New LTC RNNs can approximate any continuous system with fewer units.
problem Approximating continuous dynamical systems with neural networks.
method Introducing LTC RNNs with variable time-constant synaptic transmission.
result LTC RNNs can approximate any n-dimensional continuous dynamical system. New neural networks with variable time constants for better time-series prediction.
problem Improving neural network performance in time-series prediction.
method Constructing networks of linear dynamical systems modulated by nonlinear gates, using numerical differential equation solvers.
result Liquid Time-Constant Networks (LTCs) yield superior performance on time-series prediction tasks.
We study the computational capacity of a model neuron, the Tempotron, which classifies sequences of spikes by linear-threshold operations. We use statistical mechanics and extreme value theory to derive the capacity of the system in random classification tasks. In contrast to its static analog, the Perceptron, the Temp…
New findings on GRW space-times with constant scalar curvature.
problem Understanding GRW space-times in different subspaces.
method Analyzing orthogonal subspaces of Gray's decomposition.
result Generalized quasi-Einstein GRW space-times reduce to known types of space-times.
LIQSS method improves accuracy and efficiency for power system simulations.
problem Accurately modeling and simulating long-duration mission profiles of Naval power systems.
method Linear Implicit Quantized State System (LIQSS) method for stiff, nonlinear, differential algebraic equations.
result LIQSS1 method yields results within 1% accuracy of continuous methods and increases efficiency logarithmically with quantization size.
The apparent stochasticity of in-vivo neural circuits has long been hypothesized to represent a signature of ongoing stochastic inference in the brain. More recently, a theoretical framework for neural sampling has been proposed, which explains how sample-based inference can be performed by networks of spiking neurons.…
This paper examines the problem of locating outlier columns in a large, otherwise low-rank, matrix. We propose a simple two-step adaptive sensing and inference approach and establish theoretical guarantees for its performance; our results show that accurate outlier identification is achievable using very few linear sum…
This paper suggests a learning-theoretic perspective on how synaptic plasticity benefits global brain functioning. We introduce a model, the selectron, that (i) arises as the fast time constant limit of leaky integrate-and-fire neurons equipped with spiking timing dependent plasticity (STDP) and (ii) is amenable to the…
We introduce a technique that can automatically tune the parameters of a rule-based computer vision system comprised of thresholds, combinational logic, and time constants. This lets us retain the flexibility and perspicacity of a conventionally structured system while allowing us to perform approximate gradient descen…
We show that the standard stochastic gradient decent (SGD) algorithm is guaranteed to learn, in polynomial time, a function that is competitive with the best function in the conjugate kernel space of the network, as defined in Daniely, Frostig and Singer. The result holds for log-depth networks from a rich family of ar…
Study local foliations of surfaces with constant mean curvature and constant expansion in space-time.
problem Characterize surfaces with constant mean curvature and constant expansion in space-time.
method Use Lyapunov Schmidt reduction in an n+1 dimensional manifold to construct and prove the uniqueness of foliations.
result Construct and prove the uniqueness of local foliations of surfaces with constant mean curvature and constant expansion.
This paper presents a general theory that aims at explaining timescales observed empirically in technology transitions and predicting those of future transitions. This framework is used further to derive a theory for exploring the dynamics that underlie the complex phenomenon of irreversible and path dependent price or…
In this work we develop a tractable structural model with analytical default probabilities depending on a random default barrier and possibly random volatility ideally associated with a scenario based underlying firm debt. We show how to calibrate this model using a chosen number of reference Credit Default Swap (CDS) …
This paper uses Bayesian optimization to efficiently identify stochastic dynamical systems.
problem Efficiently identifying linear stochastic dynamical systems with unknown coefficients and noise variances.
method Adaptive Bayesian optimization with ensemble Gaussian processes (EGP) and Kalman filter recursion.
result BO-based estimator achieves RMSE below the Cramer-Rao bound, improving robustness and consistency.
Deep learning method improves myelin water fraction estimation.
problem Estimating myelin water fraction in the brain using magnetic resonance relaxometry.
method Combines input layer regularization with automated regularization hyperparameter tuning.
result Proposed method outperforms classical methods and multi-layer perceptrons on in vivo brain data.
