DeepWeightFlow generates diverse neural network weights efficiently.
problem Generating complete neural network weights efficiently and accurately.
method Flow Matching in weight space with Git Re-Basin and TransFusion.
result DeepWeightFlow generates high-accuracy neural networks without fine-tuning.
Affine spiking neural networks learn efficiently and generalize well.
problem Learning with spiking neural networks, especially with positive weights.
method Affine encoders and decoders, continuous parameter dependence, gradient-based training.
result Affine spiking neural networks can approximate shallow ReLU networks and generalize well.
Graphs of neural networks are represented to preserve symmetry, improving performance across various tasks.
problem Lack of equivariance in neural network representations of other neural networks.
method Represent neural networks as computational graphs and use graph neural networks to preserve permutation symmetry.
result Single model encodes diverse neural architectures, outperforming state-of-the-art methods.
Generalization bounds derived for neural ODEs and deep residual networks.
problem Understanding the generalization capability of neural ODEs and deep residual networks.
method Lipschitz-based argument and analogy with deep residual networks.
result A generalization bound involving the magnitude of weight matrix differences.
New method improves neural network robustness by identifying functions rather than parameters.
problem Neural networks' lack of robustness to distribution shifts.
method Identify the function represented by quadratic networks, not their parameters.
result Obtain robust generalization bounds for neural networks.
Wide neural networks on R generalize well with early stopping.
problem Understanding generalization in wide neural networks.
method Analysis of spectral properties of NTK and NNK, convergence of NNK to NTK, minimax rates, and early stopping strategy.
result Wide neural networks trained with early stopping achieve the minimax rate and generalize well.
Study bounds graph neural networks' over-parameterized error.
problem Understanding graph neural networks' performance in over-parameterized regimes.
method Developed mean-field regime bounds for graph convolutional and message passing neural networks.
result Established upper bounds with a convergence rate of O ( 1 / n ) O(1/n) O ( 1/ n ) for generalization error. We establish a margin based data dependent generalization error bound for a general family of deep neural networks in terms of the depth and width, as well as the Jacobian of the networks. Through introducing a new characterization of the Lipschitz properties of neural network family, we achieve significantly tighter g…
Improved graph neural network bounds using graph diffusion matrix.
problem Empirical performance of graph neural networks on real-world graphs.
method Unified model of graph neural networks, focusing on feature diffusion matrix stability.
result Generalization bounds scale with largest singular value of feature diffusion matrix, smaller than prior bounds.
The accuracy of deep learning, i.e., deep neural networks, can be characterized by dividing the total error into three main types: approximation error, optimization error, and generalization error. Whereas there are some satisfactory answers to the problems of approximation and optimization, much less is known about th…
Novel framework explains generalization in deep neural networks.
problem Understanding and improving generalization in deep neural networks.
method Topological Quantum Neural Networks as the semi-classical limit of Deep Neural Networks.
result Demonstrates that the perceptron, viewed as the semi-classical limit, achieves similar results to standard neural networks without training.
Paper analyzes sample complexity of polynomial neural networks.
problem Understanding the sample complexity of polynomial neural networks.
method Extends previous literature to polynomial neural networks and analyzes sample complexity.
result Obtains novel results on sample complexity of polynomial neural networks.
CNN-F uses generative feedback to improve neural networks' robustness to perturbations.
problem Neural networks' vulnerability to input perturbations like noise and attacks.
method Enforces self-consistency in neural networks by incorporating generative recurrent feedback.
result CNN-F shows significantly improved adversarial robustness compared to conventional CNNs.
This paper compares deeper and wider neural networks for optimal generalization error in Sobolev losses.
problem The dilemma of choosing between deeper or wider neural networks for optimal generalization error.
method Analytical investigations into the influence of sample points, parameters, and loss function regularity on neural network architecture.
result A higher number of parameters favors wider neural networks, while more sample points and greater loss function regularity favor deeper neural networks.
neuralGAM package interprets neural networks by fitting them to feature contributions.
problem difficulty understanding neural network decisions
method Generalized Additive Neural Networks (GAM)
result interpretable Deep Learning model with accurate feature contributions
Model-based neural networks generalize better than ReLU networks for sparse recovery.
problem Understanding and quantifying the superior generalization of model-based neural networks.
method Using complexity measures like global and local Rademacher complexities, the paper provides theoretical bounds on generalization and estimation errors.
result Model-based neural networks exhibit higher generalization capabilities for sparse recovery problems compared to ReLU networks.
