metabeta uses neural networks to speed up Bayesian mixed-effects regression.
problem Bayesian mixed-effects regression is computationally expensive.
method metabeta is a neural network model that pre-trains to estimate posterior distributions.
result metabeta achieves comparable performance to MCMC at a fraction of the time.
MC-GMENN improves neural networks for clustered data using Monte Carlo methods.
problem Improving neural network performance on clustered data with correlations.
method MC-GMENN employs Monte Carlo methods to train generalized mixed effects neural networks.
result MC-GMENN outperforms existing models in generalization and quantifying inter-cluster variance.
Study compares neural and statistical models for Parkinson's disease progression from voice data.
problem Difficult statistical analysis of longitudinal voice biomarkers due to subject correlation, small cohorts, and varied disease trajectories.
method Evaluated Neural Mixed Effects (NME), Generalized Neural Network Mixed Models (GNMMs), and semi-parametric Generalized Additive Mixed Models (GAMMs).
result GAMMs achieve stronger predictive performance and retain interpretable smooth effects and subject-level structure.
Neural models improve GLMMs for complex data.
problem Nonlinear relationships in grouped data.
method Replaced linear function with neural networks.
result Improved performance on synthetic and real-world data.
Proposes integrating random effects into deep neural networks for better predictive performance.
problem Correlated data in real-life applications are not handled well by traditional deep neural networks.
method Uses mixed models with random effects to handle correlations in deep neural networks, minimizing Gaussian negative log-likelihood with SGD.
result Improves predictive performance over natural competitors in various correlation scenarios.
The paper analyzes oversmoothing in GNNs and quantifies the effects of mixing and denoising.
problem Oversmoothing in Graph Neural Networks (GNNs).
method Non-asymptotic analysis of graph convolutions and effects of mixing and denoising.
result The number of layers required for oversmoothing to occur is O(logN/log(logN)) for dense graphs. This paper compares methods for handling mixed-attribute data in GFMM neural networks.
problem Handling datasets with mixed features in GFMM neural networks.
method Three main methods: encoding, combining with other classifiers, and specific learning algorithms.
result Encoding methods and combining with decision trees improve GFMM models' performance.
NoLimits.jl: Flexible and Composable Nonlinear Mixed-Effects Modeling in Julia
problem Flexible and composable nonlinear mixed-effects modeling
method Macro-based modeling language and unified interface
result Substantially expand the range of nonlinear mixed-effects models
Proposes a new model for context-dependent decision-making.
problem Constant preference parameters in decision models are too rigid.
method Introduces Context-aware Bayesian mixed multinomial logit model using neural networks.
result Models context-dependent intra-respondent heterogeneity effectively.
We present a general-purpose method to train Markov chain Monte Carlo kernels, parameterized by deep neural networks, that converge and mix quickly to their target distribution. Our method generalizes Hamiltonian Monte Carlo and is trained to maximize expected squared jumped distance, a proxy for mixing speed. We demon…
ARMED models improve deep learning interpretability and generalize better on clustered data.
problem Clustered data leads to spurious associations and poor model fitting.
method Adversarial regularization and mixed effects subnetworks.
result ARMED models outperform conventional methods in accuracy and generalization.
Novel GLMMNet model tackles high-cardinality categorical features in actuarial applications.
problem Inadequate encoding methods for high-cardinality categorical features in actuarial data.
method Generalised Linear Mixed Model Neural Network (GLMMNet) integrating a generalised linear mixed model in a deep learning framework.
result GLMMNet often outperforms or performs comparably with entity embedded neural networks, providing transparency.
This paper examines properties of feedforward graphs to improve neural network performance.
problem The choice of computational graph can significantly impact neural network performance.
method The paper introduces two measures: fidelity and mixing time, and evaluates popular graphs using these measures.
result Popular graphs are evaluated based on fidelity and mixing time, revealing their performance implications.
A new SSL method improves medical image classification using global latent mixing.
problem Costly annotation of large-scale medical image data sets.
method Linear mixing of labeled and unlabeled data in both input and latent space.
result Improved performance in semi-supervised classification of thoracic disease and skin lesion.
A scalable Bayesian inference method for mixed-effects models in systems biology.
problem Scalable Bayesian inference for complex hierarchical mixed-effects models in systems biology.
method Constructing amortized approximations of likelihood and posterior distributions, refined for each individual dataset.
result Our method is both fast and competitive in statistical accuracy compared to exact pseudomarginal Bayesian inference.
