45 citations · 48 across the 7 of their papers we have counts for
7 papers
FisherSFT: Data-Efficient Supervised Fine-Tuning of Language Models Using Information Gain
Rohan Deb, Kiran Thekumparampil, Kousha Kalantari +3
Supervised fine-tuning (SFT) is a standard approach to adapting large language models (LLMs) to new domains. In this work, we improve the statistical efficiency of SFT by selecting…
Comparing Few to Rank Many: Active Human Preference Learning using Randomized Frank-Wolfe
Kiran Koshy Thekumparampil, Gaurush Hiranandani, Kousha Kalantari +2
We study learning of human preferences from a limited comparison feedback. This task is ubiquitous in machine learning. Its applications such as reinforcement learning from human f…
Language-Model Prior Overcomes Cold-Start Items
Shiyu Wang, Hao Ding, Yupeng Gu +3
The growth of recommender systems (RecSys) is driven by digitization and the need for personalized content in areas such as e-commerce and video streaming. The content in these sys…
Optimal Design for Human Preference Elicitation
Subhojyoti Mukherjee, Anusha Lalitha, Kousha Kalantari +4
Learning of preference models from human feedback has been central to recent advances in artificial intelligence. Motivated by the cost of obtaining high-quality human annotations,…
Fixed-Budget Best-Arm Identification with Heterogeneous Reward Variances
Anusha Lalitha, Kousha Kalantari, Yifei Ma +2
We study the problem of best-arm identification (BAI) in the fixed-budget setting with heterogeneous reward variances. We propose two variance-adaptive BAI algorithms for this sett…
Information-Theoretic Privacy with General Distortion Constraints
Kousha Kalantari, Oliver Kosut, Lalitha Sankar
The privacy-utility tradeoff problem is formulated as determining the privacy mechanism (random mapping) that minimizes the mutual information (a metric for privacy leakage) betwee…
Robust Privacy-Utility Tradeoffs under Differential Privacy and Hamming Distortion
Kousha Kalantari, Lalitha Sankar, Anand Sarwate
A privacy-utility tradeoff is developed for an arbitrary set of finite-alphabet source distributions. Privacy is quantified using differential privacy (DP), and utility is quantifi…