Empirical study shows removing neural parameter symmetries impacts model performance.
problem Understanding the impact of neural parameter symmetries on model performance.
method Developed two methods to reduce parameter space symmetries in neural networks.
result Removing parameter symmetries can lead to faster and more effective Bayesian neural network training.
A hybrid neural network improves robustness in estimating vehicle parameters from noisy data.
problem Estimating parameters of a mechanical vehicle model from noisy acceleration data.
method Introduced a convolutional neural network with two objective functions: naive and hybrid.
result The hybrid objective function outperforms the naive one in robustness on noisy input data.
The paper studies how regularization parameters affect sparsity in deep neural networks.
problem Reducing the complexity of deep neural networks by promoting sparsity.
method Derives ℓ1-norm sparsity-promoting models, characterizes sparsity levels, and develops algorithms for selecting optimal regularization parameters. result Developed algorithms to select regularization parameters for desired sparsity levels in neural networks.
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.
NPAS trains neural networks with a fixed parameter budget, improving performance and compactness.
problem Training neural networks requires memory, and existing methods struggle with arbitrary parameter budgets.
method NPAS learns to share parameters automatically, covering low and high budgets.
result NPAS and SSNs improve network performance and compactness across various tasks.
Deep neural networks with specific parameter sets can approximate smooth functions efficiently.
problem Approximating smooth functions with deep neural networks.
method Deep neural networks with ReLU activation and specific parameter sets {0,±21,±1,2} are used to approximate Cβ-smooth functions. result The constructed networks can approximate Cβ-smooth functions with parameters {0,±21,±1,2} efficiently, achieving the same convergence rate as sparse networks with parameters in [−1,1]. PENN neural network estimates parameter distributions for econ models.
problem Lack of interpretability in deep neural networks for econ applications.
method Generative neural network architecture for Bayesian inference.
result PENN provides interpretable parameter estimates and visualizations.
Single neural network predicts ImageNet model parameters for faster training.
problem Training diverse ImageNet models requires significant resources and time.
method Trained a neural network to predict ImageNet model parameters and used them for initialization.
result Models initialized with predicted parameters converge faster and achieve competitive performance.
New method uses sparse deep neural networks for high-dimensional regression with improved parameter estimation.
problem Improving parameter estimation in high-dimensional sparse regression models.
method Proposes nonparametric estimation of partial derivatives in sparse deep neural networks.
result Established convergence rate of nonparametric estimation of partial derivatives as O(n−1/4). APD method decomposes neural network parameters into simple, faithful components.
problem Understanding the internal mechanisms learned by neural networks.
method Attribution-based Parameter Decomposition (APD) method.
result Demonstrated effectiveness in recovering features, separating computations, and identifying representations.
Deep neural networks solve parameter estimation for FitzHugh-Nagumo ODEs.
problem Estimating parameters of a nonlinear dynamical system from noisy time series data.
method Dense and convolutional neural networks for inverse problem solving.
result Deep neural networks accurately estimate FitzHugh-Nagumo model parameters from noisy data.
Deep learning predicts neural network parameters efficiently.
problem Optimizing neural network parameters remains inefficient.
method Used graph neural networks to predict parameters of unseen networks.
result Achieved surprisingly good performance on unseen networks.
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 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…
The study calibrates neural networks' parameters through optimal contraction in prediction problems.
problem Ensuring the existence and uniqueness of optimal parameters in neural networks.
method Transforming RNNs into contractions and solving matrix equations involving Sylvester equations.
result Optimal parameters exist, are unique, and can be found through an algorithm with desired precision.
Deep neural networks estimate long memory parameters efficiently.
problem Estimating long memory parameters in stochastic processes.
method Scale-invariant 1D Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM) models trained with synthetic data.
result Neural models outperform conventional methods in precision, speed, consistency, and robustness.
Paper optimizes neural network initialization using SMT solvers.
problem Improving neural network performance through better initialization.
method Reduces initialization to SMT problem solving.
result Proposed method achieves better performance than random initialization.