New algorithms optimize neural networks with ReLU activations using sampling.
problem Optimizing trained neural networks with ReLU activations.
method Iterative algorithm and enhanced algorithm using sampling and neighborhood search.
result The methods reduce the initial MIP problem into smaller LP or MIP problems.
Deep-SITAR uses autoencoders to predict growth patterns.
problem Predicting individual growth trajectories from population data.
method Deep learning framework integrating autoencoders and B-spline models.
result Deep-SITAR predicts individual growth without full model re-estimation.
The paper uses neural networks to estimate treatment effects even with many confounders.
problem Estimating treatment effects with a growing number of confounders.
method General optimization framework using neural networks to approximate nuisance functions.
result Neural networks can handle a diverging number of confounders and alleviate the curse of dimensionality.
This study compares machine learning methods for high-cardinality categorical variables.
problem Machine learning struggles with high-cardinality categorical variables.
method Empirical comparison of tree-boosting, deep neural networks, and linear mixed effects models.
result Tree-boosting with random effects outperforms deep neural networks with random effects.
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-mixing data. result Proves neural nets can generalize well on non-iid data.
Improved machine learning for reservoir optimization problems.
problem Optimizing control in high-dimensional storage problems.
method Modified dynamic programming algorithm with neural networks for Bellman values and conditional cuts.
result Neural networks outperform classical feedforward networks in estimating Bellman values.
Mixed integer programming identifies critical neurons in neural networks.
problem Identifying neurons critical for network performance and generalization.
method Developed a mixed integer program (MIP) to assign importance scores to neurons, guiding pruning decisions.
result The method identifies multiple 'lucky' sub-networks resulting in optimized architectures that generalize across datasets.
Models for sequential data such as the recurrent neural network (RNN) often implicitly model a sequence as having a fixed time interval between observations and do not account for group-level effects when multiple sequences are observed. We propose a model for grouped sequential data based on the RNN that accounts for …
SelectMix improves deep learning robustness against noisy labels.
problem Deep neural networks memorize noisy labels, degrading performance.
method Confidence-guided targeted sample mixing with soft labels.
result SelectMix consistently outperforms baseline methods on noisy label datasets.
Wide Bayesian neural networks have a simpler weight posterior, leading to faster MCMC sampling.
problem Sampling from the posterior of wide Bayesian neural networks is challenging.
method Introducing repriorisation, a data-dependent reparameterisation that simplifies the posterior distribution.
result The repriorisation map accelerates MCMC sampling, achieving up to 50x higher effective sample size.
The paper develops mixed-integer formulations for neural networks using partitioning.
problem Optimizing trained ReLU neural networks with balanced model size and tightness.
method Partitioning node inputs into groups, forming the convex hull via disjunctive programming.
result The proposed formulations outperform existing ones, especially with fewer partitions.
Adding linear layers to ReLU networks favors functions with low mixed variation.
problem Understanding function space bias in overparameterized neural networks.
method Examined a family of networks with varying depths and same capacity but different representation costs, focusing on the effect of adding linear layers to the input side.
result Adding linear layers to shallow ReLU networks results in a bias towards functions with low mixed variation, which can be well approximated by single- or multi-index models.
Efficient Bitwidth Search optimizes neural network quantization for better performance.
problem Finding optimal bitwidth for weights and activations of each layer efficiently.
method EBS algorithm reusing meta weights and binary decomposition for efficient mixed precision convolution.
result Mixed precision QNN outperforms uniform bitwidth and other techniques on CIFAR10 and ImageNet.
Probabilistic deep learning uses neural networks and models to handle uncertainty.
problem Handling uncertainty in deep learning models.
method Two approaches: probabilistic neural networks and deep probabilistic models.
result TensorFlow Probability library supports both approaches.
Paper proposes deep neural networks for nonparametric regression from dependent data.
problem Nonparametric regression from strongly mixing observations.
method Minimum error entropy principle applied to deep neural networks.
result Deep neural networks achieve minimax optimal convergence rates for Gaussian errors.
Study improves maize yield prediction using BNs with mixed-effects models.
problem Limited causal inference in agronomic data models.
method Integrates random effects into Bayesian networks, leveraging hierarchical data structure.
result Significantly reduces maize yield prediction error from 28% to 17%.
We extend neural networks with fractional and mixed activation functions for better function approximation.
problem Limitations in approximating higher-order smooth functions in complex spaces.
method Incorporating fractional exponents in activation functions and defining new density functions.
result Improved accuracy and broader applicability of neural network approximation theory.