New bound for neural nets on non-iid data.
problem Generalization of deep nets for dependent data.
method Establishes a generalization bound for feed-forward neural networks on φ φ φ -mixing data. result Proves neural nets can generalize well on non-iid data.
PCGs encompass a broader range of neural networks.
problem Understanding the broader scope of neural network models.
method Proving PCGs as a superset of feedforward neural networks.
result PCGs represent a wider class of neural network models.
The paper uses geometry to understand how neural networks learn.
problem Understanding the learning capability of neural networks.
method Statistical and differential geometric analysis of neural networks performing simple regression.
result Neural networks with higher generalization capability have a slower convergence rate.
New study shows neural networks need many samples for training.
problem How much data is needed to train a ReLU feed-forward neural network?
method Theoretical and empirical analysis of ReLU feed-forward neural networks.
result Generalization error scales at 1 / n 1/\sqrt{n} 1/ n in sample size n n n . Quantum neural networks generalize better due to flatter parameter space.
problem Generalization in quantum neural networks.
method Mapped feature data to a quantum state, applied unitary evolution, and measured for classification.
result Quantum neural networks have better generalization than classical networks.
GraphMoE generates random graphs using neural networks and graphlets.
problem Learning generative models for random graphs.
method GraphMoE uses a neural network trained with graphlets and subgraph counts to match the distribution of random graphs.
result GraphMoE can generate graphs that mimic various real-world datasets and fool graph classifiers.
Recently low displacement rank (LDR) matrices, or so-called structured matrices, have been proposed to compress large-scale neural networks. Empirical results have shown that neural networks with weight matrices of LDR matrices, referred as LDR neural networks, can achieve significant reduction in space and computation…
The paper analyzes how low-rank layers in neural networks improve generalization.
problem Understanding how low-rank layers affect generalization in neural networks.
method Applying Maurer's chain rule for Gaussian complexity to analyze rank and spectral norm constraints.
result Deep networks with low-rank layers achieve better generalization than those with full-rank layers.
Paper calculates eigenvalue decay rates for neural network kernels on general domains.
problem Determining eigenvalue decay rates for neural network kernels on arbitrary domains.
method Proved dynamics of wide neural networks approximates NTK on general domains, used minimax optimality and interpolation spaces.
result Provided strategy to calculate eigenvalue decay rates for neural network kernels.
Smartfluidnet accelerates Eulerian fluid simulation with neural networks.
problem Current neural network methods for Eulerian fluid simulation lack flexibility and generalization.
method Smartfluidnet automates model generation and dynamic switching to meet user requirements.
result Smartfluidnet achieves 1.46x and 590x speedup compared to state-of-the-art models, with better simulation quality.
Improved deep neural network generalization through noise resilience.
problem Understanding and predicting generalization error of deep neural networks.
method Noise resilience measures to predict generalization error.
result Secured 5th position in the PGDL competition at NeurIPS 2020.
Modular neural networks generalize better with less data.
problem Theoretical and practical understanding of how modularity improves neural network generalization.
method Theoretical analysis of sample complexity, development of a novel learning rule.
result Modular networks require fewer samples to generalize compared to nonmodular networks, especially in high-dimensional tasks.
Unified analysis of neural networks for sparse signal recovery.
problem Sparse signal recovery from few linear measurements.
method Introduces a general class of neural networks with weight-sharing, analyzes their Rademacher complexity, and derives generalization bounds.
result Derives generalization bounds that depend linearly on the number of parameters and depth, applicable to various neural network types.
Study clarifies Bayesian generalization error in CBM for 3-layered linear neural networks.
problem Understanding the generalization error in concept bottleneck models.
method Mathematical analysis of Bayesian generalization error and free energy in CBM for 3-layered linear neural networks.
result CBM significantly alters the parameter region and Bayesian generalization error compared to standard models.
Survey on statistical theories of neural networks, focusing on approximation, training dynamics, and generative models.
problem Understanding the statistical properties and training dynamics of neural networks.
method Review of existing literature on neural networks from three perspectives: approximation, training dynamics, and generative models.
result Theoretical insights into neural network training dynamics and generative models.
