs with expansive convolution (with zero-padding).
result DCNNs with expansive convolution are strongly universally consistent.
Deep neural networks have almost linear sample complexity.
problem Sample complexity of deep neural networks.
method o-minimal expansion of the real field to bound sample complexity.
result Almost linear bound on sample complexity of neural networks.
Dropout increases the generalization of neural networks by expanding the weight space.
problem Understanding and improving the generalization of neural networks.
method Introducing weight expansion and showing that dropout leads to it.
result Dropout increases the generalization of neural networks by expanding the weight space.
Paper provides Edgeworth expansions for network moments, improving accuracy of sampling distributions.
problem Accurate descriptions of sampling distributions of network moment statistics.
method Edgeworth expansion applied to studentized network moment statistics.
result Higher-order accurate approximation to sampling CDF of network moment statistics.
Gradient oversmoothing and expansion hinder deep GNN training, solved with normalization.
problem Gradient oversmoothing and expansion prevent deep GNN training.
method Proposed normalization method to constrain the Lipschitz bound of each layer.
result Residual GNNs with hundreds of layers can be efficiently trained with the proposed normalization.
Expanding neural networks improves their learning from noisy data.
problem Improving neural network performance in noisy conditions.
method Sparse expansion of neural network inputs, followed by pruning, enhances generalization.
result Sparse expansion of neural networks improves generalization performance, even after pruning.
Using sequence to sequence algorithms for query expansion has not been explored yet in Information Retrieval literature nor in Question-Answering's. We tried to fill this gap in the literature with a custom Query Expansion engine trained and tested on open datasets. Starting from open datasets, we built a Query Expansi…
This work proposes hyperbolic deep convolutional neural networks for better pattern recognition.
problem The limitations of Euclidean deep convolutional neural networks in capturing intricate patterns.
method Developed Hyperbolic DCNN based on Poincaré Disc, analyzing expansive convolution in non-Euclidean space.
result Hyperbolic convolutional architecture outperforms Euclidean ones in pattern recognition tasks.
Study on neural networks' performance under different normalizations as N grows.
problem Characterizing neural networks' performance under various normalizations.
method Developed an asymptotic expansion to analyze statistical output of shallow neural networks.
result No bias-variance trade-off exists to leading order in N, and variance decreases as normalization approaches mean field.
Bayesian inference for wide neural networks using Edgeworth expansion.
problem Analyzing the non-Gaussian behavior of wide neural networks in Bayesian inference.
method Proposed a non-Gaussian distribution using multivariate Edgeworth expansion for finite-width neural networks.
result Derived non-Gaussian posterior distribution in Bayesian regression tasks.
New insights on pruning deep networks by preserving function locality.
problem Designing effective pruning methods for deep neural networks.
method Revisited loss modeling using first and second order Taylor expansions, emphasizing locality.
result Both first and second order Taylor expansions can achieve similar performance in pruning.
RPN unifies various models with a reconciled polynomial network.
problem Unifying diverse models for deep function learning.
method RPN disentangles functions into inner products of expansion and reconciliation functions.
result RPN accurately approximates underlying functions for data distributions.
TEAM uses Taylor expansion to generate adversarial examples.
problem Vulnerability of deep neural networks to adversarial examples.
method Approximates DNN output using Taylor expansion and optimizes with Lagrange multiplier method.
result Improves robustness of DNNs through adversarial training.
Filters in a Convolutional Neural Network (CNN) contain model parameters learned from enormous amounts of data. In this paper, we suggest to decompose convolutional filters in CNN as a truncated expansion with pre-fixed bases, namely the Decomposed Convolutional Filters network (DCFNet), where the expansion coefficient…
Conventional deep learning classifiers are static in the sense that they are trained on a predefined set of classes and learning to classify a novel class typically requires re-training. In this work, we address the problem of Low-Shot network expansion learning. We introduce a learning framework which enables expandin…
Sharp privacy bounds for sequential analysis of sensitive data.
problem Privacy degradation under sequential analysis of sensitive data.
method Edgeworth expansion in f-differential privacy framework.
result Improved privacy bounds under composition with refined approximation accuracy.
