English
Related papers

Related papers: Learning Compositional Neural Programs with Recurs…

200 papers

Approximate linear programming (ALP) represents one of the major algorithmic families to solve large-scale Markov decision processes (MDP). In this work, we study a primal-dual formulation of the ALP, and develop a scalable, model-free…

Machine Learning · Computer Science 2018-04-30 Yichen Chen , Lihong Li , Mengdi Wang

Tabular prediction traditionally relies on gradient-boosted decision trees and deep learning models, which excel in specific tasks but lack interpretability and transferability. Reasoning large language models (LLMs) promise cross-task…

Machine Learning · Computer Science 2026-03-11 Pengxiang Cai , Zihao Gao , Wanchen Lian , Jintai Chen

We study a multi-agent reinforcement learning (MARL) problem where the agents interact over a given network. The goal of the agents is to cooperatively maximize the average of their entropy-regularized long-term rewards. To overcome the…

Machine Learning · Computer Science 2022-12-01 Yizhou Zhang , Guannan Qu , Pan Xu , Yiheng Lin , Zaiwei Chen , Adam Wierman

Recently proposed neural architecture search (NAS) methods co-train billions of architectures in a supernet and estimate their potential accuracy using the network weights detached from the supernet. However, the ranking correlation between…

Computer Vision and Pattern Recognition · Computer Science 2021-08-24 Jiefeng Peng , Jiqi Zhang , Changlin Li , Guangrun Wang , Xiaodan Liang , Liang Lin

We study the problem of model-free reinforcement learning, which is often solved following the principle of Generalized Policy Iteration (GPI). While GPI is typically an interplay between policy evaluation and policy improvement, most…

Machine Learning · Computer Science 2023-02-28 Changnan Xiao , Haosen Shi , Jiajun Fan , Shihong Deng , Haiyan Yin

We introduce RIPE, an innovative reinforcement learning-based framework for weakly-supervised training of a keypoint extractor that excels in both detection and description tasks. In contrast to conventional training regimes that depend…

Computer Vision and Pattern Recognition · Computer Science 2025-07-15 Johannes Künzel , Anna Hilsmann , Peter Eisert

Inspired by the idea of Positive-incentive Noise (Pi-Noise or $\pi$-Noise) that aims at learning the reliable noise beneficial to tasks, we scientifically investigate the connection between contrastive learning and $\pi$-noise in this…

Machine Learning · Computer Science 2026-05-11 Hongyuan Zhang , Yanchen Xu , Sida Huang , Xuelong Li

Question Paraphrase Identification (QPI) is a critical task for large-scale Question-Answering forums. The purpose of QPI is to determine whether a given pair of questions are semantically identical or not. Previous approaches for this task…

Computation and Language · Computer Science 2021-09-07 Harsh Sakhrani , Saloni Parekh , Pratik Ratadiya

Compositional generalization refers to correctly interpret novel combinations of known primitives, which remains a major challenge. Existing approaches often rely on supervised fine-tuning, which encourages models to imitate target outputs.…

Machine Learning · Computer Science 2026-05-07 Xiyan Fu , Wei Liu

Replay is a powerful strategy to promote learning in artificial intelligence and the brain. However, the conditions to generate it and its functional advantages have not been fully recognized. In this study, we develop a modular…

Systems and Control · Electrical Eng. & Systems 2024-10-08 Jiyi Wang , Likai Tang , Huimiao Chen , Marcelo G Mattar , Sen Song

We introduce ASPiRe (Adaptive Skill Prior for RL), a new approach that leverages prior experience to accelerate reinforcement learning. Unlike existing methods that learn a single skill prior from a large and diverse dataset, our framework…

Machine Learning · Computer Science 2022-10-03 Mengda Xu , Manuela Veloso , Shuran Song

We propose a novel multi-layer neural network architecture that gives a promising neural network empowered optimization approach to the image restoration problem. The proposed architecture is motivated by the recent study of monotone…

Optimization and Control · Mathematics 2025-10-27 Haruya Shimizu , Masahiro Yukawa

Existing studies on disease diagnostic models focus either on diagnostic model learning for performance improvement or on the visual explanation of a trained diagnostic model. We propose a novel learn-explain-reinforce (LEAR) framework that…

Computer Vision and Pattern Recognition · Computer Science 2021-08-24 Kwanseok Oh , Jee Seok Yoon , Heung-Il Suk

Deep reinforcement learning agents have achieved state-of-the-art results by directly maximising cumulative reward. However, environments contain a much wider variety of possible training signals. In this paper, we introduce an agent that…

We introduce a mixed integer program (MIP) for assigning importance scores to each neuron in deep neural network architectures which is guided by the impact of their simultaneous pruning on the main learning task of the network. By…

Machine Learning · Computer Science 2023-07-26 Mostafa ElAraby , Guy Wolf , Margarida Carvalho

Deep reinforcement learning (DRL) has achieved significant breakthroughs in various tasks. However, most DRL algorithms suffer a problem of generalizing the learned policy which makes the learning performance largely affected even by minor…

Machine Learning · Computer Science 2019-07-11 Zhengyao Jiang , Shan Luo

Recently, several studies proposed methods to utilize some classes of optimization problems in designing deep neural networks to encode constraints that conventional layers cannot capture. However, these methods are still in their infancy…

Machine Learning · Computer Science 2020-06-16 Younghan Jeon , Minsik Lee , Jin Young Choi

A high-dimensional and incomplete (HDI) matrix frequently appears in various big-data-related applications, which demonstrates the inherently non-negative interactions among numerous nodes. A non-negative latent factor (NLF) model performs…

Machine Learning · Computer Science 2022-10-25 Ye Yuan , Xin Luo

We use reinforcement learning to learn tree-structured neural networks for computing representations of natural language sentences. In contrast with prior work on tree-structured models in which the trees are either provided as input or…

Computation and Language · Computer Science 2016-11-29 Dani Yogatama , Phil Blunsom , Chris Dyer , Edward Grefenstette , Wang Ling

The potential of reinforcement learning (RL) to deliver aligned and performant agents is partially bottlenecked by the reward engineering problem. One alternative to heuristic trial-and-error is preference-based RL (PbRL), where a reward…

Machine Learning · Computer Science 2021-12-22 Tom Bewley , Freddy Lecue
‹ Prev 1 3 4 5 6 7 10 Next ›