Machine Learning

Authors and titles for February 2025

[1] arXiv:2502.00021 (cross-list from cs.LG) [cn-pdf, pdf, html, other]

Title: PixelBrax: Learning Continuous Control from Pixels End-to-End on the GPU Show Chinese title

Title: PixelBrax：基于GPU从像素端到端学习连续控制

Trevor McInroe, Samuel Garcin

Subjects: Machine Learning (cs.LG) ; Performance (cs.PF)

[2] arXiv:2502.00025 (cross-list from cs.LG) [cn-pdf, pdf, other]

Title: Explainable AI for Mental Health Emergency Returns: Integrating LLMs with Predictive Modeling Show Chinese title

Title: 可解释的人工智能用于心理健康紧急情况返回：将大型语言模型与预测建模相结合

Abdulaziz Ahmed, Mohammad Saleem, Mohammed Alzeen, Badari Birur, Rachel E Fargason, Bradley G Burk, Ahmed Alhassan, Mohammed Ali Al-Garadi

Subjects: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI) ; Computers and Society (cs.CY)

[3] arXiv:2502.00036 (cross-list from cs.LG) [cn-pdf, pdf, html, other]

Title: Efficient Client Selection in Federated Learning Show Chinese title

Title: 联邦学习中的高效客户端选择

William Marfo, Deepak K. Tosh, Shirley V. Moore

Subjects: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI) ; Distributed, Parallel, and Cluster Computing (cs.DC)

[4] arXiv:2502.00040 (cross-list from cs.LG) [cn-pdf, pdf, html, other]

Title: Multi-Objective Reinforcement Learning for Power Grid Topology Control Show Chinese title

Title: 多目标强化学习在电力网络拓扑控制中的应用

Thomas Lautenbacher, Ali Rajaei, Davide Barbieri, Jan Viebahn, Jochen L. Cremer

Subjects: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI) ; Systems and Control (eess.SY)

[5] arXiv:2502.00045 (cross-list from cs.LG) [cn-pdf, pdf, html, other]

Title: Restless Multi-armed Bandits under Frequency and Window Constraints for Public Service Inspections Show Chinese title

Title: 公共服务检查下的频率和窗口约束的不安分多臂老虎机问题

Yi Mao, Andrew Perrault

Subjects: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI) ; Computational Engineering, Finance, and Science (cs.CE) ; Computers and Society (cs.CY)

[6] arXiv:2502.00046 (cross-list from cs.LG) [cn-pdf, pdf, html, other]

Title: Optimization Strategies for Enhancing Resource Efficiency in Transformers & Large Language Models Show Chinese title

Title: 提升变压器与大型语言模型资源效率的优化策略

Tom Wallace, Naser Ezzati-Jivan, Beatrice Ombuki-Berman

Comments: Accepted for ACM's ICPE 2025 in Short Paper format

Subjects: Machine Learning (cs.LG) ; Computation and Language (cs.CL)

[7] arXiv:2502.00047 (cross-list from cs.LG) [cn-pdf, pdf, other]

Title: HadamRNN: Binary and Sparse Ternary Orthogonal RNNs Show Chinese title

Title: HadamRNN：二元和稀疏三元正交循环神经网络（RNNs）

Armand Foucault (IMT, ANITI), Franck Mamalet (ANITI), François Malgouyres (IMT)

Journal-ref: International Conference on Learning Representations (ICLR), Apr 2025, Singapour, Singapore

Subjects: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI)

[8] arXiv:2502.00048 (cross-list from cs.LG) [cn-pdf, pdf, other]

Title: Contextually Entangled Gradient Mapping for Optimized LLM Comprehension Show Chinese title

Title: 上下文纠缠梯度映射用于优化LLM理解

Colin Sisate, Alistair Goldfinch, Vincent Waterstone, Sebastian Kingsley, Mariana Blackthorn

Comments: arXiv admin note: This paper has been withdrawn by arXiv due to disputed and unverifiable authorship

