Paper improves multi-step traffic flow prediction performance.
problem Predicting multiple time-steps into the future based on finite history.
method Introduces a model for recursive prediction and a data augmentation method for multi-output setting.
result Improves multi-step traffic flow prediction in recursive and multi-output settings.
Novel prediction method using string invariants with evolutionary optimization.
problem Optimal prediction parameters for string invariants.
method Evolutionary algorithm for parameter optimization.
result Method performs well in single step prediction but needs improvement for multiple steps.
New model predicts chemical reactions without human input.
problem Automating retrosynthetic planning in chemistry.
method Combined Molecular Transformer and hyper-graph exploration.
result Improved accuracy in predicting reactants, reagents, solvents, and catalysts.
RNF learns distinct representations for Bayesian filtering steps, improving time series prediction accuracy and uncertainty.
problem Improving time series prediction accuracy and uncertainty using distinct representations for Bayesian filtering steps.
method Introduces Recurrent Neural Filter (RNF) architecture that learns distinct representations for each Bayesian filtering step.
result RNF improves accuracy of one-step-ahead forecasts and provides realistic uncertainty estimates.
A new multi-step model improves model-based reinforcement learning efficiency.
problem Expensive environmental interaction in reinforcement learning.
method Proposes a multi-step model for predicting action sequences with variable length.
result Multi-step model outperforms one-step model in preliminary tests.
Introduces HProbZ for probabilistic prediction with distinct sources of uncertainty.
problem Separating sources of uncertainty in neural network predictions.
method Hybrid Probabilistic Zonotope (HProbZ) combining binary, bounded, and stochastic generators.
result HProbZ represents and refines predictive uncertainty effectively compared to mixtures.
Model predicts stock price changes and forecasts using tokenized data.
problem Challenges in stock price forecasting and prediction due to dynamic data and statistical differences.
method Introduces PCIE model with tokenization to handle both forecasting and prediction.
result PCIE model outperforms state-of-the-art models in forecast and prediction tasks.
Improved chemical reaction prediction using augmented NLP models.
problem Predicting chemical reactions from text representations.
method Data augmentation and Transformer architecture for SMILES representation.
result Significantly improved accuracy in predicting chemical reactions.
Research develops a water quality prediction model using LSTM.
problem Global degradation of water resources and need for optimal water quality monitoring.
method Developed a multivariate water quality prediction model using LSTM and historical data.
result Multiple step LSTM model achieved RMSE of 0.227 mg/L.
Improved conformalized quantile regression for adaptive prediction intervals.
problem Lack of adaptiveness in the conformal step of conformalized quantile regression.
method Cluster explanatory variables by permutation importance and apply k conformal steps.
result Improved prediction intervals are more adaptive to heteroscedasticity.
TIDBD adapts TD step-sizes for better performance.
problem Finding optimal step-sizes for TD learning.
method Generalizes IDBD to TD learning, adapting step-sizes per feature.
result TIDBD outperforms other TD methods in various tasks.
Algorithm combines expert forecasts for long-term time series prediction.
problem Long-term time series prediction with expert advice.
method Develops algorithms to combine expert forecasts for long-term prediction, proving adversarial regret bounds.
result Obtains smoothing mechanism to protect against trend changes, noise, and outliers.
Diffusion-VAE tackles multi-step stock price prediction with stochastic noise.
problem Challenges in multi-step stock price prediction due to stochasticity and target price sequence.
method Combines hierarchical VAE and diffusion probabilistic techniques for seq2seq stock prediction.
result D-Va model outperforms state-of-the-art solutions in prediction accuracy and variance.
Paper improves multi-step chord prediction in jazz music.
problem Chord sequence prediction accuracy is poor in multi-step scenarios.
method Aggregated multi-scale encoder-decoder network architecture.
result Our model outperforms state-of-the-art methods in accuracy and perplexity.
Paper tackles catastrophic overfitting in single-step adversarial training.
problem Catastrophic overfitting leads to sudden drop in robust accuracy.
method Proposes a method to prevent overfitting by using all adversarial examples.
result Demonstrates prevention of catastrophic overfitting and improves robustness.
New method defends against both single-step and iterative adversarial examples.
problem Defending against adversarial examples, especially iterative ones, is computationally expensive.
method Single-Step Adversarial Training (SST) with modifications.
result Our method outperforms state-of-the-art methods in both accuracy and training time.
