Paper studies the theoretical equivalence between implicit and explicit neural networks in high dimensions.
problem Lack of theoretical analysis of implicit and explicit neural networks.
method Examined high-dimensional implicit neural networks and established their equivalence to explicit networks.
result Equivalence between implicit and explicit neural networks in high dimensions.
Characterizes Bayesian networks up to unconditional equivalence.
problem Characterizing Bayesian networks up to unconditional equivalence.
method Transformational characterization via undirected graphs and specified moves.
result Two DAGs are in the same UEC if and only if one can be transformed into the other via a finite sequence of moves.
Study shows deterministic equivalent for neural network kernel convergence.
problem Understanding convergence of neural network kernels.
method Analyzes empirical spectral distribution of Conjugate Kernel, proving convergence to a deterministic limit.
result Obtains a deterministic equivalent for the Stieltjes transform and resolvent of the Conjugate Kernel.
GENNI visualises neural network symmetries for better identifiability.
problem Identifying functionally equivalent parameters in neural networks.
method Proposes GENNI, an algorithm to efficiently visualise equivalence classes.
result Allows better exploration of identifiability questions in neural networks.
Deep and wide networks are shown to be equivalent in terms of their capability.
problem The relationship between the width and depth of neural networks.
method Formulated transforms to map networks, used polynomial representations.
result Deep and wide networks are quasi-equivalent with an arbitrarily small error.
The neural tangent kernel equivalence theorem fails in practice.
problem Does the neural tangent kernel (NTK) equivalence theorem hold in practical neural network training?
method Rigorously derived NTK and conducted numerical experiments to evaluate the equivalence theorem.
result Adding a layer to a neural network and the corresponding updated NTK do not yield matching changes in predictor error.
System uses neural networks to prove program equivalence via rewrite rules.
problem Proving equivalence between two dataflow graphs.
method Developed a graph-to-sequence neural network trained on example generation to find semantics-preserving rewrite rules.
result System correctly outputs a rewrite sequence for 96% of program pairs, proving equivalence.
Deep networks without non-linearities are equivalent to shallow ones.
problem Training deep orthogonal linear networks with no non-linearity.
method Riemannian gradient descent and gradient descent on factorization.
result Training deep overparametrized networks is equivalent to shallow ones.
Approaches to learning Bayesian networks from data typically combine a scoring function with a heuristic search procedure. Given a Bayesian network structure, many of the scoring functions derived in the literature return a score for the entire equivalence class to which the structure belongs. When using such a scoring…
Transforms between neural networks using manifold-learning techniques.
problem Establish equivalence between different neural networks.
method Diffusion maps with a Mahalanobis-like metric to construct transformations between network outputs and internal neuron activations.
result Established equivalence classes between neural networks trained on various data types.
Tangle machines are topologically inspired diagrammatic models. Their novel feature is their natural notion of equivalence. Equivalent tangle machines may differ locally, but globally they are considered to share the same information content. The goal of tangle machine equivalence is to provide a context-independent me…
Method detects neural network equivalence via matrix ensembles and spectral analysis.
problem Detecting equivalence among different deep learning architectures.
method Generating Mixed Matrix Ensembles (MMEs) and matching to conjugate circular ensembles.
result Empirical evidence shows vanishing differences in spectral densities with long tail decay rates.
Deep networks become equivalent to linear models in large data regimes.
problem Understanding the behavior of deep neural networks in large data regimes.
method Information-theoretic analysis of fully-trained neural networks in proportional scaling regime.
result Proves deep Gaussian equivalence principle, showing deep networks can be simplified to linear models.
The study shows that generative models can be effectively used to understand neural network performance.
problem Understanding the impact of data structure on neural network performance.
method Gaussian equivalence to model training data from generative models.
result The performance of neural networks can be fully captured by an appropriately chosen Gaussian model.
Single-spike neurons can approximate as well as multi-spike neurons.
problem Limitation of single-spike neurons in spiking neural networks.
method Comparison of single-spike and multi-spike neural networks.
result Single-spike and multi-spike neural networks are equivalent in approximation capabilities.
This paper explores transforming deep neural networks into simpler structures while preserving or approximating their functionality.
problem Transforming deep neural networks into simpler structures while preserving or approximating their functionality.
method Constructive proof of global linear approximation, removal of inactive or always active ReLUs, and experiments with regularization and adversarial training.
result For any feed-forward ReLU network, there exists a global linear approximation to a 2-hidden-layer shallow network with a fixed number of units.
