CurveRL optimizes large model reasoning by reweighting prompts based on their rank and density.
problem Improving large language model reasoning through context reweighting.
method Formulated prompt reweighting as a functional derivative, proposing CurveRL based on quantile coordinate transform.
result CurveRL consistently outperforms existing methods across multiple benchmarks.
Resampling outperforms reweighting for correcting biased data in machine learning models.
problem Correcting sampling bias in machine learning models trained on biased data sets.
method Compared resampling and reweighting techniques, focusing on their performance with stochastic gradient algorithms.
result Resampling outperforms reweighting when combined with stochastic gradient algorithms.
A bilevel optimization method for reweighting data leads to suboptimal results.
problem Reweighting data for better model performance on a different distribution.
method Formalizes data reweighting as a bilevel optimization problem and analyzes the limitations of classical solvers.
result The final data weights are often very sparse, indicating suboptimal solutions.
Boosts causal discovery by dynamically reweighting samples to learn better DAGs.
problem Overfitting to easier-to-fit samples and violating homogeneity assumptions in causal discovery.
method Adaptive sample reweighting via ReScore function to upweight and downweight samples based on fitting quality.
result Consistent and significant boosts in structure learning performance on synthetic and real-world datasets.
Method improves SINDy for noisy nonlinear systems.
problem Recover nonlinear dynamical systems from noisy data.
method Reweighted ℓ1-regularized least squares. result Improved accuracy and robustness in noisy conditions.
Iterative reweighted algorithms, as a class of algorithms for sparse signal recovery, have been found to have better performance than their non-reweighted counterparts. However, for solving the problem of multiple measurement vectors (MMVs), all the existing reweighted algorithms do not account for temporal correlation…
Federated learning is protected against adversarial attacks with residual-based reweighting.
problem Adversarial attacks on federated learning's aggregation process.
method Residual-based reweighting combined with iteratively reweighted least squares.
result Our aggregation algorithm outperforms other methods in label-flipping and backdoor attacks.
This paper develops a novel deep recurrent neural network for sequential signal reconstruction.
problem Sequential signal reconstruction from low-dimensional measurements.
method Unfolding a reweighted ℓ1-ℓ1 minimization algorithm to design a deep recurrent neural network. result The proposed reweighted-RNN significantly outperforms existing RNN models in sequential frame reconstruction.
CrossTrainer adapts models across diverse datasets using loss reweighting.
problem Training models with data from varying sources or of varying quality.
method Loss reweighting with optimizations for hyperparameter tuning.
result High model accuracy across various datasets with improved training time.
DoubleEnsemble improves financial predictions by selecting key features and reweighting samples.
problem Overfitting and instability in financial data analysis.
method Sample reweighting and feature selection using learning trajectory and shuffling.
result DoubleEnsemble outperforms baseline methods in financial prediction tasks.
Bayesian model clusters, forecasts, and imputes multivariate time series data.
problem Jointly modeling and forecasting sparsely observed multivariate time series with varying dynamics.
method Chinese restaurant process prior for clustering, temporally-reweighted extension for joint modeling within clusters, MCMC for inference.
result Superior forecasting and competitive imputation accuracy compared to baselines, interpretable clusters discovered in macroeconomic data.
Improved matching for multiple objects using a novel reweighting method.
problem Current multi-object matching methods have limitations and are not robust.
method Proposes a novel iterative reweighting strategy using the graph connection Laplacian.
result Demonstrates superior performance over state-of-the-art methods.
In this paper we study general lp regularized unconstrained minimization problems. In particular, we derive lower bounds for nonzero entries of first- and second-order stationary points, and hence also of local minimizers of the lp minimization problems. We extend some existing iterative reweighted l1 (IRL1) a…
Reweighted l1-algorithms have attracted a lot of attention in the field of applied mathematics. A unified framework of such algorithms has been recently proposed by Zhao and Li. In this paper we construct a few new examples of reweighted l1-methods. These functions are certain concave approximations of the l0-norm func…
Proposes a new method to improve regression models with reweighted samples.
problem Improves regression models' performance under low sample sizes and covariate perturbations.
method Reparametrizes sample weights using a doubly non-negative matrix and solves the reweighted estimate efficiently.
result Adversarial reweighting strategy delivers promising results on various datasets.
