English
Related papers

Related papers: DR3: Value-Based Deep Reinforcement Learning Requi…

200 papers

Deep neural networks (DNNs) are the workhorses of deep learning, which constitutes the state of the art in numerous application domains. However, DNN-based decision rules are notoriously prone to poor generalization, i.e., may prove…

Machine Learning · Computer Science 2023-05-11 Guy Amir , Osher Maayan , Tom Zelazny , Guy Katz , Michael Schapira

While the Implicit Bias(or Implicit Regularization) of standard loss functions has been studied, the optimization geometry induced by discriminative metric-learning objectives remains largely unexplored.To the best of our knowledge, this…

Machine Learning · Computer Science 2026-04-13 Jiawen Li

Deep reinforcement learning (deep RL) has achieved superior performance in complex sequential tasks by using deep neural networks as function approximators to learn directly from raw input images. However, learning directly from raw images…

Machine Learning · Computer Science 2019-07-31 Gabriel V. de la Cruz , Yunshu Du , Matthew E. Taylor

Offline reinforcement learning (RL) aims to learn an effective policy from a static dataset. To alleviate extrapolation errors, existing studies often uniformly regularize the value function or policy updates across all states. However, due…

Machine Learning · Computer Science 2025-05-27 Qin-Wen Luo , Ming-Kun Xie , Ye-Wen Wang , Sheng-Jun Huang

Deep reinforcement learning (RL) has achieved breakthrough results on many tasks, but agents often fail to generalize beyond the environment they were trained in. As a result, deep RL algorithms that promote generalization are receiving…

Machine Learning · Computer Science 2019-03-18 Charles Packer , Katelyn Gao , Jernej Kos , Philipp Krähenbühl , Vladlen Koltun , Dawn Song

Implicit regularization is an important way to interpret neural networks. Recent theory starts to explain implicit regularization with the model of deep matrix factorization (DMF) and analyze the trajectory of discrete gradient dynamics in…

Machine Learning · Computer Science 2023-08-14 Jian Cao , Chen Qian , Yihui Huang , Dicheng Chen , Yuncheng Gao , Jiyang Dong , Di Guo , Xiaobo Qu

Adaptive gradient methods such as Adam have gained increasing popularity in deep learning optimization. However, it has been observed that compared with (stochastic) gradient descent, Adam can converge to a different solution with a…

Machine Learning · Computer Science 2021-08-26 Difan Zou , Yuan Cao , Yuanzhi Li , Quanquan Gu

In deep learning, it is common to use more network parameters than training points. In such scenarioof over-parameterization, there are usually multiple networks that achieve zero training error so that thetraining algorithm induces an…

Machine Learning · Computer Science 2023-08-22 Hung-Hsu Chou , Carsten Gieshoff , Johannes Maly , Holger Rauhut

We propose a novel regularizer to improve the training of Generative Adversarial Networks (GANs). The motivation is that when the discriminator D spreads out its model capacity in the right way, the learning signals given to the generator G…

Machine Learning · Computer Science 2018-05-11 Yanshuai Cao , Gavin Weiguang Ding , Kry Yik-Chau Lui , Ruitong Huang

In supervised learning, it is known that overparameterized neural networks with one hidden layer provably and efficiently learn and generalize, when trained using stochastic gradient descent with a sufficiently small learning rate and…

Machine Learning · Computer Science 2022-03-24 Kulin Shah , Amit Deshpande , Navin Goyal

We propose a novel distance-based regularization method for deep metric learning called Multi-level Distance Regularization (MDR). MDR explicitly disturbs a learning procedure by regularizing pairwise distances between embedding vectors…

Computer Vision and Pattern Recognition · Computer Science 2021-02-09 Yonghyun Kim , Wonpyo Park

Deep neural networks are learning models with a very high capacity and therefore prone to over-fitting. Many regularization techniques such as Dropout, DropConnect, and weight decay all attempt to solve the problem of over-fitting by…

Machine Learning · Computer Science 2016-12-06 Armen Aghajanyan

In this work, we present a simple yet theoretically motivated improvement to Supervised Fine-Tuning (SFT) for the Large Language Model (LLM), addressing its limited generalization compared to reinforcement learning (RL). Through…

Machine Learning · Computer Science 2026-03-02 Yongliang Wu , Yizhou Zhou , Zhou Ziheng , Yingzhe Peng , Xinyu Ye , Xinting Hu , Wenbo Zhu , Lu Qi , Ming-Hsuan Yang , Xu Yang

Deep reinforcement learning (DRL) has proven extremely useful in a large variety of application domains. However, even successful DRL-based software can exhibit highly undesirable behavior. This is due to DRL training being based on…

Machine Learning · Computer Science 2023-09-12 Ophir M. Carmel , Guy Katz

Deep reinforcement learning systems often suffer from unstable training dynamics due to non-stationarity, where learning objectives and data distributions evolve over time. We show that under non-stationary targets, isotropic Gaussian…

Machine Learning · Computer Science 2026-03-20 Ali Saheb Pasand , Johan Obando-Ceron , Aaron Courville , Pouya Bashivan , Pablo Samuel Castro

It is important to understand how dropout, a popular regularization method, aids in achieving a good generalization solution during neural network training. In this work, we present a theoretical derivation of an implicit regularization of…

Machine Learning · Computer Science 2023-04-11 Zhongwang Zhang , Zhi-Qin John Xu

The deep linear network (DLN) is a model for implicit regularization in gradient based optimization of overparametrized learning architectures. Training the DLN corresponds to a Riemannian gradient flow, where the Riemannian metric is…

Dynamical Systems · Mathematics 2023-05-12 Nadav Cohen , Govind Menon , Zsolt Veraszto

Value-based deep Reinforcement Learning (RL) algorithms suffer from the estimation bias primarily caused by function approximation and temporal difference (TD) learning. This problem induces faulty state-action value estimates and therefore…

Machine Learning · Computer Science 2021-11-15 Dogan C. Cicek , Enes Duran , Baturay Saglam , Kagan Kaya , Furkan B. Mutlu , Suleyman S. Kozat

World models have recently emerged as a promising approach to reinforcement learning (RL), achieving state-of-the-art performance across a wide range of visual control tasks. This work aims to obtain a deep understanding of the robustness…

Machine Learning · Computer Science 2025-01-03 Qiaoyi Fang , Weiyu Du , Hang Wang , Junshan Zhang

Deep learning (DL) has emerged as a tool for improving accelerated MRI reconstruction. A common strategy among DL methods is the physics-based approach, where a regularized iterative algorithm alternating between data consistency and a…

Image and Video Processing · Electrical Eng. & Systems 2020-07-03 Burhaneddin Yaman , Seyed Amir Hossein Hosseini , Steen Moeller , Jutta Ellermann , Kâmil Uǧurbil , Mehmet Akçakaya