English
Related papers

Related papers: Mitigating Bias in Adaptive Data Gathering via Dif…

200 papers

Differential privacy enables organizations to collect accurate aggregates over sensitive data with strong, rigorous guarantees on individuals' privacy. Previous work has found that under differential privacy, computing multiple correlated…

Databases · Computer Science 2016-05-18 Ganzhao Yuan , Yin Yang , Zhenjie Zhang , Zhifeng Hao

We study the offline contextual bandit problem, where we aim to acquire an optimal policy using observational data. However, this data usually contains two deficiencies: (i) some variables that confound actions are not observed, and (ii)…

Machine Learning · Computer Science 2023-03-21 Siyu Chen , Yitan Wang , Zhaoran Wang , Zhuoran Yang

In many applications, e.g. in healthcare and e-commerce, the goal of a contextual bandit may be to learn an optimal treatment assignment policy at the end of the experiment. That is, to minimize simple regret. However, this objective…

Machine Learning · Computer Science 2023-11-06 Sanath Kumar Krishnamurthy , Ruohan Zhan , Susan Athey , Emma Brunskill

This paper investigates the issue of privacy in a learning scenario where users share knowledge for a recommendation task. Our study contributes to the growing body of research on privacy-preserving machine learning and underscores the need…

Machine Learning · Computer Science 2023-10-03 Alexander Galozy , Sadi Alawadi , Victor Kebande , Sławomir Nowaczyk

Contextual bandits are online learners that, given an input, select an arm and receive a reward for that arm. They use the reward as a learning signal and aim to maximize the total reward over the inputs. Contextual bandits are commonly…

Machine Learning · Computer Science 2020-02-14 Awni Hannun , Brian Knott , Shubho Sengupta , Laurens van der Maaten

An individual's decisions are often guided by those of his or her peers, i.e., neighbors in a social network. Presumably, being privy to the experiences of others aids in learning and decision making, but how much advantage does an…

Machine Learning · Computer Science 2017-04-17 L. Elisa Celis , Farnood Salehi

Prior work on differential privacy analysis of randomized SGD algorithms relies on composition theorems, where the implicit (unrealistic) assumption is that the internal state of the iterative algorithm is revealed to the adversary. As a…

Machine Learning · Statistics 2022-10-18 Jiayuan Ye , Reza Shokri

Differential privacy guarantees allow the results of a statistical analysis involving sensitive data to be released without compromising the privacy of any individual taking part. Achieving such guarantees generally requires the injection…

Machine Learning · Statistics 2023-10-31 Jack Jewson , Sahra Ghalebikesabi , Chris Holmes

We propose ${\tt AdaTS}$, a Thompson sampling algorithm that adapts sequentially to bandit tasks that it interacts with. The key idea in ${\tt AdaTS}$ is to adapt to an unknown task prior distribution by maintaining a distribution over its…

Machine Learning · Computer Science 2022-02-28 Soumya Basu , Branislav Kveton , Manzil Zaheer , Csaba Szepesvári

Adversarial attacks on stochastic bandits have traditionally relied on some unrealistic assumptions, such as per-round reward manipulation and unbounded perturbations, limiting their relevance to real-world systems. We propose a more…

Machine Learning · Computer Science 2026-05-08 Qirun Zeng , Eric He , Richard Hoffmann , Xuchuang Wang , Jinhang Zuo

Overfitting is the bane of data analysts, even when data are plentiful. Formal approaches to understanding this problem focus on statistical inference and generalization of individual analysis procedures. Yet the practice of data analysis…

Machine Learning · Computer Science 2015-09-28 Cynthia Dwork , Vitaly Feldman , Moritz Hardt , Toniann Pitassi , Omer Reingold , Aaron Roth

High dimensional sparse linear bandits serve as an efficient model for sequential decision-making problems (e.g. personalized medicine), where high dimensional features (e.g. genomic data) on the users are available, but only a small subset…

Machine Learning · Statistics 2024-10-30 Sunrit Chakraborty , Saptarshi Roy , Debabrota Basu

Datasets are often used multiple times and each successive analysis may depend on the outcome of previous analyses. Standard techniques for ensuring generalization and statistical validity do not account for this adaptive dependence. A…

Machine Learning · Computer Science 2018-06-13 Vitaly Feldman , Thomas Steinke

Multi-armed bandit algorithms have been argued for decades as useful for adaptively randomized experiments. In such experiments, an algorithm varies which arms (e.g. alternative interventions to help students learn) are assigned to…

Machine Learning · Computer Science 2021-03-29 Joseph Jay Williams , Jacob Nogas , Nina Deliu , Hammad Shaikh , Sofia S. Villar , Audrey Durand , Anna Rafferty

The potential risk of privacy leakage prevents users from sharing their honest opinions on social platforms. This paper addresses the problem of privacy preservation if the query returns the histogram of rankings. The framework of…

Artificial Intelligence · Computer Science 2014-09-25 Shang Shang , Tiance Wang , Paul Cuff , Sanjeev Kulkarni

The widespread use of machine learning and data-driven algorithms for decision making has been steadily increasing over many years. \emph{Bias} in the data can adversely affect this decision-making. We present a new mitigation strategy to…

Machine Learning · Computer Science 2025-07-25 Bruno Scarone , Alfredo Viola , Renée J. Miller , Ricardo Baeza-Yates

We consider stochastic multi-armed bandit problems with graph feedback, where the decision maker is allowed to observe the neighboring actions of the chosen action. We allow the graph structure to vary with time and consider both…

Machine Learning · Computer Science 2017-11-10 Fang Liu , Swapna Buccapatnam , Ness Shroff

Adaptive data analysis (ADA) involves a dynamic interaction between an analyst and a dataset owner, where the analyst submits queries sequentially, adapting them based on previous answers. This process can become adversarial, as the analyst…

Human-Computer Interaction · Computer Science 2025-01-22 Amir Hossein Hadavi , Mohammad M. Mojahedian , Mohammad Reza Aref

We study private prediction where differential privacy is achieved by adding noise to the outputs of a non-private model. Existing methods rely on noise proportional to the global sensitivity of the model, often resulting in sub-optimal…

We give a new proof of the "transfer theorem" underlying adaptive data analysis: that any mechanism for answering adaptively chosen statistical queries that is differentially private and sample-accurate is also accurate out-of-sample. Our…

Machine Learning · Computer Science 2024-06-05 Christopher Jung , Katrina Ligett , Seth Neel , Aaron Roth , Saeed Sharifi-Malvajerdi , Moshe Shenfeld
‹ Prev 1 4 5 6 7 8 10 Next ›