New methods for signal reconstruction using guiding sets and frame-less pathways.
problem Signal reconstruction in Hilbert spaces with specified properties.
method Axiomatic approach involving sample consistent and guiding sets, with reconstruction set defined as a shortest pathway.
result Existence and uniqueness of reconstruction set in Hilbert space, with derived stability and error bounds.
GUIDE-VAE generates user-guided data with improved realism and performance.
problem Generating data points for multi-user datasets while considering user information.
method Conditional generative model that integrates user embeddings and a pattern dictionary-based covariance composition.
result GUIDE-VAE outperforms conventional VAEs in multi-user settings, especially under data imbalance.
A new method for testing deep learning models using CGF.
problem Traditional testing methods fail to cover corner cases in DNNs.
method Monte Carlo Tree Search for coverage-guided search.
result Generated inputs result in higher coverage than previous methods.
GuideR learns rules guided by user preferences for classification, regression, and survival analysis.
problem Lack of user preferences in rule learning algorithms.
method Guided sequential covering approach.
result User preferences improve rule quality in classification, regression, and survival analysis.
Guided Evolutionary Strategies uses surrogate gradients to improve optimization.
problem Optimizing functions with unknown true gradients but available surrogate gradients.
method Combines random search with a search distribution elongated along surrogate gradient directions.
result Improves optimization performance over standard evolutionary strategies and first-order methods.
Loss-guided training accelerates node embedding methods on graphs.
problem Training efficiency in graph learning methods with implicit positive examples.
method Dynamic adjustment of training distribution based on loss values.
result Significant acceleration in training and computation over static methods.
A smaller, less-trained model guides image generation, improving quality without sacrificing variation.
problem Improving image quality and variation in diffusion models without compromising one for the other.
method Guiding a conditional model with a smaller, less-trained version of the same model.
result Significant improvements in ImageNet generation, setting record FIDs.
Optimization algorithms' regret bounds guide choice based on data and loss function.
problem Choosing the best optimization algorithm for a given dataset and loss function.
method Assumed convex and Lipschitz continuous loss function; compared traditional vs adaptive algorithms.
result Traditional algorithms' regret bounds are different from adaptive ones, providing a guide.
Researchers solved a problem about extreme mass distributions in quasi-copulas.
problem Solving the extreme mass distribution problem for quasi-copulas.
method Analytical approach using linear programming.
result Complete solution to the original problem, disproving a conjecture.
KG-WDRO optimizes transfer learning with external knowledge.
problem Over-pessimism in WDRO for small target samples.
method KG-WDRO incorporates multiple sources of external knowledge to construct smaller Wasserstein ambiguity sets.
result KG-WDRO improves transfer learning performance and adaptivity.
CGD improves diffusion models' out-of-distribution generalization.
problem Reliable sampling from high-value regions beyond training data.
method Context-guided diffusion (CGD) using unlabeled data and smoothness constraints.
result Substantial performance gains across various diffusion processes.
Bayesian-guided method selects optimal design from large candidate pool.
problem Optimizing complex structures with high-fidelity evaluations.
method Bayesian active learning with surrogate modeling.
result Optimal design identified with minimal oracle evaluations.
Enhances data programming with continuous labeling functions for better model performance.
problem Scarcity of labeled data hampers supervised learning models.
method Integrates continuous scoring functions and quality guides into a generative model to improve data programming reliability.
result Continuous labeling functions lead to improved recall and more stable model performance.
Holdout set improves risk score accuracy without biasing predictions.
problem Updating risk scores can lead to biased estimates when directly applied.
method Use a holdout set of non-intervention population to update risk scores.
result Optimal holdout size reduces adverse outcomes to optimal level.
PGNN combines physics models with neural nets for lake temperature prediction.
problem Lake temperature modeling with physical constraints.
method Physics-guided neural networks using hybrid modeling and physics-based loss functions.
result PGNN improves generalizability and scientific consistency in lake temperature predictions.
Guided Flows enhance sample quality in conditional image generation and text-to-speech.
problem Improving sample quality in conditional generative models.
method Integrating classifier-free guidance into Flow Matching (FM) models for Continuous Normalizing Flows (CNFs).
result Guided Flows significantly improve sample quality in conditional image generation and text-to-speech synthesis.
