Characterizes neural kernel and NNGP for various activations.
problem Understanding neural kernels and NNGP for non-RELU activations.
method Characterization of RKHS for various activation functions.
result Broad class of non-infinitely smooth activations generate equivalent RKHSs at different depths.
New method speeds up neural kernel computations for various activations.
problem Inefficient computation of neural kernels for general activations.
method Fast sketching method using truncated Hermite expansion.
result 106x speedup for approximate CNTK computation on CIFAR-10.
Improved neural network accuracy with multi-Kernel activation functions.
problem Designing effective activation functions for neural networks.
method Developed multi-Kernel activation functions (multi-KAF) combining multiple kernel models.
result Multi-KAFs enhance convolutional networks' accuracy on handwritten Latin OCR tasks.
New activation functions improve neural network stability and generalize well.
problem Proving theoretical generalization of non-parametric activation functions.
method Stability analysis of non-convex models trained with SGD.
result Neural networks with kernel activation functions generalize well with SGD.
Study on deep neural networks using branching processes and Mehler's formula.
problem Understanding the mathematical role of activation functions in compositional neural networks.
method Connection between compositional kernels and branching processes via Mehler's formula; new random features algorithm.
result Explicit formulas for eigenvalues of compositional kernels quantify complexity.
New active learning method for kernel selection improves efficiency and accuracy.
problem Real-world applications where acquiring true labels is costly or time-consuming.
method Active Multiple Kernel Learning (AMKL) with adaptive kernel selection (AMKL-AKS).
result AMKL-AKS achieves optimal sublinear regret and better performance with fewer labeled data.
m-arcsinh improves SVM and MLP reliability and speed in scikit-learn.
problem Improving SVM and MLP reliability and speed in scikit-learn.
method Modified arcsinh function for kernel and activation in SVM and MLP.
result Competitive classification performance and reliability of SVM and MLP with m-arcsinh.
Neural networks are generally built by interleaving (adaptable) linear layers with (fixed) nonlinear activation functions. To increase their flexibility, several authors have proposed methods for adapting the activation functions themselves, endowing them with varying degrees of flexibility. None of these approaches, h…
Generalizes NTK for surrogate gradient learning in neural networks.
problem Lack of theoretical foundation for surrogate gradient learning.
method Generalizes neural tangent kernel (NTK) for surrogate gradient learning (SGL).
result Surrogate gradient NTK provides a good characterization of SGL.
Active data collection improves convergence rates in operator learning.
problem Improving convergence rates in operator learning with linear target and stochastic input.
method Active data collection strategies with mean-zero stochastic process and continuous covariance kernels.
result Achieves arbitrarily fast error convergence rates with eigenvalue decay of covariance kernels.
Optimal kernel learning improves GP regression for high-dimensional inputs.
problem High computational costs and low prediction accuracy in GP models with many inputs.
method Approximates GP covariance with a convex combination of kernel functions, identifying active variables.
result Improves prediction accuracy and correctly identifies active input variables.
The paper studies how neural networks evolve representations, finding a unique fixed point for nonlinear activations.
problem Understanding how neural networks transform input data across layers.
method Theoretical framework for the evolution of the kernel sequence, using mean-field regime and Hermite polynomials.
result For nonlinear activations, the kernel sequence converges globally to a unique fixed point.
New algorithm reduces neural net error in contextual bandits.
problem Neural contextual bandits with general activation functions.
method Proposed an efficient algorithm with sublinear regret bound.
result Demonstrated provably sublinear regret bound in finite regime.
SANs use sparse activation functions to compress data representations.
problem Learning meaningful features without considering compression.
method Introduce φ metric, define activation functions, and present SANs.
result SANs achieve small description length and interpretable kernels.
SANs use sparse activation functions to minimize model complexity.
problem Model complexity in unsupervised learning.
method Introduce φ metric, define activation functions, present Sparsely Activated Networks (SANs).
result SANs with selected activation functions have small description length and interpretable kernels.
