English
Related papers

Related papers: Efficient Baseline-free Sampling in Parameter Expl…

200 papers

Gibbs sampling is a workhorse for Bayesian inference but has several limitations when used for parameter estimation, and is often much slower than non-sampling inference methods. SAME (State Augmentation for Marginal Estimation)…

Machine Learning · Computer Science 2014-09-19 Huasha Zhao , Biye Jiang , John Canny

The problem of binary hypothesis testing between two probability measures is considered. New sharp bounds are derived for the best achievable error probability of such tests based on independent and identically distributed observations.…

Information Theory · Computer Science 2024-05-30 Valentinian Lungu , Ioannis Kontoyiannis

Policy gradient methods, which have been extensively studied in the last decade, offer an effective and efficient framework for reinforcement learning problems. However, their performances can often be unsatisfactory, suffering from…

Machine Learning · Computer Science 2026-01-27 Shihab Ahmed , El Houcine Bergou , Aritra Dutta , Yue Wang

Pure exploration (aka active testing) is the fundamental task of sequentially gathering information to answer a query about a stochastic environment. Good algorithms make few mistakes and take few samples. Lower bounds (for multi-armed…

Machine Learning · Statistics 2019-06-26 Rémy Degenne , Wouter M. Koolen , Pierre Ménard

In certain situations that shall be undoubtedly more and more common in the Big Data era, the datasets available are so massive that computing statistics over the full sample is hardly feasible, if not unfeasible. A natural approach in this…

Machine Learning · Statistics 2015-01-12 Stéphan Clémençon , Patrice Bertail , Emilie Chautru , Guillaume Papa

Classical two-sample permutation tests for equality of distributions have exact size in finite samples, but they fail to control size for testing equality of parameters that summarize each distribution. This paper proposes permutation tests…

Econometrics · Economics 2022-04-22 Marinho Bertanha , EunYi Chung

In many real-world scenarios, reward signal for agents are exceedingly sparse, making it challenging to learn an effective reward function for reward shaping. To address this issue, the proposed approach in this paper performs reward…

Machine Learning · Computer Science 2026-05-18 Wenyun Li , Wenjie Huang , Chen Sun

Policy gradient methods can solve complex tasks but often fail when the dimensionality of the action-space or objective multiplicity grow very large. This occurs, in part, because the variance on score-based gradient estimators scales…

Machine Learning · Computer Science 2021-11-24 Thomas Spooner , Nelson Vadori , Sumitra Ganesh

This paper proposes an exploration method for deep reinforcement learning based on parameter space noise. Recent studies have experimentally shown that parameter space noise results in better exploration than the commonly used action space…

Machine Learning · Statistics 2018-09-28 Izumi Karino , Kazutoshi Tanaka , Ryuma Niiyama , Yasuo Kuniyoshi

We develop a method for policy architecture search and adaptation via gradient-free optimization which can learn to perform autonomous driving tasks. By learning from both demonstration and environmental reward we develop a model that can…

Machine Learning · Computer Science 2017-10-18 Sayna Ebrahimi , Anna Rohrbach , Trevor Darrell

Direct optimization is an appealing framework that replaces integration with optimization of a random objective for approximating gradients in models with discrete random variables. A$^\star$ sampling is a framework for optimizing such…

Machine Learning · Computer Science 2020-10-26 Guy Lorberbom , Chris J. Maddison , Nicolas Heess , Tamir Hazan , Daniel Tarlow

We propose a new class of semiparametric exponential family graphical models for the analysis of high dimensional mixed data. Different from the existing mixed graphical models, we allow the nodewise conditional distributions to be…

Machine Learning · Statistics 2015-10-16 Zhuoran Yang , Yang Ning , Han Liu

Sampling from multimodal distributions is a challenging task in scientific computing. When a distribution has an exact symmetry between the modes, direct jumps among them can accelerate the samplings significantly. However, the…

Numerical Analysis · Mathematics 2024-01-05 Lexing Ying

This paper considers the problem of efficient exploration of unseen environments, a key challenge in AI. We propose a `learning to explore' framework where we learn a policy from a distribution of environments. At test time, presented with…

Machine Learning · Computer Science 2019-10-30 Hanjun Dai , Yujia Li , Chenglong Wang , Rishabh Singh , Po-Sen Huang , Pushmeet Kohli

Policy gradient methods in reinforcement learning have become increasingly prevalent for state-of-the-art performance in continuous control tasks. Novel methods typically benchmark against a few key algorithms such as deep deterministic…

Machine Learning · Computer Science 2017-08-15 Riashat Islam , Peter Henderson , Maziar Gomrokchi , Doina Precup

Traditional nonparametric estimation methods often lead to a slow convergence rate in large dimensions and require unrealistically enormous sizes of datasets for reliable conclusions. We develop an approach based on partial derivatives,…

Methodology · Statistics 2024-08-20 Xiaowu Dai

We explore how much knowing a parametric restriction on propensity scores improves semiparametric efficiency bounds in the potential outcome framework. For stratified propensity scores, considered as a parametric model, we derive explicit…

Econometrics · Economics 2024-07-04 Haruki Kono

Statistical inference in parametric models (e.g., the Bradley--Terry model and its variants) for paired-comparison data has been explored in the high-dimensional regime, in which the number of items involving in paired comparisons diverges.…

Methodology · Statistics 2026-04-01 Haoyue Song , Lianqiang Qu , Ting Yan , Yuguo Chen

Exploration is a fundamental problem in robotics. While sampling-based planners have shown high performance, they are oftentimes compute intensive and can exhibit high variance. To this end, we propose to directly learn the underlying…

Robotics · Computer Science 2022-07-15 Lukas Schmid , Chao Ni , Yuliang Zhong , Roland Siegwart , Olov Andersson

Most bandit policies are designed to either minimize regret in any problem instance, making very few assumptions about the underlying environment, or in a Bayesian sense, assuming a prior distribution over environment parameters. The former…

Machine Learning · Computer Science 2021-01-07 Branislav Kveton , Martin Mladenov , Chih-Wei Hsu , Manzil Zaheer , Csaba Szepesvari , Craig Boutilier
‹ Prev 1 3 4 5 6 7 10 Next ›