Search for: All records

Abstract Next-generation surveys like the Legacy Survey of Space and Time (LSST) on the Vera C. Rubin Observatory (Rubin) will generate orders of magnitude more discoveries of transients and variable stars than previous surveys. To prepare for this data deluge, we developed the Photometric LSST Astronomical Time-series Classification Challenge (PLAsTiCC), a competition that aimed to catalyze the development of robust classifiers under LSST-like conditions of a nonrepresentative training set for a large photometric test set of imbalanced classes. Over 1000 teams participated in PLAsTiCC, which was hosted in the Kaggle data science competition platform between 2018 September 28 and 2018 December 17, ultimately identifying three winners in 2019 February. Participants produced classifiers employing a diverse set of machine-learning techniques including hybrid combinations and ensemble averages of a range of approaches, among them boosted decision trees, neural networks, and multilayer perceptrons. The strong performance of the top three classifiers on Type Ia supernovae and kilonovae represent a major improvement over the current state of the art within astronomy. This paper summarizes the most promising methods and evaluates their results in detail, highlighting future directions both for classifier development and simulation needs for a next-generation PLAsTiCC data set. 

Motivated by the many real-world applications of reinforcement learning (RL) that require safe-policy iterations, we consider the problem of off-policy evaluation (OPE) — the problem of evaluating a new policy using the historical data ob- tained by different behavior policies — under the model of nonstationary episodic Markov Decision Processes (MDP) with a long horizon and a large action space. Existing importance sampling (IS) methods often suffer from large variance that depends exponentially on the RL horizon H. To solve this problem, we consider a marginalized importance sampling (MIS) estimator that recursively estimates the state marginal distribution for the target policy at every step. MIS achieves a mean-squared error of [ ] where μ and π are the logging and target policies, dμt (st) and dπt (st) are the marginal distribution of the state at tth step, H is the horizon, n is the sample size and V π is the value function of the MDP under π. The result matches the t+1 Cramer-Rao lower bound in Jiang and Li [2016] up to a multiplicative factor of H. To the best of our knowledge, this is the first OPE estimation error bound with a polynomial dependence on H . Besides theory, we show empirical superiority of our method in time-varying, partially observable, and long-horizon RL environments.