Adma proposes a flexible loss function for neural networks.
problem Static loss functions limit neural network performance.
method Introduces a flexible loss function that adapts to ANN complexity and data distribution.
result Flexible loss function achieves state-of-the-art performance.
Natural graph networks are a new class of graph neural networks that are more flexible and scalable.
problem Traditional graph neural networks are limited by equivariance to node permutations.
method Introduced natural graph networks, which are more flexible and scalable than conventional graph neural networks.
result Natural graph networks are as scalable as conventional message passing graph neural networks but more flexible.
TM-VI uses flexible transformation models to approximate complex posteriors in Bayesian models.
problem Approximating complex posteriors in Bayesian models with limited flexibility.
method Transformation models for variational inference (TM-VI).
result TM-VI allows accurate approximation of complex posteriors in models with one parameter and works in a mean-field fashion for multi-parameter models.
DMAE uses neural networks to cluster data with flexible dissimilarity functions.
problem Clustering data with complex dissimilarity functions.
method Integrates a dissimilarity mixture model into deep learning architectures.
result DMAE achieves competitive clustering accuracy compared to other methods.
A new HP model balances interpretability and flexibility for EHR event sequences.
problem Balancing interpretability and flexibility in modeling diagnostic event sequences.
method Proposes a neural network-based HP with flexible impact kernel and transformer layers.
result Accurately recovers impact functions, competitive performance, and clinically meaningful interpretation.
PFNs4BO uses neural processes for flexible Bayesian Optimization.
problem Efficient surrogate modeling for Bayesian Optimization.
method In-context learning of PFNs to approximate posterior predictive distribution.
result PFNs outperform traditional GP, BNN in BO tasks.
Flexible nonstationary Gaussian process with neural network parameters.
problem Limited expressiveness of stationary Gaussian processes.
method Nonstationary kernels with neural network parameters trained jointly.
result Better accuracy and log-score compared to stationary and hierarchical models.
GNet uses Gaussian processes for scalable, flexible neural networks.
problem Large-scale predictive modeling with high computational and storage costs.
method GNet employs Gaussian processes with nonparametric activation functions and a fast algorithm for training and predictions.
result GNet achieves competitive performance across various test problems, including nonlinear function prediction and real-world data regression.
GNet uses Gaussian processes for scalable, flexible neural networks.
problem Large-scale predictive modeling with high computational and storage costs.
method GNet employs Gaussian processes with nonparametric activation functions and a fast algorithm for efficient training and predictions.
result GNet achieves competitive performance across various test problems, including nonlinear function prediction and real-world data regression.
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.
mFI-PSO generates effective adversarial images for DNNs.
problem Vulnerability of DNNs to small perturbations in images.
method Uses mFI for pixel selection and PSO for objective functions.
result mFI-PSO effectively designs flexible adversarial images.
The study compares different models for predicting factor premiums and finds neural networks perform better but have unstable weights.
problem Predicting and timing the CMA factor premium using machine learning models.
method Compared regression models (OLS, Ridge, Random Forest, Neural Network) and tested factor timing strategies.
result Neural networks outperform linear models in explaining factor premium variance, but weights are unstable.
Graph neural networks are explained through energy gradient flow and framelet decomposition.
problem Understanding and improving graph neural networks.
method Viewing framelet-based models as gradient flows of energy, proposing a generalized energy via framelet decomposition.
result The proposed model leads to more flexible dynamics, enhancing graph neural networks.
A new model uses neural networks for consistent discrete choice analysis.
problem Difficulties in specifying utility functions in RUM models.
method Alternative-Specific and Shared weights Neural Network (ASS-NN) model.
result ASS-NN provides consistent outcomes without specifying utility form.
New tractable density models from squaring neural networks.
problem Flexible models for probability distributions in machine learning.
method Squared Neural Family (SNEFY) models formed by squaring neural network outputs and normalizing.
result SNEFYs are fully tractable with closed form normalizing constants in many cases.
Neural networks fit fewer samples than their parameters suggest in practice.
problem Understanding the practical limitations of neural network flexibility.
method Examination of neural network optimization, parameter efficiency, and loss surfaces.
result Neural networks can only fit training sets with significantly fewer samples than their parameters suggest.
