works on

From the 2 of 19 linked papers with an AI index.

activity
20242026
collaborators

19 papers

cs.LG2026

The Role of Causality in Algorithmic Recourse

Srikanth Avasarala, Varun Gupta, Shahin Jabbari +2

The paper introduces a causal framework for algorithmic recourse that models how suggested changes affect both features and true outcomes, showing that accounting for causality yie…

cs.GT2026

Effort Matters in Score-Based Admissions: How Retaking and Aggregation Shape Test Scores

Christine Ling, Diptangshu Sen, Juba Ziani

The paper models how students allocate effort across multiple test retakes and shows that common scoring policies like superscoring can inflate scores and increase wealth-based dis…

cs.GT2026

The Impact of Competition on Outcomes of Score-Based College Admissions

George Bentley, Diptangshu Sen, Juba Ziani

We study how the design of admissions policies affects the ability of students admitted to universities. In our model, applicants have a multi-dimensional ability, which is a combi…

cs.IT2026

Local Differential Privacy with Correlated Noise Achieves Central-DP Optimal Cost

Madhura Pathegama, Srikanth Avasarala, Viveck R. Cadambe +1

We study privately estimating the sum of user-held values in the presence of an honest-but-curious server. This motivates requiring privacy not only at data release but also th…

cs.CY2026

Fixed Points and Stochastic Meritocracies: A Long-Term Perspective

Gaurab Pokharel, Diptangshu Sen, Sanmay Das +1

We study group fairness in the context of feedback loops induced by meritocratic selection into programs that themselves confer additional advantage, like college admissions. We in…

cs.GT2026

Data Sharing with Endogenous Choices over Differential Privacy Levels

Raef Bassily, Kate Donahue, Diptangshu Sen +2

Motivated by the rapid push to decentralize sharing of data, we study whether large-scale data sharing coalitions can form in a decentralized manner under differential privacy when…