Guided adaptive shrinkage uses co-data to improve feature selection in genomic studies.
problem Feature selection challenges in high-dimensional genomics data, especially in clinical settings.
method Guided adaptive shrinkage methods that use co-data to adapt shrinkage parameters.
result Improves feature selection in genomic studies, demonstrated through comparisons and examples.
This paper tackles real-time Bayesian inverse problems using neural networks.
problem Real-time inference of posterior distributions from experimental data.
method Amortized variational inference with Gaussian and Flow guides.
result The approach provides posterior estimates in real-time at the cost of a forward pass.
A new decision tree algorithm handles missing values efficiently.
problem Data sets with missing values.
method Proposes a decision tree algorithm that allows user-guided data partitioning and handles missing values.
result The algorithm produces more accurate and interpretable results than common procedures without imputations.
GH-PID uses guided harmonic paths for efficient SOT with interpretable diagnostics.
problem Efficiently solving Stochastic Optimal Transport with hard terminal distributions and soft costs.
method Guided Harmonic Path-Integral Diffusion (GH-PID) framework with low-dimensional guidance.
result GH-PID generates geometry-aware, cost-reducing trajectories that match terminal distributions.
End-to-end autonomous driving framework using guided auxiliary supervision.
problem Learning to drive in highly stochastic urban settings.
method Multi-task Learning from Demonstration (MT-LfD) framework with end-to-end trainable network and supervised auxiliary tasks.
result Joint learning and supervised guidance facilitate faster and better driving performance.
MOPO-LSI offers a user guide for sustainable investments.
problem Sustainable investment optimization challenges.
method Open-source library for multi-objective portfolio optimization.
result User-friendly guide for MOPO-LSI version 1.0.
GSI improves efficiency of large language model inference.
problem Efficiently guiding test-time alignment in large language models.
method Combines soft best-of-n scaling with a reward model and speculative samples. result Achieves higher accuracy and reduced latency compared to standard methods.
This work improves RL for complex robotic tasks by guiding exploration with task-specific goal distributions.
problem Solving long-horizon, complex sequential tasks in robotics with sparse rewards.
method Extends hindsight relabelling to task-specific goal distributions using a small set of demonstrations.
result Significantly higher overall performance on complex robotic manipulation tasks.
Guided dropout improves neural network performance by selectively dropping nodes.
problem Overfitting in deep neural networks.
method Guided selection of nodes for dropout based on their strength.
result Guided dropout leads to better generalization compared to conventional dropout.
EMI uses predictive signals to guide exploration in sparse reward settings.
problem Challenges of reinforcement learning with sparse reward signals.
method Constructs embedding representations of states and actions for forward prediction in the representation space.
result Competitive results on challenging tasks with continuous control and discrete actions.
Paper tackles partial label learning with self-guided retraining.
problem Dealing with partially labeled examples where each instance has a set of candidate labels.
method Unified formulation with constraints for joint training and pseudo-labeling; maximum infinity norm regularization for automatic differentiation; convex-concave optimization problem; upper-bound surrogate objective function.
result Significantly outperforms state-of-the-art partial label learning approaches.
A new learning framework uses a teacher to guide learners through rounds of exposure to data.
problem Computational intractability of supervised learning.
method Curricular phases with a teacher guiding exposure to data.
result Simple learners can acquire complex concepts efficiently from examples.
Neural-guided symbolic regression uses asymptotic constraints to find unknown functions.
problem Finding unknown functions from data points with additional mathematical constraints.
method A neural network generates expressions with desired leading powers, and Monte Carlo Tree Search optimizes the expressions.
result The system effectively finds unknown functions outside the training set compared to existing methods.
Graph Neural Networks and Guided Local Search improve TSP solutions.
problem Finding optimal solutions to the Traveling Salesperson Problem quickly.
method Hybrid approach combining Graph Neural Networks and Guided Local Search.
result Significant reduction in optimality gap for TSP solutions.
Paper proposes an alternative to set losses for predicting unordered variables without imposing structure.
problem Learning unordered variables with unknown interrelations without imposing structure.
method Viewing set prediction as conditional density estimation and using deep energy-based models with gradient-guided sampling.
result Empirically demonstrates capability to learn multi-modal densities and produce different plausible predictions.
CROSSGRAD learns general classifiers from multi-domain data without adaptation.
problem Learning classifiers that generalize across different domains.
method Cross-gradient training using domain-guided perturbations and Bayesian sampling.
result CROSSGRAD achieves better generalization to unseen domains compared to existing methods.