New kernels from ELU and GELU networks reveal non-trivial fixed points.
problem Understanding fixed-point dynamics in deep neural networks with ELU and GELU activations.
method Deriving covariance functions and analyzing fixed-point dynamics of ELU and GELU networks.
result ELU and GELU networks exhibit non-trivial fixed-point dynamics, explaining implicit regularization in overparameterized models.
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.
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…
This paper analyzes convergence rates of neural networks in the deep learning regime.
problem Understanding convergence rates of neural networks in the deep learning regime.
method Analyzing the Neural Tangent Kernel (NTK) convergence rates in the large depth limit.
result Quantifies the impact of initialization and activation function on NTK convergence rates.
The effectiveness of deep neural architectures has been widely supported in terms of both experimental and foundational principles. There is also clear evidence that the activation function (e.g. the rectifier and the LSTM units) plays a crucial role in the complexity of learning. Based on this remark, this paper discu…
Predicts atomization energy with high accuracy using graph kernels and active learning.
problem Predicting molecular atomization energy with high accuracy.
method Gaussian process regression with marginalized graph kernel, active learning.
result Achieves mean absolute error of 0.62 +- 0.01 kcal/mol with 2000 training samples.
The paper connects neural networks to physics using probability theory.
problem Creating neural networks that follow physical laws.
method Applying the central limit theorem and Gaussian process theory to neural networks.
result Neural networks can be designed to obey physical laws by choosing appropriate activation functions.
The paper uses Banach spaces to analyze neural networks.
problem Understanding the function spaces of neural networks.
method Theory of reproducing kernel Banach spaces.
result Representer theorem for wide class of Banach spaces.
Wide neural networks can learn complex functions like gravitational force law.
problem Learning complex functions like gravitational force law with neural networks.
method Extending theoretical bounds to analytic functions on the sphere using SGD and ReLU networks.
result Wide ReLU networks can learn analytic functions efficiently with proportional number of samples.
Spectral analysis shows neural networks separate from linear methods in approximating functions.
problem Separating two-layer neural networks from linear methods in function approximation.
method Spectral-based approach using Kolmogorov width and kernel spectrum.
result Upper and lower bounds on separation, explicit hard functions identified.
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.
Wide residual networks generalize well with uniform convergence to RNTK as width increases.
problem Understanding the generalization ability of wide residual networks.
method Uniform convergence of residual network kernel to residual neural tangent kernel (RNTK).
result Generalization error converges to kernel regression error with respect to RNTK.
New active learning methods use statistical leverage scores to select examples efficiently.
problem Efficiently selecting labeled examples for high model accuracy with limited labeled data.
method Proposes ALEVS and DBALEVS methods based on statistical leverage scores.
result DBALEVS selects diverse, representative examples efficiently.
This work challenges the Neural Tangent Kernel's role in overparameterized neural networks, especially with large width and depth.
problem The Neural Tangent Kernel's behavior in overparameterized neural networks with large width and depth is unclear.
method Experimental and theoretical analysis of ReLU networks with large width and depth.
result The aggregate norm of hidden neuron deviations does not vanish in infinitely-wide ReLU networks, indicating non-trivial behavior.
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.
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 fundamental goal in network neuroscience is to understand how activity in one region drives activity elsewhere, a process referred to as effective connectivity. Here we propose to model this causal interaction using integro-differential equations and causal kernels that allow for a rich analysis of effective connecti…
New insights into how overfitting affects neural networks' performance.
problem Understanding the generalization of overfitted two-layer neural networks.
method Analyzing the NTK model with ReLU activation, focusing on min ℓ2-norm solutions. result Generalization error of overfitted NTK models approaches a small limiting value, even with infinite neurons and samples.
The paper investigates how activation functions impact the training of Neural ODEs, leading to global convergence.
problem Challenges in training Neural ODEs, particularly gradient computation accuracy and convergence analysis.
method Investigates the impact of activation functions on the training dynamics of Neural ODEs.
result Establishes global convergence of Neural ODEs under gradient descent in overparameterized regimes.