RR-GNN improves GNN prediction intervals by accounting for graph heteroscedasticity and structural biases.
problem Uncertainty quantification in GNNs for high-stakes domains.
method Graph-Structured Mondrian CP, Residual-Adaptive Nonconformity Scores, Cross-Training Protocol.
result Improved efficiency and no loss of coverage compared to CP baselines.
Improved learning to reweight using deep interactions between student and teacher models.
problem Limitation of existing learning to reweight methods in utilizing student model's internal states.
method Proposes an algorithm that uses the student model's internal states to the teacher model, which returns adaptive weights to enhance student model training.
result Significant improvement over previous methods in image classification and neural machine translation experiments.
Paper proposes a method to learn cluster structured sparsity using adaptive reweighting.
problem Learning sparsity constraints from data without prior knowledge.
method Adapting IRL1 algorithm into a deep learning architecture with adaptive reweighting.
result Proposed method outperforms classical and learning-based algorithms on various tasks.
ResCP uses reservoir computing to create efficient, scalable time series prediction intervals.
problem Building distribution-free prediction intervals for time series data with small sample sizes and changing distributions.
method Reservoir Conformal Prediction (ResCP) leverages reservoir computing to dynamically reweight conformity scores based on similarity among reservoir states.
result ResCP achieves asymptotic conditional coverage and is effective across diverse forecasting tasks.
Paper proves IRLS converges to subspace from any start, with practical benefits.
problem Robust subspace estimation in machine learning.
method Iteratively Reweighted Least Squares (IRLS) with dynamic smoothing regularization.
result IRLS converges linearly to the underlying subspace from any initialization under deterministic conditions.
Defense against user shilling attacks in collaborative filtering using edge reweighting.
problem Vulnerability of collaborative filtering to profile injection attacks.
method Adversarial robustness based edge reweighting to attenuate non-robust edges.
result Effective defense against various types of attacks demonstrated through experiments.
A new method of event reweighting using boosted decision trees is presented.
problem Quality control of reweighting step in machine learning models.
method Novel event reweighting method based on boosted decision trees.
result Improved quality control of reweighting step in machine learning models.
We analyze a reweighted version of the Kikuchi approximation for estimating the log partition function of a product distribution defined over a region graph. We establish sufficient conditions for the concavity of our reweighted objective function in terms of weight assignments in the Kikuchi expansion, and show that a…
New method uses weighted SDEs to improve sampling from complex distributions.
problem Sampling from highly non-log-concave distributions.
method Introduces weighted stochastic differential equations to augment diffusion-based samplers.
result Demonstrates improved exploration of nonconvex or multimodal landscapes.
Unified framework for accelerating DNNs on resource-limited platforms.
problem Accelerating DNN execution on resource-limited platforms.
method Block-based pruning framework with reweighted regularization.
result First universal framework for both CNNs and RNNs with real-time acceleration and no accuracy compromise.
Unified analysis of reweighted least-squares algorithms for linear models.
problem Recovering unknown signals from linear measurements using reweighted least squares.
method Unified asymptotic analysis of IRLS, lin-RFM, and alternating minimization algorithms.
result The algorithms can achieve favorable performance in a few iterations with appropriate reweighting.
New reweighted losses improve diffusion model training and image quality.
problem Training and improving diffusion models for image generation.
method Constructing a cascade of time-dependent variational lower bounds.
result Significant improvements in pixel-space image modeling quality.
New convergence analysis for Lasso l1 reweighting improves practical performance.
problem Theoretical convergence of Lasso l1 reweighting methods is limited.
method Biconvex analysis for an alternated convex search.
result Numerical convergence of the algorithm sequence for practical purposes.
Reweighting improves GAN accuracy without sacrificing statistical power.
problem Improving the fidelity of generative models.
method Post-hoc reweighting function applied to generated examples.
result Weighted GAN examples significantly improve accuracy.
New algorithms improve L1 PCA performance.
problem Optimizing PCA with L1 norm for better data reduction.
method Iteratively reweighted least squares algorithms.
result Proposed algorithms outperform existing methods.
New algorithm improves online binary classification with constant time complexity.
problem Online binary classification with rebalancing.
method Non-iteratively reweighted recursive least-squares.
result Exacts converges to batch formulation and outperforms existing algorithms.
DCTR uses neural networks to improve particle physics simulations and parameter tuning.
problem High computational cost limits precise scientific analysis in particle physics.
method Deep neural networks for reweighting and parameter tuning of simulations.
result DCTR enables precise simulations and parameter tuning, improving model accuracy.