Graph neural network executes value iteration for flexible environments.
problem Value iteration in flexible environments with direct supervision.
method Graph Neural Network (GNN) executing value iteration algorithm.
result GNN accurately models value iteration across diverse environments.
Motivated by the flexibility of biological neural networks whose connectivity structure changes significantly during their lifetime, we introduce the Unstructured Recursive Network (URN) and demonstrate that it can exhibit similar flexibility during training via gradient descent. We show empirically that many of the di…
Hi-fi priors enhance BNNs by learning flexible activations.
problem Challenging to impose function-space priors on BNNs.
method Optimization techniques to learn flexible activations.
result BNNs with flexible activations can achieve desired priors.
PDSketch enables flexible robot planning by learning from domain structures.
problem Building general robots with flexible planning.
method Exploiting locality and sparsity in environmental models, PDSketch defines high-level structures for trainable neural networks.
result PDSketch automatically generates planning heuristics without additional training.
Smooth neural TPPs using B-splines for better efficiency and accuracy.
problem Efficiently modeling sequences of events in continuous time with neural networks.
method Directly parametrize the CIF as a non-negative combination of B-spline basis functions, predicting coefficients with a neural network.
result Improved computational efficiency and predictive accuracy compared to existing methods.
Rational neural networks approximate functions more efficiently with less depth.
problem Choosing optimal nonlinear activation functions in neural networks.
method Rational activation functions with optimal bounds and efficiency proofs.
result Rational neural networks approximate smooth functions more efficiently than ReLU networks with exponentially smaller depth.
Flexible DNN for survival data, avoiding proportional hazards assumption.
problem Survival analysis with complex interactions and non-proportional hazards.
method Partially linear DNN model with a flexible nonparametric component.
result FLEXI-Haz achieves optimal convergence rates and asymptotic efficiency.
The recent success of raw audio waveform synthesis models like WaveNet motivates a new approach for music synthesis, in which the entire process --- creating audio samples from a score and instrument information --- is modeled using generative neural networks. This paper describes a neural music synthesis model with fl…
Automatically learns flexible symmetry constraints in neural networks using gradients.
problem Fixed hard constraints on neural network functions that cannot be adapted.
method Improves parameterisations of soft equivariance and optimizes marginal likelihood using differentiable Laplace approximations.
result Achieves equivalent or improved performance on image classification tasks compared to baselines with hard-coded symmetry.
A theoretical performance analysis of the graph neural network (GNN) is presented. For classification tasks, the neural network approach has the advantage in terms of flexibility that it can be employed in a data-driven manner, whereas Bayesian inference requires the assumption of a specific model. A fundamental questi…
ICP models flexible DAG structures using Bayesian nonparametrics.
problem Learning the structure of complex neural networks.
method Bayesian nonparametric prior on DAGs and orders controlled by a latent Beta Process.
result ICP supports every possible DAG structure.
Graph convolutional networks adapt the architecture of convolutional neural networks to learn rich representations of data supported on arbitrary graphs by replacing the convolution operations of convolutional neural networks with graph-dependent linear operations. However, these graph-dependent linear operations are d…
Neural network model improves loss reserving accuracy and distribution flexibility.
problem Accurate estimation of claim variability alongside central estimates.
method Mixture Density Neural Network (MDN) with rolling-origin approach.
result MDN consistently outperforms classical models for central estimates and quantiles.
Flexible framework for deep distributional regression models.
problem Learning conditional distributions from semi-structured data.
method Combines additive regression models with deep networks using TensorFlow.
result State-of-the-art predictive performance with interpretability.
Improves neural network estimates using IFs without needing more data.
problem Bias and lack of flexibility in neural network models.
method MultiNet and MultiStep methods using Influence Functions.
result Improves model robustness and facilitates statistical inference without additional data.
DRN improves actuarial distributional forecasting with interpretable neural networks.
problem Challenges in modeling loss distributional properties with classic methods.
method Combines GLMs with a modified DDR method to flexibly refine baseline distribution.
result DRN improves predictive performance while maintaining interpretability.
Flexible copula model using implicit generative neural networks.
problem Limited flexibility of parametric copulas and curse of dimensionality in non-parametric methods.
method Implicit generative neural networks to model high-dimensional copula distributions with unspecified marginals.
result Demonstrated flexibility and performance on various datasets.