Subjects: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL)

[9] arXiv:2502.00052 (cross-list from cs.LG) [cn-pdf, pdf, other]

Title: Bridging Contrastive Learning and Domain Adaptation: Theoretical Perspective and Practical Application Show Chinese title

Title: 对比学习与领域适应的桥梁：理论视角与实践应用

Gonzalo Iñaki Quintana, Laurence Vancamberg, Vincent Jugnon, Agnès Desolneux, Mathilde Mougeot

Subjects: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI)

[10] arXiv:2502.00059 (cross-list from cs.LG) [cn-pdf, pdf, html, other]

Title: Large Language Models are Few-shot Multivariate Time Series Classifiers Show Chinese title

Title: 大型语言模型是Few-shot多变量时间序列分类器

Yakun Chen, Zihao Li, Chao Yang, Xianzhi Wang, Guandong Xu

Subjects: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI)

[11] arXiv:2502.00061 (cross-list from cs.LG) [cn-pdf, pdf, html, other]

Title: From Data to Action: Charting A Data-Driven Path to Combat Antimicrobial Resistance Show Chinese title

Title: 从数据到行动：绘制对抗抗菌素耐药性的数据驱动路径

Qian Fu, Yuzhe Zhang, Yanfeng Shu, Ming Ding, Lina Yao, Chen Wang

Comments: 29 pages, 3 figures, 4 tables, survey paper

Subjects: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI) ; Populations and Evolution (q-bio.PE)

[12] arXiv:2502.00088 (cross-list from cs.LG) [cn-pdf, pdf, html, other]

Title: Re-Visiting Explainable AI Evaluation Metrics to Identify The Most Informative Features Show Chinese title

Title: 重新审视可解释人工智能的评估指标以识别最具信息量的特征

Ahmed M. Salih

Subjects: Machine Learning (cs.LG) ; Machine Learning (stat.ML)

[13] arXiv:2502.00108 (cross-list from cs.LG) [cn-pdf, pdf, html, other]

Title: Tracking Most Significant Shifts in Infinite-Armed Bandits Show Chinese title

Title: 追踪无限臂多臂老虎机中的最重要变化

Joe Suk, Jung-hun Kim

Subjects: Machine Learning (cs.LG) ; Machine Learning (stat.ML)

[14] arXiv:2502.00112 (cross-list from cs.LG) [cn-pdf, pdf, html, other]

Title: SAGRAD: A Program for Neural Network Training with Simulated Annealing and the Conjugate Gradient Method Show Chinese title

Title: SAGRAD：一种使用模拟退火和共轭梯度法的神经网络训练程序

Javier Bernal, Jose Torres-Jimenez

Journal-ref: Journal of Research of the National Institute of Standards and Technology Volume 120 (2015)

Subjects: Machine Learning (cs.LG) ; Neural and Evolutionary Computing (cs.NE)

[15] arXiv:2502.00140 (cross-list from cs.LG) [cn-pdf, pdf, html, other]

Title: Demystifying MPNNs: Message Passing as Merely Efficient Matrix Multiplication Show Chinese title

Title: 解析MPNN：消息传递不过是高效的矩阵乘法

Qin Jiang, Chengjia Wang, Michael Lones, Wei Pang

Subjects: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI) ; Neural and Evolutionary Computing (cs.NE) ; Social and Information Networks (cs.SI)

[16] arXiv:2502.00172 (cross-list from cs.LG) [cn-pdf, pdf, other]

Title: Distribution-Specific Agnostic Conditional Classification With Halfspaces Show Chinese title

Title: 基于半空间的分布特定不可知条件分类

Jizhou Huang, Brendan Juba

Subjects: Machine Learning (cs.LG) ; Computational Complexity (cs.CC) ; Machine Learning (stat.ML)

[17] arXiv:2502.00177 (cross-list from cs.LG) [cn-pdf, pdf, html, other]

