Reframed GES uses a neural conditional dependence measure for consistent causal structure learning.
problem Identifying causal structure in nonparametric settings.
method Reframed GES algorithm with a neural conditional dependence measure.
result Optimality and consistency of the reframed GES algorithm under standard assumptions.
A neural network approach for efficient conditional SHAP calculations.
problem Efficiently calculating conditional SHAP values for various models.
method Surrogate neural network approach for conditional SHAP.
result Efficiently calculates conditional SHAP values for neural networks and other regression models.
New neural process models produce correlated predictions for better estimation tasks.
problem Need for models that can handle correlated predictions for tasks like weather forecasting.
method Developed new Neural Process models that can produce correlated predictions and support exact maximum likelihood training.
result Improved predictive performance on various experiments with synthetic and real data.
Parallel recordings of neural spike counts have revealed the existence of context-dependent noise correlations in neural populations. Theories of population coding have also shown that such correlations can impact the information encoded by neural populations about external stimuli. Although studies have shown that the…
Estimates conditional distribution function using neural networks for censored and uncensored data.
problem Estimating conditional distribution function for censored and uncensored data.
method Neural network algorithm based on Cox regression with time-dependent covariates, using full likelihood with unconstrained optimization.
result Proposed method yields more accurate estimates than existing methods when model assumptions are violated.
New algorithm ensures global convergence in deep neural networks beyond NTK regime.
problem Existing global convergence guarantees do not apply to practical deep networks.
method Proposes an algorithm with global convergence guarantees under the expressivity condition.
result Algorithm ensures global convergence in practical settings beyond NTK regime.
Sparse-penalized deep neural networks improve performance in weakly dependent processes.
problem Nonparametric regression and classification under weak dependence.
method Sparse-penalized deep neural networks with oracle inequalities and convergence rates established.
result The proposed estimators outperform non-penalized ones in simulations.
Neural Networks are being integrated into safety critical systems, e.g., perception systems for autonomous vehicles, which require trained networks to perform safely in novel scenarios. It is challenging to verify neural networks because their decisions are not explainable, they cannot be exhaustively tested, and finit…
ARCNPs improve CNPs by autoregressively modeling dependencies.
problem CNPs struggle with modeling dependencies in predictions.
method Autoregressive deployment of factorized Gaussian CNPs.
result ARCNPs significantly outperform non-AR CNPs in various tasks.
The paper bounds the excess risk of deep neural networks for weakly dependent processes.
problem Learning with weakly dependent data using deep neural networks.
method Approximation of smooth functions by deep neural networks and a bound on excess risk.
result The excess risk bound for deep learning under weak dependence is close to O ( n − 1 / 2 ) \mathcal{O}(n^{-1/2}) O ( n − 1/2 ) for sufficiently smooth functions. Improved Gaussian Neural Processes for efficient multi-dimensional predictions.
problem Inability to model dependencies in outputs limits CNPs and NPs applicability.
method Proposes a new approach to model output dependencies using latent variables for maximum likelihood training, scalable to 2D and 3D data.
result Proposed models show good performance in synthetic experiments.
Deep neural nets learn from weakly dependent processes.
problem Learning from ψ ψ ψ -weakly dependent processes. method Deep neural networks for ψ ψ ψ -weakly dependent processes. result Established consistency of empirical risk minimization algorithm and generalization bound.
Researchers analyze neural process architectures and their representational capacities.
problem Understanding what functions can be represented by different neural process architectures.
method Analyzing four types of neural process architectures: CNPs, ANPs, TNPs, and their latent variants.
result Prove these architectures form a strict hierarchy and characterize their representational capabilities.
Neural network method estimates covariate-dependent graphical models with statistical guarantees.
problem Estimating graph structure from covariate-dependent data.
method Neural network approach that allows flexible functional dependency on covariates.
result Theoretical PAC guarantees for the method's performance.
Unified GP model optimizes hyperparameters with conditional dependence.
problem Efficient tuning of hyperparameters in neural networks.
method Unified Bayesian optimization framework based on a new Gaussian process (GP) model.
result Higher prediction accuracy and better optimization efficiency observed.
New bounds on neural network test loss derived from conditional information measures.
problem Estimating test loss of neural networks trained on limited data.
method Framework based on conditional information density between hypothesis and training set.
result Tail bounds on test loss decay as 1/n, improving over previous 1/sqrt{n} bounds.
Bayesian neural networks with dependent weights converge to Gaussian mixtures.
problem Limitations of standard Gaussian priors in neural networks.
method Posterior analysis with Gaussian likelihood for networks with dependent weights.
result Posterior distribution identified in the wide-width limit, ensuring invertibility of random covariance matrix.