New method uses neural tangent kernel for efficient active learning.
problem Efficiently approximating deep learning's look-ahead selection criteria.
method Approximates retraining with neural tangent kernel for active learning.
result Approximation works asymptotically and enables sequential active learning.
New method uses trainable activations to make BNNs behave like GPs.
problem Making Bayesian Neural Networks (BNNs) behave like Gaussian Processes (GPs).
method Introduced trainable activations and periodic activations to map GP priors to BNNs. Used 2-Wasserstein distance for optimization.
result Method consistently outperforms existing approaches or matches heuristic methods.
The paper develops a multi-kernel method with sparsity constraint for regression.
problem Developing a robust regression method with sparsity constraints.
method Banach-space formulation, generalized total-variation regularization, multi-kernel expansion, adaptive kernel positions, ℓ1 penalty on coefficients. result The method achieves sparsity in the kernel coefficients, reducing the number of active kernels to the number of data points.
Graph neural networks (GNNs) are a class of neural networks that allow to efficiently perform inference on data that is associated to a graph structure, such as, e.g., citation networks or knowledge graphs. While several variants of GNNs have been proposed, they only consider simple nonlinear activation functions in th…
New neural architectures with multivariate nonlinearities are optimal in function space.
problem Optimality of neural architectures with multivariate nonlinearities.
method Construction of Banach spaces via k-plane transform and sparsity-promoting norm, proving representer theorem. result Neural architectures with multivariate nonlinearities are optimal in function space.
Procedure removes training data dependency from deep networks, improving generalization.
problem Removing dependency on training data in deep networks for better generalization.
method Deterministic and stochastic parts to ensure forgetting, leveraging activation and weight dynamics.
result New bound on information extraction from black-box networks, ensuring forgetting in activations.
A new ensemble of Gaussian processes improves active learning efficiency.
problem Efficiently labeling data in high-cost domains like medical imaging.
method Adaptive weighted ensemble of Gaussian processes (EGP) for active learning.
result EGP-based approaches outperform single GP-based active learning methods.
Study uses multi-kernel Hawkes models to analyze high-frequency price dynamics.
problem Understanding responsive speeds of market participants in high-frequency trading.
method Multi-kernel Hawkes models with conditional Hessian analysis for optimization.
result Existence of multi-kernels (UHF, VHF, HF) in high-frequency price dynamics.
Gated recurrent neural networks have achieved remarkable results in the analysis of sequential data. Inside these networks, gates are used to control the flow of information, allowing to model even very long-term dependencies in the data. In this paper, we investigate whether the original gate equation (a linear projec…
In this paper, we consider parameter recovery for non-overlapping convolutional neural networks (CNNs) with multiple kernels. We show that when the inputs follow Gaussian distribution and the sample size is sufficiently large, the squared loss of such CNNs is locally strongly convex in a basin of attraction…
A framework and benchmark for deep batch active learning in neural networks.
problem Efficiently acquiring labels for neural network regression.
method Framework of base kernels, transformations, and selection methods; use of sketched finite-width neural tangent kernels and clustering.
result Proposed method outperforms state-of-the-art on benchmark, scales to large data sets.
Graph Neural Tangent Kernels combine GNNs and GKs for better graph classification.
problem Limited expressive power of graph kernels and difficulties in training graph neural networks.
method Graph Neural Tangent Kernels (GNTKs) are infinitely wide multi-layer GNNs trained by gradient descent.
result GNTKs achieve strong performance on graph classification datasets.
This paper explores neural models to improve modeling of Hawkes process intensity functions.
problem Traditional Hawkes process intensity function's parametrized kernel function biases future event predictions.
method Uses neural models to model the kernel function of Hawkes process intensity function.
result Neural models can better capture future event characteristics using past events data.
New framework establishes positivity of DNTK for PINNs.
problem Establishing positivity of NTK for PINNs with multiple differential operators.
method Proposed Differential Neural Tangent Kernel (DNTK) for PINNs.
result Positivity of infinite width DNTK for various activation functions and differential operators.