Amir Gilad

Amir Gilad

Assistant Professor

The Hebrew University

About

I am an Assistant Professor (Senior Lecturer) at the Hebrew University of Jerusalem’s School of Computer Science and Engineering.

My research focuses on responsible data science including uses of causal inference in data analysis, differential privacy, fairness and representation aspects in data, and the development of tools and algorithms that aim to assist users in understanding and gaining insights into data.

I am a recipient of the 2017 VLDB Best Paper Award, the 2018 SIGMOD Research Highlight Award, the 2019 Google Ph.D. Fellowship in Structured Data and Database Management, and the 2024 Alon Scholarship for the Integration of Outstanding Faculty.

Before joining the Hebrew University, I was a postdoctoral researcher in the Database Group at Duke University, hosted by Prof. Sudeepa Roy, Prof. Ashwin Machanavajjhala, and Prof. Jun Yang. I obtained my Ph.D in Computer Science from Tel Aviv University, where I was advised by Prof. Daniel Deutch.

I am recruiting M.Sc. and Ph.D. students! Please contact me if you are interested in working together.

Interests

  • Data Management
  • Responsible Data Science
  • Causal Inference Applications for Data Analysis
  • Differential Privacy

Education

  • Postdoc in the Database Group

    Duke University

  • PhD in Computer Science

    Tel Aviv University

  • MSc in Computer Science

    Tel Aviv University

  • BSc in Mathematics and Computer Science

    Tel Aviv University

Projects

Data Quality Assessment and Repair

Develop approaches for assessing data quality and bias, and devise algorithms to repair the data.

Private and Fair Data Generation

Generate data in a Differentially Private manner that is faithful to the private data and also satisfies fairness and integrity constraints.

Causal inference usage in data analysis

Employ causal inference principles to enhance and improve data analysis capabilities.

Recent Publications

(2024). The Cost of Representation by Subset Repairs. In PVLDB 18(2), 2025.

Link

(2024). Finding Convincing Views to Endorse a Claim. In PVLDB 18(2), 2025.

Link

(2024). DP-PQD: Privately Detecting Per-Query Gaps In Synthetic Data Generated By Black-Box Mechanisms. In PVLDB 17(1), 2024.

PDF Link

(2024). PD-Explain: A Unified Python-native Framework for Query Explanations Over DataFrames. In PVLDB 17(12), 2024.

PDF Link

(2024). Qr-Hint: Actionable Hints Towards Correcting Wrong SQL Queries. In SIGMOD.

PDF Link

(2024). Summarized Causal Explanations For Aggregate Views. In SIGMOD.

PDF Link

(2023). Characterizing and Verifying Queries Via CINSGEN. In SIGMOD.

PDF Link

Teaching

Topics in Responsible Data Science

Seminar on Advanced Topics in Databases

Seminar on Causal Inference in Data Analysis

Extended Introduction to Computer Science

Workshop: Google Technologies

Contact