This work establishes the equivalence between neural networks and support vector machines.
problem Establishing the equivalence between neural networks and support vector machines.
method Proposed a method to establish the equivalence between infinitely wide neural networks trained by soft margin loss and standard soft margin SVMs with NTK trained by subgradient descent.
result The equivalence between NN and SVM is established, enabling practical applications such as non-vacuous generalization bounds and robustness certificates.
This paper reconstructs equivalence classes in 1D neural networks.
problem Reconstructing equivalence classes in neural networks.
method Singular Riemannian geometry approach.
result Algorithm to build the set of points on the same equivalence class.
Deep neural networks and Gaussian processes are shown to be equivalent through activation functions.
problem Understanding the relationship between neural networks and Gaussian processes.
method Developing an equivalence theory based on activation functions and kernels.
result Models can be seen as neural networks with improved uncertainty prediction or deep Gaussian processes with increased accuracy.
Unified scaling laws reveal how model size and training time impact neural network performance.
problem Understanding how much performance improvement can be expected from scaling model size or data volume.
method Established scale-time equivalence and combined it with a linear model analysis of double descent.
result Unified theoretical scaling laws explain previously unexplained phenomena and offer a more accessible path to training large models.
The study explores how Matrix Product States can represent boolean and continuous functions.
problem Representing arbitrary boolean and continuous functions using Matrix Product States.
method Developed a construction method for MPS to represent boolean gates and proved density in continuous function space.
result MPS can accurately represent arbitrary boolean functions and continuous functions densely.
A new sampler improves the inference of causal structures from observational data.
problem Inferring causal relationships from observational data when DAGs are Markov equivalent.
method Developed a non-reversible Markov chain, Causal Zig-Zag sampler, targeting Markov Equivalence Classes of DAGs.
result The sampler improves mixing and offers efficient algorithms for DAG inference.
NeuroDiff improves neural network equivalence verification with fine-grained approximations.
problem Verifying the equivalence of compressed neural networks.
method Symbolic and fine-grained approximation technique for differential verification.
result NeuroDiff achieves up to 1000X speedup and 5X accuracy improvement.
This paper explores fuzzy systems' equivalence to neural networks and other machine learning methods.
problem Designing optimal fuzzy systems and overcoming challenges.
method Comparative analysis of Takagi-Sugeno-Kang fuzzy systems with neural networks, mixture of experts, CART, and stacking ensemble regression.
result Functional equivalence between fuzzy systems and machine learning methods.
A new complexity measure for neural networks improves upon classical methods.
problem Lack of a refined complexity measure for comparing different neural network architectures, especially permutation-invariant ones.
method Introduced an equivalence relation among linear functions and counted them relative to this relation.
result The new complexity measure clearly distinguishes between different models and increases exponentially with depth.
Develops exact convex optimization formulations for neural networks.
problem Training two-layer neural networks with rectified linear units.
method Uses semi-infinite duality and minimum norm regularization to develop exact convex optimization formulations.
result Shows equivalence of ReLU networks trained with weight decay to block ℓ1 penalized convex models. Deterministic method for certifying neural network robustness.
problem Certifying neural network robustness against adversarial attacks.
method Equivalence between training and Gaussian averaging for robustness certification.
result Comparable certified accuracy and robustness to stochastic methods but with single model evaluation.
An interesting approach to analyzing neural networks that has received renewed attention is to examine the equivalent kernel of the neural network. This is based on the fact that a fully connected feedforward network with one hidden layer, a certain weight distribution, an activation function, and an infinite number of…
New approach to neural networks by incorporating observation noise and arbitrary prior means.
problem Misspecification on noisy data and limitations of NTK-GP equivalence.
method Introducing a regularizer for observation noise and proposing a shifted network for arbitrary prior means.
result Removes key obstacles to practical Gaussian process modeling in neural networks.
Study of two-layer NNs under Gaussian mixtures data, proving polynomial models equivalent to neural networks.
problem Training and generalization performance of two-layer NNs under structured Gaussian mixture data.
method Asymptotic analysis of two-layer NNs after one gradient descent step under Gaussian mixture data assumption.
result High-order polynomial models equivalent to nonlinear neural networks under certain conditions.
Recent reports have described that learning Bayesian networks are highly sensitive to the chosen equivalent sample size (ESS) in the Bayesian Dirichlet equivalence uniform (BDeu). This sensitivity often engenders some unstable or undesirable results. This paper describes some asymptotic analyses of BDeu to explain the …
Study deep maxout networks and their equivalence to Gaussian processes.
problem Understanding neural networks with infinite width.
method Derive equivalence between deep maxout networks and Gaussian processes, characterize maxout kernel, and provide efficient numerical implementation.
result Bayesian inference based on deep maxout network kernel leads to competitive results compared to finite-width counterparts and deep neural network kernels.