Graph Metanetworks process diverse neural architectures efficiently.
problem Processing diverse neural architectures efficiently.
method Builds metanetworks using graph neural networks to process graphs representing input neural networks.
result Proves GMNs are expressive and equivariant to parameter permutation symmetries.
We propose two neural network based mixture models in this article. The proposed mixture models are explicit in nature. The explicit models have analytical forms with the advantages of computing likelihood and efficiency of generating samples. Computation of likelihood is an important aspect of our models. Expectation-…
Study shows depth improves trainability of neural networks by improving kernel conditioning.
problem Improving trainability of neural networks with random initialization and overparameterization.
method Analyzes the role of depth in training neural networks, proving that depth improves conditioning of kernel matrices.
result General result showing depth improves trainability of neural networks by improving the conditioning of kernel matrices.
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.
Neural networks with DAGs show linearity as width increases.
problem Understanding linearity in neural networks with arbitrary DAG structures.
method Analyzing the transition to linearity in networks with arbitrary DAGs, characterizing width by minimum in-degree.
result General neural networks with DAGs exhibit linearity as width approaches infinity.
Generalizes neural tangent kernel analysis for two-layer networks with noise and regularization.
problem Limitations of NTK analysis in deep learning practice.
method Generalized NTK analysis for two-layer neural networks with weight decay and gradient noise.
result Noisy gradient descent with weight decay exhibits 'kernel-like' behavior and converges linearly.
Equivariant neural networks are a class of neural networks designed to preserve symmetries inherent in the data. In this paper, we introduce a general method for modifying a neural network to enforce equivariance, a process we refer to as equivarification. We further show that group convolutional neural networks (G-CNN…
Recently, with convolutional neural networks gaining significant achievements in many challenging machine learning fields, hand-crafted neural networks no longer satisfy our requirements as designing a network will cost a lot, and automatically generating architectures has attracted increasingly more attention and focu…
Equivariant neural networks use symmetry to interpret complex data.
problem Interpreting and understanding the behavior of equivariant neural networks.
method Decompose layers into simple representations and analyze nonlinear activation functions.
result Equivariant neural networks can be interpreted using a filtration generalizing Fourier series.
Neural networks outperform kernels by learning features better.
problem Current theories of feature learning do not adequately assess feature quality.
method Introduced feature quality metric and examined existing theories empirically.
result Current theories of feature learning do not provide a sufficient foundation for neural network generalization.
Gradient descent methods for deep ReLU networks achieve optimal generalization rates.
problem Generalization of gradient descent methods for deep neural networks
method Establishing minimax-optimal rates for GD and SGD with deep ReLU networks
result Gradient descent methods for deep ReLU networks achieve optimal generalization rates
Neural FGP learns portfolio generating functions from data.
problem Portfolio optimisation challenges in estimating drifts and covariances.
method Neural network approach to learn G ( ⋅ ) G(\cdot) G ( ⋅ ) from market data. result Neural FGP outperforms classical benchmarks.
A neural network model minimizes region-based free energy for faster inference in MRFs.
problem Efficient inference in complex Markov random fields (MRFs).
method Region-based Energy Neural Network (RENN) that directly minimizes region-based free energy.
result RENN outperforms other methods in marginal distribution estimation, partition function estimation, and MRF learning.
Study on hidden units in finite Bayesian neural networks and their tail properties.
problem Understanding the behavior of hidden units in finite Bayesian neural networks.
method Introduced a generalized Weibull-tail property to describe hidden units tails.
result Unit priors become heavier-tailed going deeper, providing insights into finite Bayesian neural networks.
We applied pre-defined kernels also known as filters or masks developed for image processing to convolution neural network. Instead of letting neural networks find its own kernels, we used 41 different general-purpose kernels of blurring, edge detecting, sharpening, discrete cosine transformation, etc. for the first la…
Study reveals hidden null components in overparametrized neural networks.
problem Hidden null components in overparametrized neural networks.
method Structure theorem of null space for neural networks using ridgelet transforms.
result Null components can be uniquely written as linear combinations of ridgelet transforms.
We present an efficient coresets-based neural network compression algorithm that sparsifies the parameters of a trained fully-connected neural network in a manner that provably approximates the network's output. Our approach is based on an importance sampling scheme that judiciously defines a sampling distribution over…