Hopfield networks improve reaction template prediction for few/zero-shot scenarios.
problem Predicting reaction templates for new molecules in CASP.
method Adapted Hopfield networks to associate reaction templates, molecules, and structural information.
result Significantly improved performance for templates with few or zero training examples.
Bayesian Quadrature speeds up integration by selecting batches of points instead of single points.
problem Efficiently parallelizing Bayesian Quadrature for integration over non-negative integrands.
method Developed methods to select batches of points at each step, based on recent batch Bayesian Optimization.
result Significantly reduces computation time, especially for expensive integrands.
Automatically infers high dynamic range illumination from a single indoor photo.
problem Predicting accurate indoor illumination from a single image.
method End-to-end deep neural network trained in three steps: lighting classifier, scene light localization, and fine-tuning for intensity prediction.
result Significantly outperforms previous methods in recovering high-quality HDR illumination.
Model predicts multi-modal sequences using N-curves.
problem Capturing multi-modal data in sequential data.
method Neural network model based on Mixture Density Networks with Bézier curves.
result Smooth multi-mode predictions without Monte Carlo simulation.
Itô maps provide a method for any-step SDE integration.
problem Stochastic dynamics
method Itô map formulation
result Empirical results on synthetic and image-generation benchmarks
This study proposes methods for multi-step-ahead stock price prediction using decomposition and neural networks.
problem Inaccurate one-step-ahead forecasting limits stock market decision-making.
method Two novel methods: DCT-MFRFNN and VMD-MFRFNN.
result VMD-MFRFNN outperforms other methods in multi-step-ahead stock price prediction.
Training of the neural autoregressive density estimator (NADE) can be viewed as doing one step of probabilistic inference on missing values in data. We propose a new model that extends this inference scheme to multiple steps, arguing that it is easier to learn to improve a reconstruction in k steps rather than to lea…
A new method reduces adversarial training time without overfitting.
problem Catastrophic overfitting in single-step adversarial training.
method FGSMPR: FGSM with PGD Regularization.
result Reduces the gap to multi-step adversarial training.
CW-EDMD improves prediction accuracy by learning local Koopman models for different state-space regions.
problem Inefficient global Koopman operator approximation for distinct local dynamics.
method Cluster-Weighted EDMD (CW-EDMD) learns a soft phase-space partition and per-cluster EDMD operators using EM objective.
result CW-EDMD significantly reduces prediction errors across various systems and configurations.
Paper explains DRL strategies for portfolio management using linear models.
problem Difficulty in understanding DRL-based trading strategies.
method Empirical approach using linear models and integrated gradients.
result DRL agents show stronger multi-step prediction power than machine learning methods.
Discrete Flow Maps bypass sequential prediction limits for parallel text generation.
problem Sequential autoregressive prediction limits large language model speed.
method Flow Maps compress generative trajectories into single-step mappings.
result Discrete Flow Maps surpass previous state-of-the-art results in discrete flow modeling.
Sparse hierarchical graph classification improves graph-based benchmarks.
problem Sparse hierarchical graph classification challenges.
method Combining recent advances in graph neural network design, differentiable graph coarsening, and sparse pooling.
result Competitive hierarchical graph classification results possible without sacrificing sparsity.
Unified framework for predicting data changes influenced by predictions.
problem Complex feedback loops in environments where predictions alter data distributions.
method Repeated Risk Minimization (RRM) and two-step plug-in estimator integrating RePPI and Importance Sampling.
result Achieves semiparametric efficiency bound and robustness under mild misspecification.
Optimizes random forest inference by defining step order to maximize accuracy.
problem Limited inference time in resource-constrained systems.
method Designs anytime random forest algorithm on step granularity, proposing optimal step order.
result Backward Squirrel Order performs nearly as well as the optimal step order.
Efficient regularization mitigates catastrophic overfitting in single-step adversarial training.
problem Catastrophic overfitting in single-step adversarial training.
method ELLE regularization term to enforce local linearity of the loss function.
result Our regularization term effectively mitigates catastrophic overfitting without the drawbacks of previous methods.