New neural network approach for optimizing latent variable models.
problem Stability issues in marginalizing Gaussian Bayesian networks.
method Developed a new graphical structure and a neural network algorithm.
result Established a duality between parameter optimization and neural network training.
Neural networks cannot approximate certain functions in Sobolev spaces, leading to unbounded parameter growth.
problem Non-closedness of sets of neural networks in Sobolev spaces.
method Construction of sequences of neural networks whose realizations converge to functions not realizable by neural networks.
result Sets of realized neural networks are not closed in order-(m−1) Sobolev spaces Wm−1,p for p∈[1,∞]. Hybrid approach combines VI and HMC for efficient Bayesian inference in neural networks.
problem Computational demands and inaccuracies in Bayesian inference for neural networks.
method Combines VI and HMC, reducing parameter space and accelerating inference.
result Significantly reduces inference time for large neural networks, improving uncertainty quantification.
Study on measuring vulnerability of neural network parameters via corruption.
problem Understanding the robustness and generalization of deep neural networks.
method Proposes an indicator to measure parameter robustness via parameter corruption and provides a gradient-based estimation.
result Demonstrates the effectiveness of the proposed indicator and training method in improving parameter robustness and accuracy.
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.
Symmetry of neural network densities can be determined from correlation functions.
problem Determining symmetries of neural network densities without knowing the density itself.
method Symmetry-via-duality approach using invariance properties of correlation functions.
result Symmetries of neural network densities can be determined via dual computations of correlation functions.
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.
A neural network with a single hidden layer can't represent certain multivariable functions.
problem Representing certain multivariable functions with a neural network having only one hidden layer.
method Developed a continuum version of a one-hidden-layer neural network with ReLU activation, and proved constraints on its parameters and second derivative.
result Existence of a smooth binary function that cannot be precisely represented by any such neural network.
The paper proves consistency of neural networks with regularization.
problem Overfitting in neural networks with large scale data.
method Theoretical framework of neural networks with regularization, sieves method, and minimal neural networks theory.
result The estimated neural network converges to the true underlying function as sample size increases.
HMRNN combines HMMs and neural networks for Alzheimer's disease forecasting.
problem Improving disease progression modeling with hidden states not fully known.
method Developed HMRNN combining HMMs and recurrent neural networks.
result HMRNN improves disease forecasting and offers novel clinical interpretation.
Bayesian Neural Networks improve precision cosmology from simulations.
problem Extracting precise cosmological parameters from complex simulations.
method Using Bayesian Neural Networks on The Quijote simulations.
result Demonstrates BNNs' ability to estimate associated uncertainties and complex output distributions.
Study uses neural networks for fast Hawkes model parameter estimation in finance.
problem Estimating parameters of Hawkes models from high-frequency financial data.
method Recurrent neural networks for parameter estimation.
result Significantly faster computational performance compared to traditional methods.
Embeds sparsity in deep neural networks, allowing exact zero parameters.
problem Learning sparse structures in deep networks.
method Embeds sparsity into neural network structure, allowing exact zero parameters during training.
result Can learn both structured and unstructured sparsity.
KM method reduces ConvNet parameters to 9% higher accuracy with minimal additional memory.
problem Expensive memory usage for training ConvNets on embedded devices.
method Kernel Modulation (KM) method that adapts all network parameters for each task.
result KM delivers up to 9% higher accuracy than other parameter-efficient methods.
Unified method for deriving ridgelet transforms for various neural network architectures.
problem Deriving closed-form expressions for ridgelet transforms in modern neural network architectures.
method Unified Fourier slice method to derive ridgelet transforms for diverse neural network types.
result Systematic method to derive ridgelet transforms for various neural network architectures.
Bayesian neural networks improve likelihood-free inference efficiency.
problem Efficient parameter inference from simulation models with uncertainty.
method Bayesian neural networks for summary statistics, adaptive sampling.
result More robust and efficient posterior estimation.