Ant colonies and boosting algorithms both reduce bias and variance through adaptive mechanisms.
problem Understanding the mathematical principles behind ensemble learning and ant colony behavior.
method Developed a formal mapping between AdaBoost's adaptive reweighting and ant recruitment dynamics.
result Proved that the fundamental theorem of weak learnability has a direct analog in colony decision-making.
Reduces bias in linear models by reweighting samples.
problem Bias in linear models due to collinearity among input variables.
method Sample reweighting to reduce collinearity.
result Improves stability of prediction results across different data distributions.
Toy model study shows resampling/reweighting can improve feature learning in imbalanced classification.
problem Improving feature learning in imbalanced classification problems.
method High-dimensional toy model with replica method, class-wise resampling/reweighting, and simplified model.
result No resampling/reweighting can sometimes give best feature learning performance.
Connection found between signal processing and slime mold dynamics.
problem Convergence of IRLS algorithm remains an open problem.
method Connection between IRLS and Physarum dynamics, proving convergence of a damped version.
result Convergence and complexity bounds for a damped version of the IRLS algorithm.
A method removes treatment-covariate dependence for counterfactual prediction without adversarial training.
problem Counterfactual prediction under assignment bias.
method Information-theoretic approach learning a stochastic representation Z to minimize mutual information with outcomes.
result The method performs favorably in likelihood, counterfactual error, and policy evaluation compared to adversarial baselines.
Paper accelerates an optimization algorithm using extrapolation techniques.
problem Optimizing problems with a sum of a differentiable loss and a nonconvex sparsity regularizer.
method Incorporates extrapolation techniques into iteratively reweighted ℓ1 algorithms. result Sequence generated clusters at stationary points of the optimization problem.
A meta-learning algorithm reweights examples to improve deep learning robustness.
problem Overfitting and label noise in deep learning models.
method Meta-learning algorithm that learns example weights based on gradient directions.
result Significant improvement in performance on class imbalance and corrupted label problems.
Algorithm samples polygons of fixed edge lengths in any dimension.
problem Sampling random closed polygons with fixed edge lengths in any dimension.
method Weighted edge vectors on unit sphere, Möbius transformation, reweighting factors.
result Algorithm samples polygons according to standard probability measures efficiently.
The paper improves sample reweighting methods for adapting to covariate shifts.
problem Improving accuracy in reproducing kernel Hilbert spaces when data distributions differ.
method Combining known error bounds for reweighted kernel regression in RKHS to show reduced sample size needed for accuracy.
result Under weak smoothness conditions, fewer samples are needed for the same accuracy as standard supervised learning.
Spectral clustering is widely used to partition graphs into distinct modules or communities. Existing methods for spectral clustering use the eigenvalues and eigenvectors of the graph Laplacian, an operator that is closely associated with random walks on graphs. We propose a new spectral partitioning method that exploi…
LADDER improves DG by reweighting domain-specific classifiers.
problem Challenges of domain generalization when causal mechanisms vary across domains.
method LADDER learns causal and style representations, reweights classifiers at inference.
result LADDER achieves gains in accuracy on various DG tasks.
A new method uses GAN principles to balance treatment groups in causal inference.
problem Biased observational data in treatment outcomes estimation.
method Bi-level optimization with a discriminator and a weights generator.
result The method effectively estimates causal effects with theoretical bounds on estimation error.
Optimizes sample reweighting to match laws under covariate shift using Wasserstein distance.
problem Matching laws of samples with different distributions under covariate shift.
method Minimizes Wasserstein distance between empirical measures of samples using Nearest Neighbors weights.
result Consistent reweighting leads to asymptotic convergence of empirical measures.
Q-MMR evaluates policies using reweighted rewards and moment matching.
problem Off-policy evaluation in finite-horizon MDPs.
method Q-MMR learns scalar weights for data points via a moment matching objective against a value-function discriminator class.
result Data-dependent finite-sample guarantee with a dimension-free error bound.
Method reweights instances and classes to improve robustness in noisy data.
problem Improving deep learning performance in the presence of label noise.
method Formulates constrained optimization problems to assign importance weights to instances and class labels.
result Significant performance gains observed in benchmark datasets with label noise.
ARL improves fairness without protected features, showing AUC improvements for worst-case groups.
problem Training fairness in ML without known protected features.
method Adversarially Reweighted Learning (ARL) using non-protected features and task labels.
result ARL improves Rawlsian Max-Min fairness with notable AUC improvements for worst-case groups.