NGMs create mirrored features to assess neural network feature importance.
problem Lack of feature relevance information in DNNs limits their applicability.
method Structured perturbation and kernel-based conditional dependence measure for feature importance evaluation.
result Controls feature selection error rate and maintains high selection power with correlated features.
Extends PD-NJ-ODE to noisy observations and dependent observation times.
problem Predicting continuous-time stochastic processes with irregular and noisy observations.
method Extends PD-NJ-ODE to handle conditional independence and noisy observations.
result Theoretical guarantees and empirical examples for handling noisy observations and dependent observation times.
A new framework learns system design using neural features in function space.
problem Learning system design with neural feature extractors.
method Introduces feature geometry in function space, nesting technique for optimal feature approximation.
result Optimal features found from data samples using off-the-shelf architectures and optimizers.
Convolutional Neural Processes improve data efficiency in neural processes.
problem Improving data efficiency in neural processes for small datasets.
method Convolutional Neural Processes (ConvNPs) improve data efficiency by leveraging translation equivariance and convolutional neural networks.
result ConvNPs enhance the performance of neural processes in small-data problems.
IGNN captures long-range graph dependencies using fixed-point equations.
problem Limited GNN ability to capture long-range graph dependencies.
method Fixed-point equilibrium equations involving implicitly defined state vectors, leveraging Perron-Frobenius theory and projected gradient descent.
result IGNN consistently captures long-range dependencies and outperforms state-of-the-art GNNs.
New theory for local parameterization of deep ReLU networks.
problem Determining local parameters of deep ReLU neural networks.
method Introducing local lifting operators and charts of a manifold, deriving necessary and sufficient conditions for local identifiability.
result Sharp and testable conditions for local identifiability of deep ReLU networks.
This paper studies semi-supervised object classification in relational data, which is a fundamental problem in relational data modeling. The problem has been extensively studied in the literature of both statistical relational learning (e.g. relational Markov networks) and graph neural networks (e.g. graph convolutiona…
NeurISE uses neural nets to learn graphical models efficiently.
problem Efficiently learning graphical models with high-order terms.
method NeurISE, a neural net-based algorithm that approximates interaction screening objective function.
result NeurISE can find parsimonious representations without prior information.
Optimizer choice affects neural scaling laws, changing the exponent α \alpha α .
problem The exponent α \alpha α in neural scaling laws L ( N ) ∝ N − α L(N) \propto N^{-\alpha} L ( N ) ∝ N − α varies with the optimizer used. method Controlled random-feature regression experiments with five optimizer variants and six spectral conditions.
result Preconditioned optimizers yield steeper scaling (larger α \alpha α ), with the α \alpha α -shift increasing across most of the tested spectral range. Study uses deep neural networks for inference in partially linear models with dependent data.
problem Inference in partially linear models with dependent data.
method First stage deep neural network (DNN) estimation followed by n \sqrt{n} n -consistent and asymptotically normal estimator. result The DNN-estimated finite dimensional parameter achieves n \sqrt{n} n -consistency and asymptotic normality. Develops CLDS models to model neural activity with nonlinear dynamics.
problem Complex, nonlinear dynamics in neural population activity.
method Conditionally Linear Dynamical System (CLDS) models using Gaussian Process (GP) priors.
result CLDS models can perform well even in data-limited conditions.
Paper introduces non-adversarial training for Neural SDEs using signature kernel scores.
problem Stability and mode collapse issues in adversarial training of Neural SDEs.
method Uses signature kernel scores as objective function for non-adversarial training.
result Non-adversarial training leads to better performance and more stable models.
Causal Posterior Estimation improves Bayesian inference in complex models.
problem Bayesian inference in models with intractable likelihood functions.
method Normalizing flow-based approximation with conditional dependence structure.
result Improved accuracy in posterior inference through direct incorporation of model structure.
The study characterizes the conditioning of the Gauss-Newton matrix in neural networks.
problem Understanding the conditioning of the Gauss-Newton matrix in neural networks.
method Theoretical analysis of the GN matrix in deep linear and ReLU networks, extending to residual connections and convolutional layers.
result Established tight bounds on the condition number of the GN matrix in neural networks.
Study on deep neural networks for reward modeling with pairwise comparison data.
problem Reward modeling with deep neural networks in non-parametric settings.
method Established a non-asymptotic regret bound for deep reward estimators, introduced a margin-type condition.
result Improved regret bound for deep reward estimators, highlighting the importance of clear human beliefs.
