Search Results for author:
Found 24 papers, 12 papers with code
Understanding Impact of Human Feedback via Influence Functions
By quantifying the impact of human feedback on reward models, we believe that influence functions can enhance feedback interpretability and contribute to scalable oversight in RLHF, helping labelers provide more accurate and consistent feedback.
Distributionally Robust Instrumental Variables Estimation
Viewing common issues in IV estimation as distributional uncertainties, we propose DRIVE, a distributionally robust IV estimation method.
Group Shapley Value and Counterfactual Simulations in a Structural Model
We propose a variant of the Shapley value, the group Shapley value, to interpret counterfactual simulations in structural economic models by quantifying the importance of different components.
2D-OOB: Attributing Data Contribution Through Joint Valuation Framework
Data valuation has emerged as a powerful framework for quantifying each datum's contribution to the training of a machine learning model.
TimeInf: Time Series Data Contribution via Influence Functions
Evaluating the contribution of individual data points to a model's prediction is critical for interpreting model predictions and improving model performance.
Proper Dataset Valuation by Pointwise Mutual Information
Data plays a central role in the development of modern artificial intelligence, with high-quality data emerging as a key driver of model performance.
Rethinking Data Shapley for Data Selection Tasks: Misleads and Merits
Data Shapley provides a principled approach to data valuation and plays a crucial role in data-centric machine learning (ML) research.
Data Acquisition: A New Frontier in Data-centric AI
As Machine Learning (ML) systems continue to grow, the demand for relevant and comprehensive datasets becomes imperative.
DataInf: Efficiently Estimating Data Influence in LoRA-tuned LLMs and Diffusion Models
Quantifying the impact of training data points is crucial for understanding the outputs of machine learning models and for improving the transparency of the AI pipeline.
OpenDataVal: a Unified Benchmark for Data Valuation
Assessing the quality and impact of individual data points is critical for improving model performance and mitigating undesirable biases within the training dataset.
Accuracy on the Curve: On the Nonlinear Correlation of ML Performance Between Data Subpopulations
Our work highlights the importance of understanding the nonlinear effects of model improvement on performance in different subpopulations, and has the potential to inform the development of more equitable and responsible machine learning models.
Data-OOB: Out-of-bag Estimate as a Simple and Efficient Data Value
As a result, it has been recognized as infeasible to apply to large datasets.
WeightedSHAP: analyzing and improving Shapley based feature attributions
On several real-world datasets, we demonstrate that the influential features identified by WeightedSHAP are better able to recapitulate the model's predictions compared to the features identified by the Shapley value.
Mind the Gap: Understanding the Modality Gap in Multi-modal Contrastive Representation Learning
Our systematic analysis demonstrates that this gap is caused by a combination of model initialization and contrastive learning optimization.
Competition over data: how does data purchase affect users?
We introduce a new environment that allows ML predictors to use active learning algorithms to purchase labeled data within their budgets while competing against each other to attract users.
Beta Shapley: a Unified and Noise-reduced Data Valuation Framework for Machine Learning
Data Shapley has recently been proposed as a principled framework to quantify the contribution of individual datum in machine learning.
Competing AI: How does competition feedback affect machine learning?
A service that is more often queried by users, perhaps because it more accurately anticipates user preferences, is also more likely to obtain additional user data (e. g. in the form of a Yelp review).
Efficient computation and analysis of distributional Shapley values
Distributional data Shapley value (DShapley) has recently been proposed as a principled framework to quantify the contribution of individual datum in machine learning.
Principled learning method for Wasserstein distributionally robust optimization with local perturbations
We show that our approximation and risk consistency results naturally extend to the cases when data are locally perturbed.
Uncertainty quantification of molecular property prediction with Bayesian neural networks
Deep neural networks have outperformed existing machine learning models in various molecular applications.
Principled analytic classifier for positive-unlabeled learning via weighted integral probability metric
We consider the problem of learning a binary classifier from only positive and unlabeled observations (called PU learning).
Uncertainty quantification of molecular property prediction using Bayesian neural network models
In chemistry, deep neural network models have been increasingly utilized in a variety of applications such as molecular property predictions, novel molecule designs, and planning chemical reactions.
Uncertainty quantification using Bayesian neural networks in classification: Application to ischemic stroke lesion segmentation
Most recent research of neural networks in the field of computer vision has focused on improving accuracy of point predictions by developing various network architectures or learning algorithms.
General Classification
Ischemic Stroke Lesion Segmentation
+2