New monitoring method detects ML risk models' performance changes in medical interventions.
problem Monitoring ML risk models in healthcare is complicated by confounding medical interventions.
method Developed a new score-based CUSUM monitoring procedure with dynamic control limits.
result Valid inference is possible if conditional exchangeability or time-constant selection bias hold.
Gradient descent learns a neuron in noisy data.
problem Learning a single neuron with adversarial label noise.
method Gradient descent on the L22-loss. result Efficient approximate learners for various distributions and activations.
Proposes a criterion for selecting relevant auxiliary variables in incomplete data analysis.
problem Selecting useful auxiliary variables for incomplete data analysis.
method Formulates model selection problem, proposes an information criterion based on Kullback-Leibler divergence.
result Proposed information criterion is an asymptotically unbiased estimator of Kullback-Leibler divergence.
VC-PCR improves prediction by clustering correlated variables.
problem Decreased prediction accuracy due to cluster structure in predictor variables.
method Supervised variable selection and clustering to integrate cluster information into a sparse modeling process.
result VC-PCR achieves better prediction, variable selection, and clustering performance.
Study on inequalities for multinomial variables.
problem Understanding concentration inequalities for multinomial variables.
method Investigation of Dirichlet and Multinomial random variables.
result Results on concentration inequalities for multinomial variables.
This research proposes a variable importance cloud to assess variable importance across multiple good models.
problem Current variable importance measures are tied to a single model, limiting understanding of variable importance across different models.
method Introduces a variable importance cloud that maps every variable to its importance for every good predictive model.
result Shows how variable importance can vary significantly across different good models.
In this paper, we propose multi-variable LSTM capable of accurate forecasting and variable importance interpretation for time series with exogenous variables. Current attention mechanism in recurrent neural networks mostly focuses on the temporal aspect of data and falls short of characterizing variable importance. To …
A neural network finds causal relationships among latent variables.
problem Learning causal structure among latent variables in high-dimensional data.
method Redundant Input Neural Network (RINN) with modified architecture and regularized objective function.
result The RINN method successfully recovers latent causal structure between input and output variables.
Proposes DVC for better variable selection in non-grid data.
problem Challenges of identifying important variables in non-grid data.
method Imposes chain structure on blocks of variables using step-wise greedy search.
result Outperforms other generic DNNs and classifiers.
Derives derivatives and geometric framework for functions with non-independent variables.
problem Characterizing functions with non-independent variables in probabilistic models.
method Derives actual and dependent partial derivatives, dependent Jacobian matrix, and tensor metric.
result Derives gradient, Hessian, and Taylor expansion for functions with non-independent variables.
A new distance for mixed-variable, hierarchical datasets with meta variables.
problem Heterogeneous datasets limit generalizability and performance in machine learning and optimization.
method Developed a modeling framework for mixed-variable and hierarchical domains with meta variables, and a novel distance function.
result The novel distance function allows comparison of heterogeneous datasets, improving model performance.
This paper enhances LSTM neural networks for multi-variable time series data, providing interpretable insights.
problem Accurate prediction of multi-variable time series data with interpretable insights.
method Variable-wise hidden states and a mixture attention mechanism to model the generative process of the target variable.
result Enhanced prediction performance by capturing the dynamics of different variables.
Extends effect variable concept to finite states for web search evaluation.
problem Finding effect of variant variables in changes of observable variables.
method Theoretical analysis and simultaneous distribution decomposition.
result States of extreme effect variable are minimally affected by variant and highly different in observable variable.
Unified Bayesian Optimisation for mixed variables improves performance.
problem Efficient optimisation of problems with both categorical and continuous variables.
method Derive value proposals from the Expected Improvement criterion to optimise both categorical and continuous variables under a single acquisition metric.
result Unified approach significantly outperforms existing methods across mixed-variable tasks.
RNN models perform similarly with or without extraneous variables.
problem Impact of extraneous variables on RNN performance in clinical tasks.
method Investigated the effect of extraneous input variables on RNN predictive performance using EMR and randomly drawn variables.
result Degradations in RNN's predictive performance with extraneous variables were negligible.
A method to assess variable importance in complex predictive models.
problem Assessing the importance of variables in complex predictive models.
method Assigning relevance measures to each variable by comparing predictions with a ghost variable and analyzing joint effects.
result The method provides insights into variable importance and joint effects not available with other methods.