A new method reduces compounding errors in model-based reinforcement learning.
problem Compounding errors in long horizon predictions from model-based reinforcement learning.
method Maximum Entropy Model Rollouts (MEMR) with non-uniform sampling and prioritized experience replay.
result Significantly reduces computation requirements compared to other model-based methods.
Paper proposes a new landmark selection method for kernel ridge regression.
problem Efficient landmark selection for scalable kernel methods.
method Two-step approach: first computes importance scores, then clusters them into landmarks.
result Proposed method provides better accuracy and efficiency trade-offs.
A new approach to Kernel Ridge Regression using partitioning.
problem Efficiently estimating KRR for large datasets.
method Divide and conquer approach via partitioning of input space.
result Achieves optimal minimax rates and reduces approximation error.
Single-step samplers generate high-quality samples efficiently.
problem Sampling from unnormalized distributions is computationally expensive.
method Developed consistent diffusion samplers that generate samples in a single step.
result Single-step samplers produce high-fidelity samples with less than 1% of traditional samplers' evaluations.
Faster gaze prediction with less parameters.
problem Overparameterized networks for gaze prediction.
method Fisher pruning combined with knowledge distillation.
result 10x speedup for fixation prediction.
This research improves neural network uncertainty estimates and reliability.
problem Lack of inherent uncertainty estimates and variability in softmax scores.
method Ensemble-based Dirichlet modeling with method of moments estimator.
result Improved stability and predictive uncertainty estimates.
Stratify unifies and improves multi-step forecasting strategies.
problem Lack of unified frameworks for multi-step forecasting strategies.
method Proposes Stratify, a parameterized framework for multi-step forecasting.
result Novel strategies in Stratify outperform existing ones in over 84% of experiments.
LIFE framework improves model accuracy and interpretability.
problem Achieving high prediction accuracy and interpretability in neural networks.
method Three-step process: subset definition, feature creation, and linear model combination.
result LIFE consistently outperforms other models in prediction accuracy and interpretability.
MR estimator simplifies causal inference by combining models without hyperparameter tuning.
problem Difficulty in choosing optimal hyperparameters for neural network models in causal inference.
method Multiply Robust (MR) estimator that combines multiple first-step models.
result MR estimator is nr consistent and asymptotically normal under certain conditions. Proposes a method to balance tasks in multitask learning with a single gradient step update.
problem Balancing tasks in multitask learning to avoid imbalance.
method Gradient-based meta-learning to balance tasks at the gradient level, training shared and task-specific layers separately.
result Achieves state-of-the-art performance on various multitask computer vision problems.
Autoencoder learns graph representations for link prediction and node classification.
problem Link prediction and semi-supervised node classification on graphs.
method A novel autoencoder architecture for joint local graph structure and node feature learning.
result Significant improvement over related methods for graph representation learning.
Generalizes conformal prediction to multiple learnable parameters for efficient prediction sets.
problem Learning valid and efficient prediction sets with low-capacity function classes.
method Constrained empirical risk minimization (ERM) with gradient-based optimization of differentiable surrogate losses and Lagrangians.
result Achieves approximate valid population coverage and near-optimal efficiency within class.
New forward performance processes for predictable market updates.
problem Creating predictable forward performance processes for market information.
method Developed a binomial model with dynamic parameters and solved an inverse investment problem.
result Established conditions for the existence and uniqueness of solutions to the inverse problem.
Single gradient step finds adversarial examples in random neural networks.
problem Finding adversarial examples in neural networks with random architectures.
method Gradient descent approach applied to random undercomplete and overcomplete two-layers neural networks.
result A single gradient step is sufficient to find adversarial examples in random neural networks.
DCSVM efficiently classifies multi-class data using SVMs with smart partitioning.
problem Multi-class classification using SVMs with high computational cost.
method Divide and conquer approach with smart partitioning of data.
result Reduces the number of classes in each step, making final decisions in logarithmic or linear steps.
A new transformer model uses Monte Carlo methods for sequence prediction.
problem Predicting sequences from observations with uncertainty.
method Integrates Monte Carlo methods into a transformer architecture to model stochastic sequences.
result Proposes a generative model with predictive distributions.
A new autoencoder learns graph representations for link prediction and node classification.
problem Link prediction and node classification on graph data.
method Multi-task graph autoencoder architecture.
result Significant improvement over three baselines on five graph datasets.