A novel continual prediction model outperforms traditional one-time models in predicting AKI.
problem Optimally predicting AKI before it develops during a hospital stay.
method A novel continual prediction model that predicts AKI every time a patient's AKI-relevant variable changes in the EHR.
result The continual prediction model outperformed traditional one-time models, achieving a higher AUC of 0.724 compared to 0.653.
Hybrid quantum neural networks predict continuous variables.
problem Predicting continuous variables using quantum computing.
method Quantum classical hybrid neural networks for continuous variable prediction.
result Quantum neural networks outperform classical methods in continuous variable prediction.
New methods for inferring, predicting, and estimating continuous-time, discrete-event processes.
problem Inferring, predicting, and estimating entropy rate of continuous-time, discrete-event processes.
method Bayesian structural inference extended with neural networks.
result Methods are competitive for prediction and entropy-rate estimation with state-of-the-art.
This paper describes recent development and test implementation of a continuous time recurrent neural network that has been configured to predict rates of change in securities. It presents outcomes in the context of popular technical analysis indicators and highlights the potential impact of continuous predictive capab…
Combines gradient boosting with collective inference for better continuous value prediction.
problem Improving predictive performance on relational data with interdependent instances.
method Proposes a boosting algorithm that learns a collective inference model to predict continuous target variables.
result The proposed algorithm outperforms alternative boosting methods on a real network dataset.
New measure assesses predictive dependence between continuous variables, capturing non-functional relationships.
problem Quantifying the joint dependence between continuous random variables.
method Introduces a novel, fully non-parametric measure bounded [0,1] that assesses predictive accuracy loss.
result The measure captures a wide range of relationships, including non-functional ones, and is interpretable.
Proposes a method for generating prediction intervals in dose-response models using conformal prediction.
problem Uncertainty quantification in continuous treatments for personalized healthcare decisions.
method Causal dose-response problem framed as covariate shift, using weighted conformal prediction with propensity estimation and kernel functions.
result Demonstrates the significance of covariate shift assumptions for robust prediction intervals.
New method predicts continuous actions using sequence models.
problem High-dimensional continuous control problems.
method Sequence-to-sequence models for discretized action spaces.
result Achieves state-of-the-art performance in continuous control tasks.
A method for predicting survival using neural networks for both continuous and discrete time.
problem Survival prediction for both continuous and discrete time data.
method Proposes a scheme for discretizing continuous-time data and two interpolation schemes for continuous-time survival estimates.
result The hazard rate parametrization of neural networks yields better performance than the parametrization of the probability mass function.
Policy Prediction Network improves continuous control problems with model-free and model-based learning.
problem Improving sample complexity and performance in continuous control problems.
method Integrates model-free and model-based reinforcement learning, introduces implicit model-based learning for continuous action space.
result First to introduce implicit model-based learning to Policy Gradient algorithms for continuous action space.
A new video prediction model treats videos as continuous processes, reducing sampling steps and improving efficiency.
problem Efficiency and temporal coherence in video prediction models.
method Treats videos as a continuous multi-dimensional process, reducing sampling steps.
result Reduction of 75% sampling steps, state-of-the-art performance on benchmark datasets.
New approach to continual learning prioritizes adaptation over retention.
problem Catastrophic forgetting in lifelong learning models.
method Formalized CL as an online optimization problem, introduced Transfer Efficiency, and derived a Critical Task Duration.
result Retention can hinder real-time adaptation in non-stationary environments.
Paper studies continuous prediction with experts' advice using differential equations.
problem Continuous prediction with experts' advice in online learning.
method Continuous-time stochastic calculus and differential equations.
result Improved guarantees for quantile regret with continuous-time algorithm.
The paper tackles fast rates in structured prediction problems.
problem Structured prediction problems with discrete outputs.
method Introducing continuous surrogate problems and leveraging their convergence rates for discrete problems.
result Super fast rates, including exponential rates, for excess risk in structured prediction problems.
Paper predicts daytime hypoglycemia using CGM data and CART.
problem Accurately predicting daytime hypoglycemia to prevent dangerous situations.
method Classification and Regression Tree (CART) applied to CGM data.
result Model detects almost 80% of hypoglycemic events 15 min in advance.