New method encodes function preferences into neural nets for better generalization.
problem Challenges in encoding explicit function preferences in neural network training.
method Function-space empirical Bayes (FSEB) regularization.
result FSEB leads to near-perfect semantic shift detection and improved generalization.
Markov chain Monte Carlo (MCMC) methods have not been broadly adopted in Bayesian neural networks (BNNs). This paper initially reviews the main challenges in sampling from the parameter posterior of a neural network via MCMC. Such challenges culminate to lack of convergence to the parameter posterior. Nevertheless, thi…
New method uses neural networks to estimate parameters without needing detector simulations.
problem Estimating parameters in high-energy physics with detector effects.
method Two-level fitting approach: SRGN (Simulation-level fit based on Reweighting Generator-level events with Neural networks).
result Demonstrated using simulated datasets, SRGN can estimate parameters without detector effects.
Conditions for uniquely identifying parameters of deep ReLU networks.
problem Characterizing networks whose parameters can be uniquely identified.
method Conditions on deep fully-connected feedforward ReLU neural networks.
result Parameters of the network are uniquely identified under certain conditions.
A new method to prune neural networks with iterative randomization improves efficiency.
problem Efficiency in pruning randomly initialized neural networks.
method Iteratively randomizing weight values to reduce parameter requirements.
result The method achieves remarkable performance with fewer parameters.
Wavelets help compress neural networks efficiently.
problem Efficiently compressing linear layers in neural networks.
method Learnable wavelet transforms to compress RNNs.
result Wavelet compressed RNNs have fewer parameters and perform competitively.
In this paper we propose a Bayesian method for estimating architectural parameters of neural networks, namely layer size and network depth. We do this by learning concrete distributions over these parameters. Our results show that regular networks with a learnt structure can generalise better on small datasets, while f…
We propose a simple and easy to implement neural network compression algorithm that achieves results competitive with more complicated state-of-the-art methods. The key idea is to modify the original optimization problem by adding K independent Gaussian priors (corresponding to the k-means objective) over the network p…
Paper benchmarks quantum neural networks against classical ones for binary classification tasks.
problem Comparing quantum neural networks with classical ones for binary classification.
method Evaluated with two toy examples, focusing on model complexity and training data size.
result EQNN and QNN outperform ENN and DNN for smaller parameter sets and training data samples.
Not all neural network architectures are created equal, some perform much better than others for certain tasks. But how important are the weight parameters of a neural network compared to its architecture? In this work, we question to what extent neural network architectures alone, without learning any weight parameter…
Optimized neural network approximates high-dimensional functions with minimal parameters.
problem Achieving optimal approximation of high-dimensional continuous functions with minimal parameters.
method Developed a neural network with a specific activation function and architecture to achieve super approximation property.
result A composed network with at most 10889d + 10887 nonzero parameters achieves super approximation property, suggesting optimality in parameter growth.
Renormalized pruning improves neural network accuracy.
problem Over-parameterized neural networks waste many parameters.
method Propose renormalizing sparse neural networks.
result Renormalized pruning converges to zero error.
Study shows AD for neural nets with machine-representable numbers can be incorrect.
problem Correctness of AD for neural nets with machine-representable numbers.
method Analyzed two sets of parameters: incorrect and non-differentiable. Proved bounds and conditions for AD correctness.
result AD can be incorrect for machine-representable numbers, but provides a Clarke subderivative on non-differentiable set.
Proposes a new method for continual learning in neural networks.
problem Challenges in applying sequential Bayesian inference to neural networks.
method Sequential function-space variational inference.
result Neural networks trained with the proposed method achieve better predictive accuracy.
In this work, we leverage advances in sparse coding techniques to reduce the number of trainable parameters in a fully connected neural network. While most of the works in literature impose ℓ1 regularization, DropOut or DropConnect techniques to induce sparsity, our scheme considers feature importance as a criter…