Title: Evaluating Deep Human-in-the-Loop Optimization for Retinal Implants Using Sighted Participants Show Chinese title

Title: 使用视力正常参与者评估视网膜植入的人类-in-环优化的深度研究

Eirini Schoinas, Adyah Rastogi, Anissa Carter, Jacob Granley, Michael Beyeler

Subjects: Machine Learning (cs.LG) ; Computer Vision and Pattern Recognition (cs.CV) ; Human-Computer Interaction (cs.HC)

[18] arXiv:2502.00180 (cross-list from cs.LG) [cn-pdf, pdf, other]

Title: Spectral Analysis of Diffusion Models with Application to Schedule Design Show Chinese title

Title: 扩散模型的谱分析及其在调度设计中的应用

Roi Benita, Michael Elad, Joseph Keshet

Subjects: Machine Learning (cs.LG) ; Machine Learning (stat.ML)

[19] arXiv:2502.00182 (cross-list from cs.LG) [cn-pdf, pdf, html, other]

Title: Understanding Federated Learning from IID to Non-IID dataset: An Experimental Study Show Chinese title

Title: 理解从独立同分布到非独立同分布数据的联邦学习：一项实验研究

Jungwon Seo, Ferhat Ozgur Catak, Chunming Rong

Journal-ref: 36th Norwegian ICT Conference for Research and Education, NIKT 2024

Subjects: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI) ; Machine Learning (stat.ML)

[20] arXiv:2502.00190 (cross-list from cs.LG) [cn-pdf, pdf, html, other]

Title: On the Effectiveness of Random Weights in Graph Neural Networks Show Chinese title

Title: 关于图神经网络中随机权重的有效性

Thu Bui, Carola-Bibiane Schönlieb, Bruno Ribeiro, Beatrice Bevilacqua, Moshe Eliasof

Subjects: Machine Learning (cs.LG) ; Machine Learning (stat.ML)

[21] arXiv:2502.00193 (cross-list from cs.LG) [cn-pdf, pdf, other]

Title: Byzantine-Resilient Zero-Order Optimization for Communication-Efficient Heterogeneous Federated Learning Show Chinese title

Title: 拜占庭鲁棒零阶优化在通信高效的异构联邦学习中的应用

Maximilian Egger, Mayank Bakshi, Rawad Bitar

Subjects: Machine Learning (cs.LG) ; Cryptography and Security (cs.CR) ; Distributed, Parallel, and Cluster Computing (cs.DC) ; Machine Learning (stat.ML)

[22] arXiv:2502.00194 (cross-list from cs.LG) [cn-pdf, pdf, other]

Title: Physics-Informed Neural Network based Damage Identification for Truss Railroad Bridges Show Chinese title

Title: 基于物理信息神经网络的桁架铁路桥损伤识别

Althaf Shajihan, Kirill Mechitov, Girish Chowdhary, Billie F. Spencer Jr

Comments: 30 pages, 15 figures

Subjects: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI) ; Computational Physics (physics.comp-ph)

[23] arXiv:2502.00197 (cross-list from cs.LG) [cn-pdf, pdf, html, other]

Title: Learning Model Successors Show Chinese title

Title: 学习模型后继者

Yingshan Chang, Yonatan Bisk

Subjects: Machine Learning (cs.LG) ; Machine Learning (stat.ML)

[24] arXiv:2502.00201 (cross-list from cs.LG) [cn-pdf, pdf, html, other]

Title: Year-over-Year Developments in Financial Fraud Detection via Deep Learning: A Systematic Literature Review Show Chinese title

Title: 年度金融欺诈检测中深度学习的发展：系统文献综述

Yisong Chen, Chuqing Zhao, Yixin Xu, Chuanhao Nie, Yixin Zhang

Subjects: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI) ; Statistical Finance (q-fin.ST)

[25] arXiv:2502.00203 (cross-list from cs.LG) [cn-pdf, pdf, html, other]

Title: Reward-aware Preference Optimization: A Unified Mathematical Framework for Model Alignment Show Chinese title