This study examines the practical equivalence of Laplace and neural tangent kernels.
problem Understanding the practical equivalence of Laplace and neural tangent kernels.
method The study matches the kernels exactly and by matching posteriors of a Gaussian process. It also analyzes the kernels in R^d and experiments with them in regression tasks.
result The Laplace and neural tangent kernels are practically equivalent.
DEQs and explicit networks are nearly equivalent for Gaussian mixtures.
problem Understanding the equivalence between DEQs and explicit neural networks.
method Random matrix theory and analysis of kernel matrices.
result A shallow explicit network can mimic the kernel of a DEQ.
This paper introduces a new metric for deep learning networks based on their classification performance.
problem The mystery and black-box nature of deep learning networks.
method Proposes a new distance measure based on the probabilistic performance of deep learning networks.
result The proposed metric space is compact and coincides with the quotient topological space.
Paper converts deep networks to flat, equivalent kernel machines.
problem Capacity control and uniform convergence in deep learning.
method Push-forward transformation from deep networks to indefinite kernel machines.
result Flat network weights are Lp-norm regularized (0<p<1).
Study on identifying and inferring nonlinear dynamics on unknown networks.
problem Identifying network structure in nonlinear dynamic systems with unknown interactions.
method Showed network structure is not generically identified, requiring sufficient spectral heterogeneity. Developed necessary and sufficient conditions for identification and proposed a semiparametric estimator.
result Necessary and sufficient conditions for identification of network structure in nonlinear dynamic systems.
Bayesian CNNs with many channels are equivalent to Gaussian processes.
problem Understanding the behavior of deep convolutional networks in the infinite channel limit.
method Deriving an equivalence between multi-layer convolutional neural networks and Gaussian processes, introducing a Monte Carlo method for estimation.
result The GPs corresponding to CNNs with and without weight sharing are identical in the infinite channel limit.
Deep neural networks favor symmetric structures, enabling multilevel symmetries.
problem Understanding and optimizing deep neural networks.
method Formulating DNN training as convex Lasso problems with geometric algebra.
result Deep networks inherently favor symmetric structures, enabling multilevel symmetries.
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.
BDeu marginal likelihood score is a popular model selection criterion for selecting a Bayesian network structure based on sample data. This non-informative scoring criterion assigns same score for network structures that encode same independence statements. However, before applying the BDeu score, one must determine a …
K-Means and RBF networks are shown to be equivalent under certain conditions.
problem Discrete clustering vs. continuous optimization in machine learning.
method Established variational and gradient-based equivalence between K-Means and RBF networks.
result Gradient-based updates of RBF centers recover K-Means centroid update rule.
Study shows how feature weighting affects neural network regularization.
problem Understanding how feature weighting influences neural network regularization.
method Derived equivalence paths connecting different weighting matrices and ridge regularization levels.
result Ridge estimators trained on weighted features are asymptotically equivalent when evaluated against test vectors.
Deep networks are mathematically equivalent to kernel machines learned by gradient descent.
problem Understanding the learned representations of deep learning models.
method Using gradient descent to learn deep networks, showing they are equivalent to kernel machines.
result Deep network weights are a superposition of training examples, revealing the learned function.
The paper introduces a multilevel initialization method for deep neural networks.
problem Training very deep neural networks with layer-parallel methods.
method Continuous interpretation of training as optimal control, using time-dependent ODEs for neural network discretization, and a refinement strategy across the time domain.
result The method creates deep networks with good initializations from coarser networks, reducing training time and providing regularization.
Boosts linear neurons for faster convergence in neural networks.
problem Optimizing neural networks' neurons in function space.
method Reparameterizing network to whiten neuron features using Boosted Backpropagation.
result Equivalent to preconditioned gradient descent, leading to faster convergence.
Study bridges GARCH and NN models for volatility forecasting.
problem Lack of interaction between GARCH and NN approaches for volatility forecasting.
method Established equivalence between GARCH and NN models, introduced GARCH-NN approach.
result GARCH-NN approach enhances volatility forecasting compared to standalone models.
BSA reduces network data by interpreting feature subspaces.
problem Interpreting feature subspaces of unlabeled network data.
method Barycentric Subspace Analysis (BSA) for unlabeled networks.
result BSA provides a more interpretable approach compared to PCA.