In this paper, we propose an interpretable LSTM recurrent neural network, i.e., multi-variable LSTM for time series with exogenous variables. Currently, widely used attention mechanism in recurrent neural networks mostly focuses on the temporal aspect of data and falls short of characterizing variable importance. To th…
Random Forest variable importance is improved by class balancing techniques.
problem Class imbalance problem in machine learning.
method Proposed a variable selection algorithm using RF variable importance and its confidence interval.
result Our algorithm efficiently selects an optimal feature set, leading to improved prediction performance.
Variable selection for Gaussian process models is often done using automatic relevance determination, which uses the inverse length-scale parameter of each input variable as a proxy for variable relevance. This implicitly determined relevance has several drawbacks that prevent the selection of optimal input variables i…
Knoop enhances variable selection with over-parameterization and knockoffs.
problem Challenges of variable selection in high-dimensional datasets.
method Generates knockoff variables, integrates them into an over-parameterized model, and uses anomaly-based significance tests.
result Superior performance in variable selection compared to existing methods.
A serious problem in learning probabilistic models is the presence of hidden variables. These variables are not observed, yet interact with several of the observed variables. Detecting hidden variables poses two problems: determining the relations to other variables in the model and determining the number of states of …
New method for fitting graphical models with latent variables using regularized conditional likelihood.
problem Graphical modeling with latent variables and confounding dependencies.
method Regularized conditional likelihood for exponential family graphical models.
result Framework applicable to broader settings without knowing latent variables' distribution.
CIB compresses variables causally, preserving key causal interactions.
problem Constructing causal variable abstractions in complex systems.
method Causal Information Bottleneck (CIB) method, extending IB to include causal structures.
result CIB produces causally interpretable abstractions that accurately capture causal relations.
Discond-VAE separates continuous and discrete factors in data.
problem Separating shared and class-specific variations in real-world data.
method Introduces private and public latent variables to represent continuous and discrete factors, respectively.
result Discond-VAE successfully disentangles class-dependent continuous factors from discrete factors.
Extends inequality for Rademacher complexities using p-stable variables.
problem Improving Rademacher complexity bounds using p-stable variables. method Extends contraction inequality to p-stable variables for 1<p<2. result New bounds for Rademacher complexities with p-stable variables. A new method selects important variables for clustering from dependency networks.
problem Variable selection for clustering in high-cost data scenarios.
method Create dependency networks, rank variables by centrality, select top-n variables.
result Top-n variables improve clustering performance compared to existing methods.
The paper introduces methods to identify key variables discriminating between two datasets.
problem Identifying variables that distinguish between two datasets.
method Introduces a mathematical notion of discriminating variables and proposes two methods for their selection.
result Proposed methods improve upon existing techniques in two-sample variable selection.
This work presents entropic constraints from DAGs with hidden variables.
problem Characterizing causal relations in systems with hidden variables.
method Entropic inequality constraints derived from e-separation relations. result These constraints can learn about true causal models from observed data.
Proposes a two-stage method for selecting correlated predictors in high-dimensional data.
problem Selecting correlated predictors in high-dimensional data with unknown group structures.
method Two-stage approach: variable clustering followed by group selection.
result The two-stage method improves prediction accuracy and active predictor selection.
We propose a novel application of the Simultaneous Orthogonal Matching Pursuit (S-OMP) procedure for sparsistant variable selection in ultra-high dimensional multi-task regression problems. Screening of variables, as introduced in \cite{fan08sis}, is an efficient and highly scalable way to remove many irrelevant variab…
New method better identifies irrelevant variables for more accurate treatment effect estimation.
problem Handling irrelevant variables in treatment effect estimation with deep disentanglement.
method Deep embedding method to disentangle pre-treatment variables, explicitly identify and represent irrelevant variables, and orthogonalize them.
result Better identification and representation of irrelevant variables lead to more precise treatment effect prediction.
The paper proposes a method to stabilize predictions by identifying causal variables using a seed variable.
problem Stable prediction across unknown test data with potential spurious correlations.
method Conditional independence test based algorithm using a seed variable to separate causal from non-causal variables.
result The algorithm precisely separates causal and non-causal variables for stable prediction across test data.
Random forest hyperparameters affect variable selection in omics studies.
problem Impact of hyperparameters on variable selection in random forests.
method Two simulation studies using theoretical and empirical data.
result Hyperparameters influence variable selection more than the splitting strategy and sample fraction.