Neural Jump ODE improves continuous-time prediction and filtering of irregularly sampled time series.
problem Theoretical guarantees for continuous-time prediction and filtering of irregularly observed time series.
method Introducing Neural Jump ODE (NJ-ODE) that models conditional expectation between observations with neural ODEs and jumps.
result Theoretical guarantees for the L2-optimal prediction are provided, showing convergence of model output to optimal prediction. A method predicts driving intentions of human-driven vehicles for safer autonomous driving.
problem Predicting timely driving intentions of human-driven vehicles for autonomous vehicles in mixed traffic.
method A Hidden Markov Model (HMM) approach using continuous mobility features.
result HMMs trained with continuous mobility features improve prediction accuracy.
A method for continual learning using world models in reinforcement learning.
problem Catastrophic forgetting in lifelong learning with neural networks.
method Interleaving internally generated episodes of past experiences (pseudo-rehearsal) with external environment's observations.
result Consistent reduction in temporal prediction loss compared to non-interleaved learning.
Extends structured prediction to continuous manifold valued regression.
problem Continuous manifold valued regression problems.
method Geometric optimization for manifold valued regression.
result Statistical consistency of the proposed approach.
We study Lipschitz models in reinforcement learning to bound prediction and value-function errors.
problem Bounding errors in reinforcement learning models with Lipschitz continuity constraints.
method We provide bounds on multi-step prediction error and value-function estimate using the Wasserstein metric for Lipschitz models.
result Lipschitz models lead to bounded errors in prediction and value-function estimates.
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.
Temporal-difference (TD) networks are a class of predictive state representations that use well-established TD methods to learn models of partially observable dynamical systems. Previous research with TD networks has dealt only with dynamical systems with finite sets of observations and actions. We present an algorithm…
POSL predicts dynamic convection volumes in hemodiafiltration patients.
problem Continuous, personalised predictions in personalised medicine.
method Adapted POSL to dynamically predict convection volumes using combinations of parametric regressions and machine learning.
result POSL outperformed candidate learners in predicting convection volumes with lower errors and better calibration.
End-to-end network predicts and aligns continuous emotion labels.
problem Inconsistent alignment of continuous emotion labels with speech signals.
method Convolutional neural network with a multi-delay sinc layer.
result State-of-the-art results in predicting and aligning continuous emotion labels.
A neuro-inspired architecture learns without supervision using clustering and predictive coding.
problem Achieving continual learning without supervision.
method Neuro-inspired architecture based on online clustering and hierarchical predictive coding.
result The architecture achieves continual learning without supervision.
RIPE predicts and explains continuous/discrete data with sparse rule sets.
problem Predicting and explaining continuous/discrete data.
method RIPE infers a model from a sample, extracting a sparse set of hyperrectangles (rules) to partition the feature space.
result RIPE efficiently predicts and explains data, superior to other algorithms.
Study finds RNNs predict STBG better than ARIMA, useful for diabetes patients.
problem Improving short-term blood glucose prediction for diabetes management.
method Investigated Recurrent Neural Networks (RNNs) and compared them to ARIMA for STBG prediction.
result Population-based RNN model outperforms ARIMA across various prediction horizons.
Develops conformalized prediction intervals for bounded continuous outcomes.
problem Predicting continuous outcomes within bounded ranges, especially when models are misspecified.
method Conformal prediction intervals based on transformation regression models, accounting for heteroscedasticity and asymmetry.
result Valid finite-sample coverage confirmed in simulations and real data applications.
Proposes first method for continuously indexed domain adaptation.
problem Challenges of transferring knowledge between continuously indexed domains.
method Combines adversarial adaptation with a novel discriminator.
result Outperforms state-of-the-art methods on synthetic and real-world datasets.
PARMESAN learns from memory without parameters for fast, efficient continual learning.
problem Inflexibility in deep learning methods for continual learning.
method Transductive reasoning and memory search for parameter-free learning.
result 3-4 orders of magnitude faster than baselines, comparable performance.
Continuous-depth Evoformer reduces protein folding prediction time and resource usage.
problem Efficient protein structure prediction with reduced computational costs.
method Continuous-depth formulation of Evoformer using Neural Ordinary Differential Equations (Neural ODEs).
result The continuous-time Evoformer achieves constant memory cost and improved efficiency.
Enhances SBM with continuous attributes for better network analysis.
problem Community detection in networks with multiple continuous attributes.
method Augmented stochastic block model with multivariate Gaussian parameters.
result Satisfactory performance in link prediction and collaborative filtering tasks.
