English
Related papers

Related papers: Learning Representations in Reinforcement Learning…

200 papers

The theory of reinforcement learning has focused on two fundamental problems: achieving low regret, and identifying $\epsilon$-optimal policies. While a simple reduction allows one to apply a low-regret algorithm to obtain an…

Machine Learning · Computer Science 2022-06-23 Andrew Wagenmaker , Max Simchowitz , Kevin Jamieson

We provide in this paper a concrete method for training a quantum neural network to maximize the relevant information about a property that is transmitted through the network. This is significant because it gives an operationally well…

Quantum Physics · Physics 2024-01-23 Ahmet Burak Catli , Nathan Wiebe

Keyframe selection has become essential for video understanding with vision-language models (VLMs) due to limited input tokens and the temporal sparsity of relevant information across video frames. Video understanding often relies on…

Computer Vision and Pattern Recognition · Computer Science 2025-11-18 Yuan Zhou , Litao Hua , Shilong Jin , Wentao Huang , Haoran Duan

Mutual Information (MI) plays an important role in representation learning. However, MI is unfortunately intractable in continuous and high-dimensional settings. Recent advances establish tractable and scalable MI estimators to discover…

Machine Learning · Statistics 2020-05-05 Liangjian Wen , Yiji Zhou , Lirong He , Mingyuan Zhou , Zenglin Xu

Branch-and-bound is a systematic enumerative method for combinatorial optimization, where the performance highly relies on the variable selection strategy. State-of-the-art handcrafted heuristic strategies suffer from relatively slow…

Machine Learning · Computer Science 2022-06-15 Tianyu Zhang , Amin Banitalebi-Dehkordi , Yong Zhang

The Information Bottleneck (IB) method frequently suffers from unstable optimization, characterized by abrupt representation shifts near critical points of the IB trade-off parameter, beta. In this paper, I introduce a novel approach to…

Machine Learning · Computer Science 2025-05-15 Faruk Alpay

Deep learning models are nowadays broadly deployed to solve an incredibly large variety of tasks. Commonly, leveraging over the availability of "big data", deep neural networks are trained as black-boxes, minimizing an objective function at…

Machine Learning · Computer Science 2022-10-04 Enzo Tartaglione

Deep reinforcement learning (RL) algorithms suffer severe performance degradation when the interaction data is scarce, which limits their real-world application. Recently, visual representation learning has been shown to be effective and…

Machine Learning · Computer Science 2022-08-17 Yang Yue , Bingyi Kang , Zhongwen Xu , Gao Huang , Shuicheng Yan

Information Bottleneck (IB) is a technique to extract information about one target random variable through another relevant random variable. This technique has garnered significant interest due to its broad applications in information…

Information Theory · Computer Science 2024-04-09 Lingyi Chen , Shitong Wu , Jiachuan Ye , Huihui Wu , Wenyi Zhang , Hao Wu

In this paper, we frame homogeneous-feature multi-task learning (MTL) as a hierarchical representation learning problem, with one task-agnostic and multiple task-specific latent representations. Drawing inspiration from the information…

Machine Learning · Computer Science 2022-10-04 João Machado de Freitas , Sebastian Berg , Bernhard C. Geiger , Manfred Mücke

Maintaining efficient semantic representations of the environment is a major challenge both for humans and for machines. While human languages represent useful solutions to this problem, it is not yet clear what computational principle…

Computation and Language · Computer Science 2018-08-13 Noga Zaslavsky , Charles Kemp , Terry Regier , Naftali Tishby

We study the problem of inverse reinforcement learning (IRL), where the learning agent recovers a reward function using expert demonstrations. Most of the existing IRL techniques make the often unrealistic assumption that the agent has…

Machine Learning · Computer Science 2021-12-20 Franck Djeumou , Murat Cubuktepe , Craig Lennon , Ufuk Topcu

Invariant risk minimization (IRM) has recently emerged as a promising alternative for domain generalization. Nevertheless, the loss function is difficult to optimize for nonlinear classifiers and the original optimization objective could…

Machine Learning · Computer Science 2022-03-22 Bo Li , Yifei Shen , Yezhen Wang , Wenzhen Zhu , Colorado J. Reed , Jun Zhang , Dongsheng Li , Kurt Keutzer , Han Zhao

In distributed optimization, the practical problem-solving performance is essentially sensitive to algorithm selection, parameter setting, problem type and data pattern. Thus, it is often laborious to acquire a highly efficient method for a…

Optimization and Control · Mathematics 2024-01-04 Daokuan Zhu , Tianqi Xu , Jie Lu

We develop a portfolio allocation framework that leverages deep learning techniques to address challenges arising from high-dimensional, non-stationary, and low-signal-to-noise market information. Our approach includes a dynamic embedding…

Portfolio Management · Quantitative Finance 2025-01-31 Jinghai He , Cheng Hua , Chunyang Zhou , Zeyu Zheng

Artificial neural networks have successfully tackled a large variety of problems by training extremely deep networks via back-propagation. A direct application of back-propagation to spiking neural networks contains biologically implausible…

Neural and Evolutionary Computing · Computer Science 2021-11-29 Kyle Daruwalla , Mikko Lipasti

We study how to effectively leverage expert feedback to learn sequential decision-making policies. We focus on problems with sparse rewards and long time horizons, which typically pose significant challenges in reinforcement learning. We…

Machine Learning · Computer Science 2018-06-12 Hoang M. Le , Nan Jiang , Alekh Agarwal , Miroslav Dudík , Yisong Yue , Hal Daumé

We study the design of sample-efficient algorithms for reinforcement learning in the presence of rich, high-dimensional observations, formalized via the Block MDP problem. Existing algorithms suffer from either 1) computational…

Machine Learning · Computer Science 2023-04-13 Zakaria Mhammedi , Dylan J. Foster , Alexander Rakhlin

Information Bottleneck (IB) is a widely used framework that enables the extraction of information related to a target random variable from a source random variable. In the objective function, IB controls the trade-off between data…

Machine Learning · Computer Science 2025-08-13 Sota Kudo , Naoaki Ono , Shigehiko Kanaya , Ming Huang

Coordination graphs are a central abstraction in cooperative multi-agent reinforcement learning (MARL), yet existing sparse-graph learners lack a theoretically grounded mechanism to decide which edges should exist and how much information…

Artificial Intelligence · Computer Science 2026-05-19 Wei Duan , Junyu Xuan , En Yu , Xiaoyu Yang , Jie Lu
‹ Prev 1 8 9 10 Next ›