English
Related papers

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

200 papers

In this paper, we analyze several methods for approximating gradients of noisy functions using only function values. These methods include finite differences, linear interpolation, Gaussian smoothing and smoothing on a sphere. The methods…

Optimization and Control · Mathematics 2021-03-29 Albert S. Berahas , Liyuan Cao , Krzysztof Choromanski , Katya Scheinberg

When to solve math problems, most language models take a sampling strategy to predict next word according conditional probabilities. In the math reasoning step, it may generate wrong answer. Considering math problems are deterministic, we…

Computation and Language · Computer Science 2023-07-19 Gang Chen

Stochastic gradient methods for machine learning and optimization problems are usually analyzed assuming data points are sampled \emph{with} replacement. In practice, however, sampling \emph{without} replacement is very common, easier to…

Machine Learning · Computer Science 2016-10-18 Ohad Shamir

We consider a sequential decision making task where we are not allowed to evaluate parameters that violate an a priori unknown (safety) constraint. A common approach is to place a Gaussian process prior on the unknown constraint and allow…

Machine Learning · Computer Science 2022-12-12 Alessandro G. Bottero , Carlos E. Luis , Julia Vinogradska , Felix Berkenkamp , Jan Peters

Model-free reinforcement learning methods such as the Proximal Policy Optimization algorithm (PPO) have successfully applied in complex decision-making problems such as Atari games. However, these methods suffer from high variances and high…

Machine Learning · Computer Science 2018-11-20 Feiyang Pan , Qingpeng Cai , An-Xiang Zeng , Chun-Xiang Pan , Qing Da , Hualin He , Qing He , Pingzhong Tang

Resolving the exploration-exploitation trade-off remains a fundamental problem in the design and implementation of reinforcement learning (RL) algorithms. In this paper, we focus on model-free RL using the epsilon-greedy exploration policy,…

Machine Learning · Computer Science 2020-07-03 Michael Gimelfarb , Scott Sanner , Chi-Guhn Lee

In this paper, we present algorithms that perform gradient ascent of the average reward in a partially observable Markov decision process (POMDP). These algorithms are based on GPOMDP, an algorithm introduced in a companion paper (Baxter…

Artificial Intelligence · Computer Science 2019-11-18 J. Baxter , P. L. Bartlett , L. Weaver

While experimental design often focuses on selecting the single best alternative from a finite set (e.g., in ranking and selection or best-arm identification), many pure-exploration problems pursue richer goals. Given a specific goal,…

Machine Learning · Statistics 2025-05-28 Chao Qin , Wei You

In this paper we explore methods to exploit symmetries for ensuring sample efficiency in reinforcement learning (RL), this problem deserves ever increasing attention with the recent advances in the use of deep networks for complex RL tasks…

Machine Learning · Statistics 2017-06-12 Anuj Mahajan , Theja Tulabandhula

We recently introduced a scale of kernel-based greedy schemes for approximating the solutions of elliptic boundary value problems. The procedure is based on a generalized interpolation framework in reproducing kernel Hilbert spaces and was…

Numerical Analysis · Mathematics 2025-07-10 Bernard Haasdonk , Gabriele Santin , Tizian Wenzel

Imitation learning has enabled robots to perform complex, long-horizon tasks in challenging dexterous manipulation settings. As new methods are developed, they must be rigorously evaluated and compared against corresponding baselines…

Balancing exploration and exploitation is a fundamental part of reinforcement learning, yet most state-of-the-art algorithms use a naive exploration protocol like $\epsilon$-greedy. This contributes to the problem of high sample complexity,…

Machine Learning · Computer Science 2019-11-21 Tom Blau , Lionel Ott , Fabio Ramos

Machine learning models, and deep neural networks in particular, are increasingly deployed in risk-sensitive domains such as healthcare, environmental forecasting, and finance, where reliable quantification of predictive uncertainty is…

Machine Learning · Computer Science 2026-04-07 Asena Karolin Özdemir , Lars H. Heyen , Arvid Weyrauch , Achim Streit , Markus Götz , Charlotte Debus

Many machine learning tasks require sampling a subset of items from a collection based on a parameterized distribution. The Gumbel-softmax trick can be used to sample a single item, and allows for low-variance reparameterized gradients with…

Machine Learning · Computer Science 2021-03-02 Sang Michael Xie , Stefano Ermon

We consider a sequential decision making task, where the goal is to optimize an unknown function without evaluating parameters that violate an a~priori unknown (safety) constraint. A common approach is to place a Gaussian process prior on…

Machine Learning · Computer Science 2024-05-13 Alessandro G. Bottero , Carlos E. Luis , Julia Vinogradska , Felix Berkenkamp , Jan Peters

Reinforcement learning with evaluation metrics as rewards is widely used to enhance specific capabilities of language models. However, for tasks such as factually consistent summarisation, existing metrics remain underdeveloped, limiting…

Computation and Language · Computer Science 2026-05-27 Yuxuan Ye , Raul Santos-Rodriguez , Edwin Simpson

Policy gradient (PG) estimation becomes a challenge when we are not allowed to sample with the target policy but only have access to a dataset generated by some unknown behavior policy. Conventional methods for off-policy PG estimation…

Machine Learning · Statistics 2022-06-22 Chengzhuo Ni , Ruiqi Zhang , Xiang Ji , Xuezhou Zhang , Mengdi Wang

Ordinary differential equations (ODEs) are commonly used to model dynamic behavior of a system. Because many parameters are unknown and have to be estimated from the observed data, there is growing interest in statistics to develop…

Statistics Theory · Mathematics 2010-01-13 Xin Qi , Hongyu Zhao

Exploration is a key challenge in Reinforcement Learning, especially in long-horizon, deceptive and sparse-reward environments. For such applications, population-based approaches have proven effective. Methods such as Quality-Diversity…

Neural and Evolutionary Computing · Computer Science 2022-11-24 Bryan Lim , Manon Flageat , Antoine Cully

A new method of deriving comparative statics information using generalized compensated derivatives is presented which yields constraint-free semidefiniteness results for any differentiable, constrained optimization problem. More generally,…

Optimization and Control · Mathematics 2013-10-29 M. Hossein Partovi , Michael R. Caputo