7 papers
Why Global LLM Leaderboards Are Misleading: Small Portfolios for Heterogeneous Supervised ML
Jai Moondra, Ayela Chughtai, Bhargavi Lanka +1
Ranking LLMs via pairwise human feedback underpins current leaderboards for open-ended tasks, such as creative writing and problem-solving. We analyze ~89K comparisons in 116 langu…
Many Preferences, Few Policies: Towards Scalable Language Model Personalization
Cheol Woo Kim, Jai Moondra, Roozbeh Nahavandi +3
The holy grail of LLM personalization is a single LLM for each user, perfectly aligned with that user's preferences. However, maintaining a separate LLM per user is impractical due…
Promise of Graph Sparsification and Decomposition for Noise Reduction in QAOA: Analysis for Trapped-Ion Compilations
Jai Moondra, Phillip C. Lotshaw, Philip C. Lotshaw +2
We develop new approximate compilation schemes that significantly reduce the expense of compiling the Quantum Approximate Optimization Algorithm (QAOA) for solving the Max-Cut prob…
Stochastic Function Certification with Correlations
Rohan Ghuge, Jai Moondra, Mohit Singh
We study the Stochastic Boolean Function Certification (SBFC) problem, where we are given Bernoulli random variables on a ground set of elements with…
Improved Regret Guarantees for Online Mirror Descent using a Portfolio of Mirror Maps
Swati Gupta, Jai Moondra, Mohit Singh
OMD and its variants give a flexible framework for OCO where the performance depends crucially on the choice of the mirror map. While the geometries underlying OPGD and OEG, both s…
Provably Small Portfolios for Multiobjective Optimization with Application to Subsidized Facility Location
Swati Gupta, Jai Moondra, Mohit Singh
Many multiobjective real-world problems, such as facility location and bus routing, become more complex when optimizing the priorities of multiple stakeholders. These are often mod…