paper-with-me

Papers

Understanding Influence Functions and Datamodels via Harmonic Analysis

2022-10-03 · Nikunj Saunshi, Arushi Gupta, Mark Braverman, Sanjeev Arora

Influence functions estimate effect of individual data points on predictions of the model on test data and were adapted to deep learning in Koh and Liang [2017]. They have been used for detecting data poisoning, detecting helpful and harmful examples, influence of groups of datapoints, etc. Recently, Ilyas et al. [2022] introduced a linear regression method they termed datamodels to predict the effect of training points on outputs on test data. The current paper seeks to provide a better theoretical understanding of such interesting empirical phenomena. The primary tool is harmonic analysis and the idea of noise stability. Contributions include: (a) Exact characterization of the learnt datamodel in terms of Fourier coefficients. (b) An efficient method to estimate the residual error and quality of the optimum linear datamodel without having to train the datamodel. (c) New insights into when influences of groups of datapoints may or may not add up linearly.

📄 PDF Abstract BibTeX arXiv:2210.01072

Code (0)

등록된 구현이 없습니다.

Tasks

Data Poisoning

Methods 이 논문이 사용한 방법론

Test 설명 없음
Linear Regression Linear Regression is a method for modelling a relationship between a dependent variable and independent variables. These models can be fit with numerous approaches. The most…

Similar Papers 제목 키워드 기반

Datamodels: Predicting Predictions from Training Data

2022-02-01 · Andrew Ilyas, Sung Min Park, Logan Engstrom, Guillaume Leclerc 외

We present a conceptual framework, datamodeling, for analyzing the behavior of a model class in terms of the training data. For any fixed "target" example $x$, training set $S$, and learning algorithm, a datamodel is a p…

Data Curation Alone Can Stabilize In-context Learning

2022-12-20 · Ting-Yun Chang, Robin Jia

In-context learning (ICL) enables large language models (LLMs) to perform new tasks by prompting them with a sequence of training examples. However, it is known that ICL is very sensitive to the choice of training exampl…

DiversityIn-Context LearningRetrieval

Data-Driven Modelling for Harmonic Current Emission in Low-Voltage Grid Using MCReSANet with Interpretability Analysis

2023-11-26 · Jieyu Yao, Hao Yu, Paul Judge, Jiabin Jia 외

Even though the use of power electronics PE loads offers enhanced electrical energy conversion efficiency and control, they remain the primary sources of harmonics in grids. When diverse loads are connected in the distri…

Feature Importance

Data Debiasing with Datamodels (D3M): Improving Subgroup Robustness via Data Selection

2024-06-24 · Saachi Jain, Kimia Hamidieh, Kristian Georgiev, Andrew Ilyas 외

Machine learning models can fail on subgroups that are underrepresented during training. While techniques such as dataset balancing can improve performance on underperforming groups, they require access to training group…

Harmonic Control Lyapunov Barrier Functions for Constrained Optimal Control with Reach-Avoid Specifications

2023-10-04 · Amartya Mukherjee, Ruikun Zhou, Haocheng Chang, Jun Liu

This paper introduces harmonic control Lyapunov barrier functions (harmonic CLBF) that aid in constrained control problems such as reach-avoid problems. Harmonic CLBFs exploit the maximum principle that harmonic function…