Title: 奖励感知偏好优化：模型对齐的统一数学框架

Shengyang Sun, Yian Zhang, Alexander Bukharin, David Mosallanezhad, Jiaqi Zeng, Soumye Singhal, Gerald Shen, Adithya Renduchintala, Tugrul Konuk, Yi Dong, Zhilin Wang, Dmitry Chichkov, Olivier Delalleau, Oleksii Kuchaiev

Comments: 8 pages, 4 figures; update author names

Subjects: Machine Learning (cs.LG) ; Computation and Language (cs.CL)

[26] arXiv:2502.00204 (cross-list from cs.LG) [cn-pdf, pdf, html, other]

Title: Nearly-Optimal Bandit Learning in Stackelberg Games with Side Information Show Chinese title

Title: 具有侧信息的Stackelberg博弈中的近似最优Bandit学习

Maria-Florina Balcan, Martino Bernasconi, Matteo Castiglioni, Andrea Celli, Keegan Harris, Zhiwei Steven Wu

Subjects: Machine Learning (cs.LG) ; Computer Science and Game Theory (cs.GT)

[27] arXiv:2502.00206 (cross-list from cs.LG) [cn-pdf, pdf, html, other]

Title: BICompFL: Stochastic Federated Learning with Bi-Directional Compression Show Chinese title

Title: BICompFL：具有双向压缩的随机联邦学习

Maximilian Egger, Rawad Bitar, Antonia Wachter-Zeh, Nir Weinberger, Deniz Gündüz

Subjects: Machine Learning (cs.LG) ; Distributed, Parallel, and Cluster Computing (cs.DC) ; Information Theory (cs.IT) ; Machine Learning (stat.ML)

[28] arXiv:2502.00212 (cross-list from cs.LG) [cn-pdf, pdf, html, other]

Title: STP: Self-play LLM Theorem Provers with Iterative Conjecturing and Proving Show Chinese title

Title: STP：具有迭代猜想与证明的自我博弈LLM定理证明器

Kefan Dong, Tengyu Ma

Comments: 25 pages, 5 figures

Subjects: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI) ; Logic in Computer Science (cs.LO)

[29] arXiv:2502.00213 (cross-list from cs.LG) [cn-pdf, pdf, html, other]

Title: Understanding Why Adam Outperforms SGD: Gradient Heterogeneity in Transformers Show Chinese title

Title: 理解为何Adam的表现优于SGD：Transformer中的梯度异质性

Akiyoshi Tomihari, Issei Sato

Subjects: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI) ; Neural and Evolutionary Computing (cs.NE)

[30] arXiv:2502.00217 (cross-list from cs.LG) [cn-pdf, pdf, html, other]

Title: Fantastic Multi-Task Gradient Updates and How to Find Them In a Cone Show Chinese title

Title: 神奇的多任务梯度更新及如何在锥体内找到它们

Negar Hassanpour, Muhammad Kamran Janjua, Kunlin Zhang, Sepehr Lavasani, Xiaowen Zhang, Chunhua Zhou, Chao Gao

Comments: 16 pages, 7 figures, 5 tables

Subjects: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI) ; Computer Vision and Pattern Recognition (cs.CV)

[31] arXiv:2502.00220 (cross-list from cs.LG) [cn-pdf, pdf, html, other]

Title: Algorithmic Clustering based on String Compression to Extract P300 Structure in EEG Signals Show Chinese title

Title: 基于字符串压缩的算法聚类提取脑电图信号中的P300结构

Guillermo Sarasa, Ana Granados, Francisco B Rodríguez

Journal-ref: Computer Methods and Programs in Biomedicine 2019

Subjects: Machine Learning (cs.LG) ; Information Theory (cs.IT) ; Signal Processing (eess.SP)

[32] arXiv:2502.00225 (cross-list from cs.LG) [cn-pdf, pdf, html, other]

