More Like this

1. Minimax Model Learning

   Voloshin, C; Jiang, N; Yue, YS (January 2021, 24TH INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND STATISTICS (AISTATS))

   Banerjee, A; Fukumizu, K (Ed.)

   We present a novel off-policy loss function for learning a transition model in model-based reinforcement learning. Notably, our loss is derived from the off-policy policy evaluation objective with an emphasis on correcting distribution shift. Compared to previous model-based techniques, our approach allows for greater robustness under model mis-specification or distribution shift induced by learning/evaluating policies that are distinct from the data-generating policy. We provide a theoretical analysis and show empirical improvements over existing model-based off-policy evaluation methods. We provide further analysis showing our loss can be used for off-policy optimization (OPO) and demonstrate its integration with more recent improvements in OPO. 

   more » « less
2. Minimax Rate-Distortion

   https://doi.org/10.1109/TIT.2023.3328532  

   Mahmood, Adeel; Wagner, Aaron B (December 2023, IEEE Transactions on Information Theory)
3. Minimax-Optimal Location Estimation

   Shivam Gupta, Jasper Lee (December 2023, Thirty-seventh Conference on Neural Information Processing Systems)

   Location estimation is one of the most basic questions in parametric statistics. Suppose we have a known distribution density f , and we get n i.i.d. samples from f (x − μ) for some unknown shift μ. The task is to estimate μ to high accuracy with high probability. The maximum likelihood estimator (MLE) is known to be asymptotically optimal as n → ∞, but what is possible for finite n? In this paper, we give two location estimators that are optimal under different criteria: 1) an estimator that has minimax-optimal estimation error subject to succeeding with probability 1 − ¶ and 2) a confidence interval estimator which, subject to its output interval containing μ with probability at least 1 − ¶, has the minimum expected squared interval width among all shift-invariant estimators. The latter construction can be generalized to minimizing the expectation of any loss function on the interval width. 

   more » « less
4. Minimax-Optimal Location Estimation

   Gupta, Shivam; Lee, Jasper CH; Price, Eric; Valiant, Paul (December 2023, NeurIPS 2023)

   Location estimation is one of the most basic questions in parametric statistics. Suppose we have a known distribution density f, and we get n i.i.d. samples from f(x − µ) for some unknown shift µ. The task is to estimate µ to high accuracy with high probability. The maximum likelihood estimator (MLE) is known to be asymptotically optimal as n → ∞, but what is possible for finite n? In this paper, we give two location estimators that are optimal under different criteria: 1) an estimator that has minimax-optimal estimation error subject to succeeding with probability 1 − δ and 2) a confidence interval estimator which, subject to its output interval containing µ with probability at least 1 − δ, has the minimum expected squared interval width among all shift-invariant estimators. The latter construction can be generalized to minimizing the expectation of any loss function on the interval width. 

   more » « less
5. Minimax Nonparametric Parallelism Test

   Xing, Xin; Liu, Meimei; Ma, Ping; Zhong, Wenxuan (May 2020, Journal of machine learning research)

   null (Ed.)