English
Related papers

Related papers: Deep Metric Tensor Regularized Policy Gradient

200 papers

In this paper, we develop a novel regularization method for deep neural networks by penalizing the trace of Hessian. This regularizer is motivated by a recent guarantee bound of the generalization error. We explain its benefits in finding…

Machine Learning · Computer Science 2023-02-23 Yucong Liu , Shixing Yu , Tong Lin

The trace norm is widely used in multi-task learning as it can discover low-rank structures among tasks in terms of model parameters. Nowadays, with the emerging of big datasets and the popularity of deep learning techniques, tensor trace…

Machine Learning · Computer Science 2020-02-13 Yi Zhang , Yu Zhang , Wei Wang

We investigate the challenge of parametrizing policies for reinforcement learning (RL) in high-dimensional continuous action spaces. Our objective is to develop a multimodal policy that overcomes limitations inherent in the commonly-used…

Machine Learning · Computer Science 2023-07-21 Zhiao Huang , Litian Liang , Zhan Ling , Xuanlin Li , Chuang Gan , Hao Su

Understanding how systems built out of modular components can be jointly optimized is an important problem in biology, engineering, and machine learning. The backpropagation algorithm is one such solution and has been instrumental in the…

Machine Learning · Computer Science 2026-03-05 Christian Pehle , Jean-Jacques Slotine

Policy gradient methods are among the most effective methods for large-scale reinforcement learning, and their empirical success has prompted several works that develop the foundation of their global convergence theory. However, prior works…

Machine Learning · Computer Science 2020-12-25 Junzi Zhang , Jongho Kim , Brendan O'Donoghue , Stephen Boyd

The adaptive cubic regularization algorithm employing the inexact gradient and Hessian is proposed on general Riemannian manifolds, together with the iteration complexity to get an approximate second-order optimality under certain…

Optimization and Control · Mathematics 2024-05-07 Z. Y. Li , X. M. Wang

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

Backpropagation, the cornerstone of deep learning, is limited to computing gradients for continuous variables. This limitation poses challenges for problems involving discrete latent variables. To address this issue, we propose a novel…

Machine Learning · Computer Science 2023-10-17 Liyuan Liu , Chengyu Dong , Xiaodong Liu , Bin Yu , Jianfeng Gao

Recently, the impressive empirical success of policy gradient (PG) methods has catalyzed the development of their theoretical foundations. Despite the huge efforts directed at the design of efficient stochastic PG-type algorithms, the…

Machine Learning · Computer Science 2023-11-09 Ilyas Fatkhullin , Anas Barakat , Anastasia Kireeva , Niao He

In this paper we propose a novel gradient algorithm to learn a policy from an expert's observed behavior assuming that the expert behaves optimally with respect to some unknown reward function of a Markovian Decision Problem. The…

Machine Learning · Computer Science 2012-06-26 Gergely Neu , Csaba Szepesvari

Deep Neural Networks and Reinforcement Learning methods have empirically shown great promise in tackling challenging combinatorial problems. In those methods a deep neural network is used as a solution generator which is then trained by…

Machine Learning · Computer Science 2023-11-08 Constantine Caramanis , Dimitris Fotakis , Alkis Kalavasis , Vasilis Kontonis , Christos Tzamos

Despite its recent successes, Deep Reinforcement Learning (DRL) is notoriously sample-inefficient. We argue that this inefficiency stems from the standard practice of optimizing policies directly in the high-dimensional and highly redundant…

Machine Learning · Computer Science 2026-02-25 Davide Tenedini , Riccardo Zamboni , Mirco Mutti , Marcello Restelli

We argue that inventory management presents unique opportunities for the reliable application of deep reinforcement learning (DRL). To enable this, we emphasize and test two complementary techniques. The first is Hindsight Differentiable…

Machine Learning · Computer Science 2025-09-12 Matias Alvo , Daniel Russo , Yash Kanoria , Minuk Lee

We present an end-to-end algorithm for training deep neural networks to grasp novel objects. Our algorithm builds all the essential components of a grasping system using a forward-backward automatic differentiation approach, including the…

Robotics · Computer Science 2020-07-16 Min Liu , Zherong Pan , Kai Xu , Kanishka Ganguly , Dinesh Manocha

Upside Down Reinforcement Learning (UDRL) is a promising framework for solving reinforcement learning problems which focuses on learning command-conditioned policies. In this work, we extend UDRL to the task of learning a…

Machine Learning · Computer Science 2025-01-29 Jacopo Di Ventura , Dylan R. Ashley , Vincent Herrmann , Francesco Faccio , Jürgen Schmidhuber

The high-dimensional parameter space of deep neural networks -- the neuromanifold -- is endowed with a unique metric tensor defined by the Fisher information. Reliable and scalable computation of this metric tensor is valuable for theorists…

Machine Learning · Computer Science 2026-03-04 Ke Sun

This paper investigates efficient deep neural networks (DNNs) to replace dense unstructured weight matrices with structured ones that possess desired properties. The challenge arises because the optimal weight matrix structure in popular…

Machine Learning · Computer Science 2024-03-11 Changwoo Lee , Hun-Seok Kim

Deep Deterministic Policy Gradient (DDPG) algorithm is one of the most well-known reinforcement learning methods. However, this method is inefficient and unstable in practical applications. On the other hand, the bias and variance of the Q…

Machine Learning · Computer Science 2020-07-02 Shuai Han , Wenbo Zhou , Shuai Lü , Jiayu Yu

Deep learning classifiers face significant challenges when dealing with heterogeneous multi-modal and multi-organ biomedical datasets. The low-level feature distinguishability limited to imaging-modality hinders the classifiers' ability to…

Image and Video Processing · Electrical Eng. & Systems 2025-02-04 Mehmet Can Yavuz , Yang Yang

Deep distance metric learning (DDML), which is proposed to learn image similarity metrics in an end-to-end manner based on the convolution neural network, has achieved encouraging results in many computer vision tasks.$L2$-normalization in…

Computer Vision and Pattern Recognition · Computer Science 2018-03-29 Xuefei Zhe , Shifeng Chen , Hong Yan
‹ Prev 1 3 4 5 6 7 10 Next ›