Joslim optimizes both width and weight configurations for slimmable neural networks, improving model efficiency.
problem Optimizing both width and weight configurations for slimmable neural networks to improve efficiency.
method Proposes a general framework for joint optimization of width configurations and weights, and introduces Joslim algorithm.
result Improves model efficiency by up to 1.7% in top-1 accuracy on the ImageNet dataset.
The recent success of Deep Neural Networks (DNNs) has drastically improved the state of the art for many application domains. While achieving high accuracy performance, deploying state-of-the-art DNNs is a challenge since they typically require billions of expensive arithmetic computations. In addition, DNNs are typica…
Graph convolutional deep kernel machine learns representations for graph tasks.
problem Limited representation learning in infinite-width neural networks.
method Developed a graph convolutional deep kernel machine as an infinite-width limit.
result Representation learning improves performance for heterophilous node classification tasks.
SPQR package uses neural networks for flexible quantile regression.
problem Flexible modeling of non-linear relationships in quantile regression.
method Monotonic splines and neural networks for density estimation; model-agnostic covariate effects.
result Allows for non-linear and quantile-specific effects.
Extended LSTMs improve volatility prediction by 20%.
problem Predicting asset price volatility with long memory.
method Extended LSTMs with multiple flexible timescales.
result Extended LSTMs outperform rough volatility predictions by 20%.
DeepHazard uses neural networks to predict time-varying survival risks.
problem Traditional survival models assume proportional hazards and do not account for time-varying covariate information.
method DeepHazard is a neural network approach that models time-varying hazards without proportional hazards assumption.
result DeepHazard outperforms existing methods in predicting survival time, as shown by C-index metrics on real datasets.
EBPs model exchangeable data with flexible distributions.
problem Current energy-based models restrict set cardinality and limited distribution forms.
method Introduced Energy-Based Processes (EBPs) that extend energy models to exchangeable data with neural network parameterizations.
result EBPs can express more flexible distributions over sets without cardinality restrictions.
APINNs improve physics-informed neural networks through flexible domain decomposition.
problem Improving physics-informed neural networks (PINNs) for solving partial differential equations (PDEs).
method Introduces a trainable gate network for soft domain decomposition, allowing flexible parameter sharing and improved generalization.
result APINNs significantly improve PINNs and XPINNs, demonstrating better performance on various types of PDEs.
Study models weather index insurance pricing by insurers and farmers, finding flexible pricing kernels boost profits.
problem Monopoly pricing of weather index insurance with risk and flexibility considerations.
method Bowley-type sequential game with insurer and farmer, using neural networks for farmer's payoff.
result Flexible pricing kernels increase insurer profits closer to indemnity insurance levels.
Neural networks have proven to be extremely powerful tools for modern artificial intelligence applications, but computational and storage complexity remain limiting factors. This paper presents two compatible contributions towards reducing the time, energy, computational, and storage complexities associated with multil…
A scalable framework uses Langevin sampling to approximate neural network models of evolving processes.
problem Uncertainty quantification in neural network models of dynamic systems.
method Flexible data model based on NODE, joint learning of data model and posterior parameters, Langevin sampling.
result Demonstrated performance on chemical reaction and material physics data, compared favorably to variational inference.
Deep recurrent neural networks perform well on sequence data and are the model of choice. However, it is a daunting task to decide the structure of the networks, i.e. the number of layers, especially considering different computational needs of a sequence. We propose a layer flexible recurrent neural network with adapt…
Neural network estimates network models efficiently.
problem Estimating flexible ERGMs is challenging due to intractable normalizing constants.
method Trains a neural network on parameter-simulation pairs to invert and estimate parameters quickly and in parallel.
result The method performs well in practice and accommodates extra network statistics.
Although various linear log-distance path loss models have been developed, advanced models are requiring to more accurately and flexibly represent the path loss for complex environments such as the urban area. This letter proposes an artificial neural network (ANN) based multi-dimensional regression framework for path …
Neural network learns its size and structure during training.
problem Adapting neural network architecture to specific datasets.
method Flexible setup allowing neural network to learn size and topology during training.
result Trained networks achieve virtually identical performance and have learned optimal structure.