Modern quantum machine learning (QML) methods involve variationally optimizing a parameterized quantum circuit on a training data set, and subsequently making predictions on a testing data set (i.e., generalizing). In this work, we provide a comprehensive study of generalization performance in QML ...
This paper introduces a novel measure-theoretic theory for machine learning that does not require statistical assumptions. Based on this theory, a new regularization method in deep learning is derived and shown to outperform previous methods in CIFAR-10, CIFAR-100, and SVHN. Moreover, the proposed...
Bengio, Emmanuel, Joelle Pineau, and Doina Precup. "Interference and generalization in temporal difference learning." International Conference on Machine Learning. PMLR, 2020. 特色 本文的一大特色就是 Bengio 大佬写的英语实在看不懂(误)。这篇文章给了很多实验和理论上的线索,来探究强化学习里面的 interfere...
Raileanu, Roberta, and Rob Fergus. "Decoupling value and policy for generalization in reinforcement learning."International Conference on Machine Learning. PMLR, 2021. 提出了一种面向泛化的 actor-critic 类算法。该算法 1)把价值函数网络和策略网络分开训练;2)使用鼓励表示学习和具体任务无关的特征的辅助任务。
Advances in machine learning and artificial intelligence have begun to approximate and even surpass human performance, but machine systems reliably struggle to generalize information to untrained situations. We describe a neural network model that is trained to play one video game (Breakout) and ...
This thesis addresses several problems related to generalization in machine learning systems. We introduce a theoretical framework for studying learning and generalization. Within this framework, a closed form is derived for the expected generalization error that estimates the out-of-sample performance in...
In statistics and machine learning, overfitting occurs when a statistical model describes random error or noise instead of the underlying relationship. “Overfitting” is when a classifier fits the training data too tightly. Such a classifier works well on the training data but not on independent ...
machine learning1,2. For some, generalization is crucial to ensure that models behave robustly, reliably and fairly when making predictions about data different from the data on which they were trained, which is of critical importance when models are employed in the real world. Others see good ...
传统machine learning 中人们就常用各种正则项来抑制过拟合,最典型的应该是 L2 正则,而近些年 RL 领域中也有若干 paper 研究正则项的影响,比如今年 ICLR Regularization Matters in Policy Optimization[7]作者称 L2 可以起到比 entropy regularization 更好的效果,DL 里常用的 dropout 可以为 off-policy 训练带来一些...
A Dissection of Overfitting and Generalization in Continuous Reinforcement Learning The risks and perils of overfitting in machine learning are well known. However most of the treatment of this, including diagnostic tools and remedies, was developed for the supervised learning case. In this work, we...