Proposes TgNN-LD to improve neural network effectiveness and efficiency.
problem Limits in maintaining tradeoff between data and domain knowledge.
method Converts loss function to constrained form with PDEs, ECs, and EK as constraints, incorporating Lagrangian variables for equitable tradeoff.
result Improves prediction accuracy and conserves resources.
A new model learns demand patterns from data, reducing complexity and improving accuracy.
problem Forecasting short-term demand from spatiotemporal data with complex patterns.
method Temporal-Guided Network (TGNet) using graph networks and temporal-guided embedding.
result TGNet achieves competitive performance with fewer parameters compared to state-of-the-art models.
Expert-guided model improves seismic compliance monitoring.
problem Classifying seismic data with missingness and expert knowledge.
method Expert-guided class-conditional model with interpretable goodness-of-fit features.
result Interpretable classifier outperforms standard machine learning, especially with small training data.
GGFPS improves model performance by sampling molecules more efficiently.
problem Improving model performance and reducing data costs in chemistry problems.
method Gradient-Guided Furthest Point Sampling (GGFPS) that leverages molecular force norms.
result GGFPS leads to superior data efficiency and model robustness compared to other sampling methods.
Enhances out-of-domain calibration of neural networks.
problem Improving calibration performance of deep neural networks in out-of-domain settings.
method Consistency-guided temperature scaling (CTS) that considers style and content consistency.
result Significantly enhances out-of-domain calibration performance.
Enhances molecular design models by fine-tuning uncertainty-guided VAEs.
problem Fine-tuning pre-trained generative models for specific molecular property optimization.
method Uncertainty-guided fine-tuning of variational autoencoders in an active learning setting.
result Uncertainty-guided fine-tuning improves model performance across multiple molecular properties.
Proposes a method to optimize neural network initialization using marginal likelihood maximization.
problem Optimizing hyperparameters for neural network initialization.
method Leverages the connection between neural networks and Gaussian processes to infer optimal hyperparameters.
result Marginal likelihood maximization provides near-optimal prediction performance on MNIST classification tasks.
Study task-guided exploration in linear dynamical systems, improving sample complexity.
problem Efficiently learning about an environment to complete a specific task.
method Proposed a computationally efficient experiment-design based exploration algorithm.
result Optimally explores the environment, collecting precise information needed to complete the task.
A new discrepancy method improves efficiency and accuracy in unsupervised domain adaptation.
problem Measuring the difference between source and target domains without labeled target data.
method Source-guided discrepancy (S-disc) that uses source domain labels for efficient computation and tighter generalization bounds.
result S-disc provides a tighter generalization error bound than existing discrepancies.
GAT-RWOS uses graph attention to improve imbalanced data classification.
problem Imbalanced data leads to biased models favoring majority classes.
method Combines GATs and random walks to generate synthetic minority samples.
result Improves classification performance on imbalanced datasets.
Generates high-resolution faces based on attributes.
problem Creating realistic face images with user-specified attributes.
method Conditional CycleGAN, handling unpaired data and attribute control.
result Produces realistic face images with user-controlled attributes.
The paper proposes a system for faster probabilistic program inference.
problem Intractable probabilistic program inference in PPLs.
method Amortized inference using guide programs with neural network components.
result Preliminary results show faster inference with guide programs.
New method predicts spatio-temporal data with short and long-range dependence.
problem Uncertainty in predicting the distribution of mixed moving average fields.
method Theory-guided machine learning approach using generalized Bayesian algorithm.
result Fixed-time and any-time PAC Bayesian bounds for ensemble forecasts.
DC-Check helps guide ML development by considering data-centric aspects.
problem Lack of standardized framework for data-centric considerations in ML.
method DC-Check is a checklist-style framework for data-centric AI at ML pipeline stages.
result Promotes thoughtfulness and transparency in ML development.
GRAC improves reinforcement learning by self-guiding and self-regularizing.
problem Learning divergence and slow updates in reinforcement learning algorithms.
method Self-regularized TD-learning and self-guided policy improvement.
result Achieved or outperformed state-of-the-art results on OpenAI gym tasks.
XGL uses global explanations to guide human supervision in machine learning.
problem Improving model quality through human-machine interaction.
method XGL employs global explanations to guide human selection of informative examples.
result XGL avoids overselling the model's quality and performs comparably to other strategies.