Deep ReLU networks show that 4 layers suffice for unique input recovery.
problem Injectivity capacity of deep ReLU networks.
method Developed a program connecting deep ReLU injectivity to an l-extension of the ℓ0 spherical perceptrons, using random duality theory. result Only 4 layers are needed for unique input recovery, showing expansion saturation effect.
Sparse random features improve accuracy in data-scarce settings.
problem Limited accuracy of random feature methods in data-scarce applications.
method Sparse random feature expansion using compressive sensing.
result Improved generalization bounds for sparse random features.
New neural network models for functional data.
problem Handling non-linear functional data.
method Functional Direct Neural Network (FDNN) and Functional Basis Neural Network (FBNN) with gradient-based optimization.
result Demonstrated effectiveness in complex functional models.
Paper defines mathematical framework for neural network explainability.
problem Neural network explainability and equivariant operators.
method Mathematical framework based on Group Equivariant Non-Expansive Operators (GENEOs) and complexity measures.
result Formal properties and interpretability of Group Equivariant Operators (GEOs) defined.
Polynomial Chaos Expansion improves operator learning for PDEs.
problem Approximating mappings between infinite-dimensional functional spaces.
method Polynomial Chaos Expansion (PCE) for operator learning.
result PCE achieves strong performance in operator learning and uncertainty quantification.
Unified bounds for neural networks incorporating physical laws.
problem Limitations in existing generalization analyses for PINNs and VPINNs.
method Unified framework using Taylor expansion and Koopman-based analysis.
result High-rank networks can generalize well even with differential operators.
The paper approximates financial derivatives using neural networks and iterated integrals.
problem Approximating p-integrable financial derivatives. method Using iterated Stratonovich integrals and neural networks.
result Approximate solutions to the Lp-hedging problem. Polynomial time algorithm learns depth-2 neural networks with ReLU activations.
problem Learning depth-2 neural networks with non-zero bias terms and general ReLU activations.
method Robust tensor decomposition of Hermite expansions.
result Polynomial time and sample efficient learning of depth-2 networks with ReLU activations.
Unsupervised estimation of latent variable models is a fundamental problem central to numerous applications of machine learning and statistics. This work presents a principled approach for estimating broad classes of such models, including probabilistic topic models and latent linear Bayesian networks, using only secon…
Taylorized training improves neural network training at finite width.
problem Understanding and improving neural network training at finite width.
method Training the k-th order Taylor expansion of the neural network at initialization.
result Taylorized training agrees with full neural network training better as k increases and can significantly close the performance gap.
Rescaling expansiveness proven for k*-expansive vector fields.
problem Proving rescaling expansiveness for k*-expansive vector fields.
method Introducing and exploring singular-expansive flows.
result Rescaling expansiveness established for k*-expansive vector fields.
Residual networks' depth is mathematically equivalent to expanding an implicit ensemble size.
problem Understanding why deep residual networks are effective.
method Formal analysis of residual networks as ensembles of shallow models.
result Increasing network depth is equivalent to expanding the size of an implicit ensemble, revealing a hierarchical structure.
Deep neural network solves portfolio optimization with MGARCH and small transaction costs.
problem Optimizing portfolios with MGARCH and small transaction costs.
method Fixed-point RL algorithm using neural networks.
result NN algorithm shows positive testing performance.
Paper improves training physics-informed neural networks with model ensembles.
problem Training physics-informed neural networks (PINNs) is difficult due to convergence to wrong solutions.
method Proposes training an ensemble of PINNs, using ensemble agreement to expand the solution interval.
result Algorithm stabilizes PINN training and yields competitive performance.