Study feature representations induced by dependence between variables.
problem Learning feature representations from dependent random variables.
method Characterized sufficient and necessary conditions for dependence-induced representations, and provided a family of loss functions.
result Features learned from the family of loss functions can be expressed as the composition of a loss-dependent function and the maximal correlation function.
Paper models spatio-temporal extremes using conditional variational autoencoders.
problem Modeling co-occurrence of extreme weather events under changing climate conditions.
method Conditional Variational Autoencoder (cXVAE) with CNN integration.
result Accurately emulates spatial fields and recovers extremal dependence with low computational cost.
Study on functions computed by deep-layered machines finds same distribution in neural networks and Boolean circuits.
problem Understanding the space of functions computed by deep-layered machines.
method Investigation of Boolean functions on random-layered machines, including neural networks and Boolean circuits.
result The space of functions computed at large depth limit is characterized and the macroscopic entropy of Boolean functions is either monotonically increasing or decreasing with depth.
The paper proposes a machine learning approach for state-dependent asset allocation.
problem Market conditions cause performance deviations from long-term averages.
method Analyzes historical market states and asset returns to directly relate state variables to portfolio weights.
result The proposed approach generates a more efficient portfolio compared to traditional methods.
Training-free model learns SDE dynamics without training, accelerating parameter studies.
problem High computational cost of simulating parameter-dependent SDEs.
method Training-free conditional diffusion model with joint kernel-weighted Monte Carlo estimator.
result Accurate approximation of conditional distributions across varying parameter values.
Neural Lévy model improves risk and density forecasting for financial returns.
problem Financial returns exhibit heavy tails, volatility clustering, and jumps.
method Proposes a neural Lévy jump-diffusion framework that learns conditional drift, diffusion, jump intensity, and size distribution.
result Demonstrates improved calibration, sharper tail control, and risk reduction.
Bird sounds possess distinctive spectral structure which may exhibit small shifts in spectrum depending on the bird species and environmental conditions. In this paper, we propose using convolutional recurrent neural networks on the task of automated bird audio detection in real-life environments. In the proposed metho…
CeCNN predicts SE and AL from UWF images, improving myopia screening.
problem Predicting axial length and spherical equivalence from UWF fundus images.
method Copula-enhanced Convolutional Neural Network (CeCNN) for multiresponse regression.
result CeCNN improves prediction of SE and AL compared to baseline CNNs.
Optimal model averaging for conditional generative models improves performance across various data types.
problem Multiple plausible generators for conditional distributions can vary in performance.
method Sample-based maximum mean discrepancy, static model averaging, and mixture-of-experts model averaging.
result MoEMA improves over competing baselines across various data types.
Paper develops methods for inference on time series data using neural networks and sieves.
problem Inference on time series data with nonparametric conditional moment restrictions.
method GN-QLR based inference using general nonlinear sieves and multilayer neural networks.
result Optimally weighted GN-QLR statistic is asymptotically Chi-square distributed.
Neural-PDE learns PDEs from data using LSTM, outperforming traditional methods.
problem Solving time-dependent PDEs numerically is challenging.
method Bidirectional LSTM encoder to learn governing rules from data.
result Neural-PDE efficiently predicts PDE dynamics with minimal parameters.
Multi-Entity Dependence Learning (MEDL) explores conditional correlations among multiple entities. The availability of rich contextual information requires a nimble learning scheme that tightly integrates with deep neural networks and has the ability to capture correlation structures among exponentially many outcomes. …
NeuroMemFPP uses LSTM to estimate FPP parameters with high accuracy.
problem Estimating parameters of fractional Poisson process with memory and long-range dependence.
method Recurrent Neural Network (RNN), specifically Long Short-Term Memory (LSTM), for parameter estimation.
result The LSTM-based approach reduces MSE by about 55.3% compared to traditional MOM method.
Neural interaction discoveries can be real or artifacts of model flexibility.
problem Identifying real neural interactions from data.
method Using a multiplicative-gating extension of neural additive vector autoregression.
result Effective rank of the joint lag-block covariance predicts interaction recoverability.
Spatiotemporal forecasting has various applications in neuroscience, climate and transportation domain. Traffic forecasting is one canonical example of such learning task. The task is challenging due to (1) complex spatial dependency on road networks, (2) non-linear temporal dynamics with changing road conditions and (…
This work combines recurrent models with diffusion for probabilistic time series forecasting.
problem Scalability and capturing high-dimensional distributions and cross-feature dependencies in time series forecasting.
method Combines recurrent neural networks' efficiency with diffusion models' probabilistic modeling, using stochastic interpolants and conditional generation.
result Offers scalable probabilistic time series forecasting methods.