English
Related papers

Related papers: Credit Attribution and Stable Compression

200 papers

The goal of predictive data attribution is to estimate how adding or removing a given set of training datapoints will affect model predictions. In convex settings, this goal is straightforward (i.e., via the infinitesimal jackknife). In…

Machine Learning · Computer Science 2025-04-24 Andrew Ilyas , Logan Engstrom

Recent research reveals that machine learning (ML) models are highly sensitive to minor changes in their training procedure, such as the inclusion or exclusion of a single data point, leading to conflicting predictions on individual data…

Machine Learning · Computer Science 2025-07-15 Falaah Arif Khan , Denys Herasymuk , Nazar Protsiv , Julia Stoyanovich

Artificial Intelligence (AI) has made its way into various scientific fields, providing astonishing improvements over existing algorithms for a wide variety of tasks. In recent years, there have been severe concerns over the trustworthiness…

Machine Learning · Computer Science 2024-08-20 Surbhi Mittal , Kartik Thakral , Richa Singh , Mayank Vatsa , Tamar Glaser , Cristian Canton Ferrer , Tal Hassner

As attribution-based explanation methods are increasingly used to establish model trustworthiness in high-stakes situations, it is critical to ensure that these explanations are stable, e.g., robust to infinitesimal perturbations to an…

In this paper, we consider differentially private classification when some features are sensitive, while the rest of the features and the label are not. We adapt the definition of differential privacy naturally to this setting. Our main…

Machine Learning · Computer Science 2023-12-14 Zeyu Shen , Anilesh Krishnaswamy , Janardhan Kulkarni , Kamesh Munagala

Data attribution methods, which quantify the influence of individual training data points on a machine learning model, have gained increasing popularity in data-centric applications in modern AI. Despite a recent surge of new methods…

Machine Learning · Computer Science 2025-10-24 Weiyi Wang , Junwei Deng , Yuzheng Hu , Shiyuan Zhang , Xirui Jiang , Runting Zhang , Han Zhao , Jiaqi W. Ma

The use of algorithmic predictions in decision-making leads to a feedback loop where the models we deploy actively influence the data distributions we see, and later use to retrain on. This dynamic was formalized by Perdomo et al. 2020 in…

Machine Learning · Computer Science 2026-03-02 Gabriele Farina , Juan Carlos Perdomo

Differential privacy is the de-facto privacy standard in data analysis. The classic model of differential privacy considers the data to be static. The dynamic setting, called differential privacy under continual observation, captures many…

Data Structures and Algorithms · Computer Science 2023-06-21 Monika Henzinger , A. R. Sricharan , Teresa Anna Steiner

Auditing differential privacy has emerged as an important area of research that supports the design of privacy-preserving mechanisms. Privacy audits help to obtain empirical estimates of the privacy parameter, to expose flawed…

Cryptography and Security · Computer Science 2025-09-25 Önder Askin , Tim Kutta , Holger Dette

The widespread adoption of machine learning necessitates robust privacy protection alongside algorithmic resilience. While Local Differential Privacy (LDP) provides foundational guarantees, sophisticated adversaries with prior knowledge…

Machine Learning · Computer Science 2025-07-31 Xiaojin Zhang , Wei Chen

The development of fair and unbiased machine learning models remains an ongoing objective for researchers in the field of artificial intelligence. We introduce the Differential Adjusted Parity (DAP) loss to produce unbiased informative…

Machine Learning · Computer Science 2025-04-10 Bucher Sahyouni , Matthew Vowels , Liqun Chen , Simon Hadfield

The robustness of algorithms against covariate shifts is a fundamental problem with critical implications for the deployment of machine learning algorithms in the real world. Current evaluation methods predominantly measure robustness…

Credit scoring is vital in the financial industry, assessing the risk of lending to credit card applicants. Traditional credit scoring methods face challenges with large datasets and data imbalance between creditworthy and non-creditworthy…

Computational Engineering, Finance, and Science · Computer Science 2024-09-26 Kejian Tong , Zonglin Han , Yanxin Shen , Yujian Long , Yijing Wei

Towards understanding the statistical complexity of learning from heterogeneous sources, we study the problem of multi-distribution learning. Given $k$ data sources, the goal is to output a classifier for each source by exploiting shared…

Machine Learning · Statistics 2026-02-25 Rafael Hanashiro , Abhishek Shetty , Patrick Jaillet

While unbiased machine learning models are essential for many applications, bias is a human-defined concept that can vary across tasks. Given only input-label pairs, algorithms may lack sufficient information to distinguish stable (causal)…

Machine Learning · Computer Science 2022-06-28 Yujia Bao , Shiyu Chang , Regina Barzilay

How do we formalize the challenge of credit assignment in reinforcement learning? Common intuition would draw attention to reward sparsity as a key contributor to difficult credit assignment and traditional heuristics would look to temporal…

Machine Learning · Computer Science 2021-03-11 Dilip Arumugam , Peter Henderson , Pierre-Luc Bacon

Continual learning is an emerging paradigm in machine learning, wherein a model is exposed in an online fashion to data from multiple different distributions (i.e. environments), and is expected to adapt to the distribution change.…

Machine Learning · Computer Science 2022-03-29 Binghui Peng , Andrej Risteski

We investigate the in-distribution generalization of machine learning algorithms. We depart from traditional complexity-based approaches by analyzing information-theoretic bounds that quantify the dependence between a learning algorithm and…

Machine Learning · Statistics 2024-08-27 Borja Rodríguez-Gálvez , Ragnar Thobaben , Mikael Skoglund

The widespread use of Artificial Intelligence (AI) in consequential domains, such as healthcare and parole decision-making systems, has drawn intense scrutiny on the fairness of these methods. However, ensuring fairness is often…

Artificial Intelligence · Computer Science 2021-09-10 Ninareh Mehrabi , Umang Gupta , Fred Morstatter , Greg Ver Steeg , Aram Galstyan

Multi-distribution learning extends agnostic Probably Approximately Correct (PAC) learning to the setting in which a family of $k$ distributions, $\{D_i\}_{i\in[k]}$, is considered and a classifier's performance is measured by its error…

Machine Learning · Computer Science 2025-06-24 Chicheng Zhang , Yihan Zhou
‹ Prev 1 4 5 6 7 8 10 Next ›