New Hermite approximations accelerate convergence with adaptive coordinate transformations.
problem Accelerating convergence of spectral approximations for Hermite expansions.
method Using normalizing flows for adaptive coordinate transformations and deriving error estimates.
result Error estimates for Hermite expansions under adaptive coordinate transformations.
Model neural plasticity as binary optimization to dynamically activate or deactivate network units.
problem Dynamic learning and adaptability of neural networks.
method Model neural plasticity as an L0-norm regularized binary optimization problem, where units can be activated or deactivated based on a cost-benefit tradeoff. result Demonstrates that a single parameter k can modulate learning dynamics, unifying network sparsification and expansion. Deep ReLU networks can approximate smooth functions nearly optimally.
problem Approximating smooth functions with deep neural networks.
method Using Taylor expansions and deep ReLU network approximations, the paper establishes optimal approximation error bounds.
result Deep ReLU networks of width and depth O(NlnN) and O(LlnL) can approximate f∈Cs([0,1]d) with an error O(∥f∥Cs([0,1]d)N−2s/dL−2s/d). CN-DPM model tackles task-free continual learning for neural networks.
problem Current continual learning methods are limited to task-boundary known settings.
method CN-DPM uses a neural Dirichlet process mixture model for expansion-based task-free learning.
result CN-DPM successfully performs task-free continual learning for image classification and generation.
The paper derives expansions for Green's operators and resolvents using Hadamard methods.
problem Analyzing normally hyperbolic operators and their Green's functions.
method Hadamard expansions for powers of Green's operators and resolvents.
result Derives expansions involving Hadamard coefficients for advanced/retarded Green's operators.
Neural networks can approximate functionals on RKHS with error bounds.
problem Approximating functionals on RKHS using neural networks.
method Interpolating orthogonal projections in RKHS using point evaluations.
result Explicit error bounds for various kernels (inverse multiquadric, Gaussian, Sobolev).
MFNs parameterize non-local interactions through matrix equivariant functions, improving graph neural network performance.
problem Challenges in modeling non-local interactions in graphs, such as oversmoothing and oversquashing.
method Matrix Function Neural Networks (MFNs) using resolvent expansions for non-local interactions.
result Achieves state-of-the-art performance in graph benchmarks and captures intricate non-local interactions.
Finite-width neural networks are approximated by Gaussian processes with finite size corrections.
problem Understanding the behavior of finite-width neural networks as they approach infinite width.
method Analyzing the distribution of outputs at initialization for large, finite neural networks with a single hidden layer.
result The distribution of outputs at initialization is well described by a Gaussian perturbed by the fourth Hermite polynomial, with the perturbation scale inversely proportional to the number of network units.
New method improves neural network performance by focusing on steep function regions.
problem Improving neural network performance by focusing on steep function regions.
method Variance Based Samples Weighting (VBSW) using labels local variance to weight training points.
result Significantly increases the performances of neural networks for various tasks.
We develop a neural network model to classify liver cancer patients into high-risk and low-risk groups using genomic data. Our approach provides a novel technique to classify big data sets using neural network models. We preprocess the data before training the neural network models. We first expand the data using wavel…
A new 1-iteration GMM learning algorithm improves robustness and accuracy.
problem Improving robustness and accuracy in Gaussian Mixture Model learning.
method GMM expansion idea, 1-iteration learning algorithm, theoretical proof of convergence.
result Guaranteed convergence of the new algorithm regardless initial parameters.
New algorithm finds corrupted vertices in graphs with few queries.
problem Adversarial tampering of graph edges and vertices.
method Active learning algorithm with polynomial query complexity.
result Efficiently recovers corrupted vertices with small query complexity.
New findings show neural network training loss follows a power law over time.
problem Understanding the optimization process of neural networks during training.
method Spectral analysis of the integral operator representing the linearized evolution of a large network.
result The loss function in neural network training follows a power law behavior, L(t)∼t−ξ, with exponent ξ determined by network parameters and data characteristics.