5 papers
Shuffle and Joint Differential Privacy for Generalized Linear Contextual Bandits
Sahasrajit Sarmasarkar
We present the first algorithms for generalized linear contextual bandits under shuffle differential privacy and joint differential privacy. While prior work on private contextual…
Preference Learning with Response Time: Robust Losses and Guarantees
Ayush Sawarni, Sahasrajit Sarmasarkar, Vasilis Syrgkanis
This paper investigates the integration of response time data into human preference learning frameworks for more effective reward model elicitation. While binary preference data ha…
Multi-Selection for Recommendation Systems
Sahasrajit Sarmasarkar, Zhihao Jiang, Ashish Goel +2
We present the construction of a multi-selection model to answer differentially private queries in the context of recommendation systems. The server sends back multiple recommendat…
A Characterization of List Regression
Chirag Pabbaraju, Sahasrajit Sarmasarkar
There has been a recent interest in understanding and characterizing the sample complexity of list learning tasks, where the learning algorithm is allowed to make a short list of $…
Query complexity of heavy hitter estimation
Sahasrajit Sarmasarkar, Kota Srinivas Reddy, Nikhil Karamchandani
We consider the problem of identifying the subset of elements in the support of an underlying distribution whose probability value is la…