Convolutional neural network (CNN) and its variants have led to many state-of-art results in various fields. However, a clear theoretical understanding about them is still lacking. Recently, multi-layer convolutional sparse coding (ML-CSC) has been proposed and proved to equal such simply stacked networks (plain networ…
Paper tackles NAS problem by modeling it as a sparse supernet.
problem Neural Architecture Search (NAS) problem, particularly Mixed-Path Search.
method Model NAS as a sparse supernet with sparsity constraints. Use hierarchical accelerated proximal gradient algorithm for optimization.
result Proposed method finds compact, general, and powerful neural architectures.
Improved anomaly detection in time series data using kervolutional neural networks.
problem Anomaly detection in time series data.
method Mixed kervolutional and convolutional layers in a temporal auto-encoder.
result The mixed model detects anomalies more sensitively in time series data.
Develops HDNNs for mixed geoscience data inputs.
problem Lack of multisource, multi-scale information in deep learning studies.
method Hybrid architecture combining feature and target learning.
result HDNNs achieve higher accuracy and better generalization in reservoir prediction.
Develops a deep learning framework for various data types.
problem Handling nonparametric regression and classification across different data types.
method Introduces a general framework with two estimators: NPDNN and SPDNN, based on data satisfying generalized Bernstein-type inequalities.
result Both NPDNN and SPDNN estimators are minimax optimal in many classical settings.
In healthcare, making the best possible predictions with complex models (e.g., neural networks, ensembles/stacks of different models) can impact patient welfare. In order to make these complex models explainable, we present DeepSHAP for mixed model types, a framework for layer wise propagation of Shapley values that bu…
Existing popular methods for semi-supervised learning with Graph Neural Networks (such as the Graph Convolutional Network) provably cannot learn a general class of neighborhood mixing relationships. To address this weakness, we propose a new model, MixHop, that can learn these relationships, including difference operat…
MaGNet integrates local and global graph information for interpretable results.
problem Lack of interpretability and inability to learn varying-order representations in GNNs.
method Model-agnostic Graph Neural Network (MaGNet) framework integrating estimation and interpretation models.
result MaGNet effectively integrates information of various orders and provides meaningful, interpretable results.
Graph neural networks improve solving linear optimization problems.
problem Improving the efficiency of solving linear optimization problems.
method Using graph neural networks to simulate standard interior-point methods for linear optimization problems.
result Graph neural networks can solve linear optimization problems close to optimality, often outperforming conventional solvers.
Theoretical analysis of deep neural networks for time series data.
problem Theoretical development for deep neural networks on temporally dependent observations is lacking.
method Established non-asymptotic bounds for prediction error of deep neural networks under mixing-type assumptions.
result Deep neural networks can model non-linear time series data with additional logarithmic factors due to dependence.
A new method quantifies feature-map discriminativeness for efficient pruning of deep neural networks.
problem Efficiently pruning deep neural networks to reduce computation while maintaining accuracy.
method Presented a novel mathematical formulation (Discriminant Information, DI) to quantify feature-map discriminativeness, enabling efficient pruning and intra-layer mixed precision quantization.
result Our pruned ResNet50 achieves 44% FLOPs reduction without any Top-1 accuracy loss.
Novel approach constructs differential causal networks from EEG data.
problem Difficulty in modeling interactions of thousands of neurons in group comparisons.
method Hierarchical differential dynamic causal nets based on Chen-Fliess expansions.
result Evidence of network functional disruptions in epileptic brains.
Method improves regression models using unlabeled data.
problem Improving predictive performance of regression models with limited labeled data.
method Mixed semi-supervised generalized-linear-regression with different mixing mechanisms.
result Integrating unlabeled data consistently improves predictive performance.
We present a neurosymbolic framework for the lifelong learning of algorithmic tasks that mix perception and procedural reasoning. Reusing high-level concepts across domains and learning complex procedures are key challenges in lifelong learning. We show that a program synthesis approach that combines gradient descent w…
New research limits how deep neural networks can be for certain functions.
problem Understanding the depth required for neural networks to represent specific functions.
method Mixed-integer optimization, polyhedral theory, tropical geometry.
result Neural networks with more than one layer are necessary to represent certain functions.
Deep ReLU networks can approximate and learn smooth functions efficiently.
problem Efficiently approximating and learning smooth functions using deep ReLU neural networks.
method Extending recent results to anisotropic and mixed smooth function classes, establishing approximation rates.
result Deep ReLU networks achieve minimax optimal rates up to logarithmic factors for various smooth function classes.