We quantify causal bias in continuous treatment settings.
problem Identifying and quantifying causal bias in continuous treatment scenarios.
method Developed a novel characterization of causal bias in structural causal models, proving conditions for zero bias and efficient estimation.
result Causal bias can be estimated efficiently under certain structural equation restrictions, allowing for causal regularization of predictive models.
Meta-descent improves online prediction in non-stationary settings.
problem Non-stationary online prediction problems.
method Meta-gradient descent to adapt step-size parameters.
result Meta-descent methods outperform other approaches in non-stationary prediction.
ScoreGrad predicts multivariate time series with energy-based models, achieving state-of-the-art results.
problem Predicting multivariate time series with generative models while considering noise and distribution.
method ScoreGrad uses continuous energy-based generative models with a feature extraction and score matching module.
result ScoreGrad achieves state-of-the-art results on six real-world datasets.
Model predicts event sequences using neural networks.
problem Predicting future events based on past patterns.
method Neural Hawkes Process with LSTM for evolving event intensities.
result Generative model achieves competitive performance.
Study efficient rebalancing strategies for portfolio tracking error.
problem Optimizing portfolio rebalancing under high-frequency asset price models.
method Discrete-time rebalancing strategies derived from continuous model.
result Asymptotically efficient sequence of simple strategies.
SupRB learns rules for continuous decision problems from examples.
problem Learning from continuous choices and explaining decisions to operators.
method SupRB is a supervised rule-based learning system for multi-dimensional continuous problems.
result SupRB provides human-understandable rules for optimal choices and quality predictions.
Improved neural network predicts spectral functions more accurately than traditional methods.
problem Reconstructing real-time spectral functions from imaginary-time Green's functions is ill-posed and challenging.
method Feature Learning Network (FL-net) for enhanced prediction accuracy.
result FL-net achieves at least 20% improvement over traditional methods like MEM.
Paper optimizes combining expert predictions using CRPS loss.
problem Optimizing combining expert predictions in online learning.
method Combines probabilistic forecasts using CRPS loss function in the prediction with expert advice framework.
result Time-independent upper bound for the regret of the Vovk's aggregating algorithm using CRPS as a loss function is obtained.
DeepMDP simplifies complex observations into continuous latent states.
problem Learning from high-dimensional observations in reinforcement learning.
method Trains a DeepMDP model that predicts rewards and next latent states.
result Optimization of DeepMDP objectives ensures quality of latent space and environment model.
A new emulator connects observables directly from data.
problem Constructing fast and accurate surrogate models for robust predictions.
method Introduces Multiparameter Eigenvalue Problem (MEP) emulator trained with Eigenvector Continuation (EC) and Parametric Matrix Model (PMM) data.
result The MEP emulator can make predictions directly from observables to observables.
This paper tackles delayed feedback in continuous training for CTR prediction, improving model performance by 3%.
problem Delayed feedback in CTR prediction leads to inferior performance and user experience.
method Comparing 5 loss functions and models in offline and online settings.
result Proposed methods outperform previous state-of-the-art by 3% relative cross entropy (RCE).
New method optimizes fairness in predictive models for continuous sensitive attributes.
problem Enforcing full statistical independence on continuous sensitive attributes is too restrictive.
method Functional bilevel optimization (FBO) and ITD algorithms.
result Achieves lowest or near-lowest fairness-accuracy regret on synthetic and real datasets.
Efficient algorithms compute conformal prediction sets for regression problems.
problem Providing strong coverage guarantees for predictions without distributional assumptions.
method Approximate homotopy continuation for convex regularized empirical risk minimization.
result Efficient algorithms to compute conformal prediction sets for regression problems.
Improved Gaussian Process model for predicting trajectories without independence assumption errors.
problem Incorrect independence assumption in previous work on Gaussian Process uncertainty propagation.
method Proposed a novel piecewise linear approximation to correct the independence assumption in continuous models.
result Corrected the independence assumption in Gaussian Process models for predicting trajectories.
Combines CP with stability bounds for efficient continuous prediction.
problem Infeasibility of CP sets for continuous targets.
method Combining CP with stability bounds for a single model fit.
result Efficient continuous prediction with guaranteed coverage.
A new method for interpreting AI models using Shapley value for functional data.
problem Interpreting AI models, especially those based on functional data.
method Proposes an interpretability method based on the Shapley value for continuous games.
result Demonstrates the effectiveness of the method through experiments with simulated and real data.