English
Related papers

Related papers: The Unintended Consequences of Discount Regulariza…

200 papers

This paper investigates the so-called reward-balancing methods, a novel class of algorithms for solving discounted-return reinforcement learning (RL) problems. These methods consist of iteratively adjusting the reward function to transform…

Optimization and Control · Mathematics 2026-04-23 Simone Baroncini , Bahman Gharesifard , Giuseppe Notarstefano

Dropout is a very effective way of regularizing neural networks. Stochastically "dropping out" units with a certain probability discourages over-specific co-adaptations of feature detectors, preventing overfitting and improving network…

Neural and Evolutionary Computing · Computer Science 2017-08-04 Pietro Morerio , Jacopo Cavazza , Riccardo Volpi , Rene Vidal , Vittorio Murino

The optimization of the variance supplemented by a budget constraint and an asymmetric $\ell_1$ regularizer is carried out analytically by the replica method borrowed from the theory of disordered systems. The asymmetric regularizer allows…

Portfolio Management · Quantitative Finance 2018-07-16 Imre Kondor , Gábor Papp , Fabio Caccioli

We present a new geometric interpretation of Markov Decision Processes (MDPs) with a natural normalization procedure that allows us to adjust the value function at each state without altering the advantage of any action with respect to any…

Machine Learning · Computer Science 2025-03-06 Arsenii Mustafin , Aleksei Pakharev , Alex Olshevsky , Ioannis Ch. Paschalidis

Deep neural networks suffer from catastrophic forgetting, where performance on previous tasks degrades after training on a new task. This issue arises due to the model's tendency to overwrite previously acquired knowledge with new…

Machine Learning · Computer Science 2025-12-02 Lama Alssum , Hasan Abed Al Kader Hammoud , Motasem Alfarra , Juan C Leon Alcazar , Bernard Ghanem

Off-policy evaluation often refers to two related tasks: estimating the expected return of a policy and estimating its value function (or other functions of interest, such as density ratios). While recent works on marginalized importance…

Machine Learning · Computer Science 2022-10-28 Audrey Huang , Nan Jiang

Policy gradient methods are among the most effective methods in challenging reinforcement learning problems with large state and/or action spaces. However, little is known about even their most basic theoretical convergence properties,…

Machine Learning · Computer Science 2020-10-16 Alekh Agarwal , Sham M. Kakade , Jason D. Lee , Gaurav Mahajan

This paper proposes a suite of rationality measures and associated theory for reinforcement learning agents, a property increasingly critical yet rarely explored. We define an action in deployment to be perfectly rational if it maximises…

Machine Learning · Computer Science 2026-05-05 Kejiang Qian , Amos Storkey , Fengxiang He

Neural language models are known to have a high capacity for memorization of training samples. This may have serious privacy implications when training models on user content such as email correspondence. Differential privacy (DP), a…

Deep neural networks with remarkably strong generalization performances are usually over-parameterized. Despite explicit regularization strategies are used for practitioners to avoid over-fitting, the impacts are often small. Some…

Computation and Language · Computer Science 2018-11-05 Deren Lei , Zichen Sun , Yijun Xiao , William Yang Wang

Autonomous systems are increasingly expected to operate in the presence of adversaries, though adversaries may infer sensitive information simply by observing a system. Therefore, present a deceptive sequential decision-making framework…

The goal of regression and classification methods in supervised learning is to minimize the empirical risk, that is, the expectation of some loss function quantifying the prediction error under the empirical distribution. When facing scarce…

Optimization and Control · Mathematics 2019-07-15 Soroosh Shafieezadeh-Abadeh , Daniel Kuhn , Peyman Mohajerin Esfahani

Algorithmic predictions are increasingly informing societal resource allocations by identifying individuals for targeting. Policymakers often build these systems with the assumption that by gathering more observations on individuals, they…

Machine Learning · Computer Science 2025-03-04 Ali Shirali , Ariel Procaccia , Rediet Abebe

We study the synthesis of a policy in a Markov decision process (MDP) following which an agent reaches a target state in the MDP while minimizing its total discounted cost. The problem combines a reachability criterion with a discounted…

Optimization and Control · Mathematics 2021-03-18 Yagiz Savas , Christos K. Verginis , Michael Hibbard , Ufuk Topcu

Regularization techniques are widely employed in optimization-based approaches for solving ill-posed inverse problems in data analysis and scientific computing. These methods are based on augmenting the objective with a penalty function,…

Optimization and Control · Mathematics 2021-06-08 Yong Sheng Soh , Venkat Chandrasekaran

Regularization aims to improve prediction performance of a given statistical modeling approach by moving to a second approach which achieves worse training error but is expected to have fewer degrees of freedom, i.e., better agreement…

Statistics Theory · Mathematics 2013-11-13 Shachar Kaufman , Saharon Rosset

Deep reinforcement learning algorithms that learn policies by trial-and-error must learn from limited amounts of data collected by actively interacting with the environment. While many prior works have shown that proper regularization…

Machine Learning · Computer Science 2023-04-21 Qiyang Li , Aviral Kumar , Ilya Kostrikov , Sergey Levine

The use of convex regularizers allows for easy optimization, though they often produce biased estimation and inferior prediction performance. Recently, nonconvex regularizers have attracted a lot of attention and outperformed convex ones.…

Optimization and Control · Mathematics 2017-02-14 Quanming Yao , James. T Kwok

Low-rank representation learning has emerged as a powerful tool for recovering missing values in power load data due to its ability to exploit the inherent low-dimensional structures of spatiotemporal measurements. Among various techniques,…

Machine Learning · Computer Science 2025-06-24 Yan Xia , Hao Feng , Hongwei Sun , Junjie Wang , Qicong Hu

We introduce the Blackwell discount factor for Markov Decision Processes (MDPs). Classical objectives for MDPs include discounted, average, and Blackwell optimality. Many existing approaches to computing average-optimal policies solve for…

Machine Learning · Computer Science 2024-07-04 Julien Grand-Clément , Marek Petrik