6 papers
Efficient Evaluation of LLM Performance with Statistical Guarantees
Skyler Wu, Yash Nair, Emmanuel J. Candès
Exhaustively evaluating many large language models (LLMs) on a large suite of benchmarks is expensive. We cast benchmarking as finite-population inference and, under a fixed query…
Are Statistical Methods Obsolete in the Era of Deep Learning? A Study of ODE Inverse Problems
Skyler Wu, Shihao Yang, S. C. Kou
In the era of AI, neural networks have become increasingly popular for modeling, inference, and prediction, largely due to their potential for universal approximation. With the pro…
Intelligently Weighting Multiple Reference Models for Direct Preference Optimization of LLMs
Skyler Wu, Aymen Echarghaoui
Fine-tuning is integral for aligning large language models (LLMs) with human preferences. Multiple-Reference Preference Optimization (MRPO) builds on Direct Preference Optimization…
Parallelizing MCMC Across the Sequence Length
David M. Zoltowski, Skyler Wu, Xavier Gonzalez +2
Markov chain Monte Carlo (MCMC) methods are foundational algorithms for Bayesian inference and probabilistic modeling. However, most MCMC algorithms are inherently sequential and t…
Missing Data Multiple Imputation for Tabular Q-Learning in Online RL
Kyla Chasalow, Skyler Wu, Susan Murphy
Missing data in online reinforcement learning (RL) poses challenges compared to missing data in standard tabular data or in offline policy learning. The need to impute and act at e…
Stabilizing Linear Passive-Aggressive Online Learning with Weighted Reservoir Sampling
Skyler Wu, Fred Lu, Edward Raff +1
Online learning methods, like the seminal Passive-Aggressive (PA) classifier, are still highly effective for high-dimensional streaming data, out-of-core processing, and other thro…