Title: Should You Use Your Large Language Model to Explore or Exploit? Show Chinese title

Title: 你应该让你的大语言模型去探索还是利用？

Keegan Harris, Aleksandrs Slivkins

Subjects: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL)

[33] arXiv:2502.00226 (cross-list from cs.LG) [cn-pdf, pdf, html, other]

Title: HackerRank-ASTRA: Evaluating Correctness & Consistency of Large Language Models on cross-domain multi-file project problems Show Chinese title

Title: HackerRank-ASTRA：评估大型语言模型在跨域多文件项目问题上的正确性和一致性

Jun Xing, Mayur Bhatia, Sahil Phulwani, Darshan Suresh, Rafik Matta

Comments: 24 pages, 25 figures

Subjects: Machine Learning (cs.LG) ; Software Engineering (cs.SE)

[34] arXiv:2502.00234 (cross-list from cs.LG) [cn-pdf, pdf, html, other]

Title: Fast Solvers for Discrete Diffusion Models: Theory and Applications of High-Order Algorithms Show Chinese title

Title: 离散扩散模型的快速求解器：高阶算法的理论与应用

Yinuo Ren, Haoxuan Chen, Yuchen Zhu, Wei Guo, Yongxin Chen, Grant M. Rotskoff, Molei Tao, Lexing Ying

Comments: 38 pages, 7 figures

Subjects: Machine Learning (cs.LG) ; Computer Vision and Pattern Recognition (cs.CV) ; Numerical Analysis (math.NA) ; Computational Physics (physics.comp-ph) ; Machine Learning (stat.ML)

[35] arXiv:2502.00241 (cross-list from cs.LG) [cn-pdf, pdf, html, other]

Title: Mordal: Automated Pretrained Model Selection for Vision Language Models Show Chinese title

Title: 莫达：用于视觉语言模型的自动化预训练模型选择

Shiqi He, Insu Jang, Mosharaf Chowdhury

Subjects: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL) ; Computer Vision and Pattern Recognition (cs.CV)

[36] arXiv:2502.00245 (cross-list from cs.LG) [cn-pdf, pdf, html, other]

Title: Contrastive Private Data Synthesis via Weighted Multi-PLM Fusion Show Chinese title

Title: 基于加权多PLM融合的对比隐私数据合成

Tianyuan Zou, Yang Liu, Peng Li, Yufei Xiong, Jianqing Zhang, Jingjing Liu, Xiaozhou Ye, Ye Ouyang, Ya-Qin Zhang

Comments: 16 pages, 11 tables, 7 figures

Subjects: Machine Learning (cs.LG)

[37] arXiv:2502.00258 (cross-list from cs.LG) [cn-pdf, pdf, html, other]

Title: ProxSparse: Regularized Learning of Semi-Structured Sparsity Masks for Pretrained LLMs Show Chinese title

Title: ProxSparse：预训练大语言模型半结构化稀疏性掩码的正则化学习

Hongyi Liu, Rajarshi Saha, Zhen Jia, Youngsuk Park, Jiaji Huang, Shoham Sabach, Yu-Xiang Wang, George Karypis

Comments: ICML25

Subjects: Machine Learning (cs.LG) ; Computation and Language (cs.CL)

[38] arXiv:2502.00264 (cross-list from cs.LG) [cn-pdf, pdf, html, other]

Title: Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion Show Chinese title

Title: 超越Transformer的排列对称性：旋转在模型融合中的作用

Binchi Zhang, Zaiyi Zheng, Zhengzhang Chen, Jundong Li

Comments: ICML 2025

Subjects: Machine Learning (cs.LG) ; Computer Vision and Pattern Recognition (cs.CV)

[39] arXiv:2502.00270 (cross-list from cs.LG) [cn-pdf, pdf, html, other]

Title: DUET: Optimizing Training Data Mixtures via Feedback from Unseen Evaluation Tasks Show Chinese title

Title: DUET：通过来自未见评估任务的反馈优化训练数据混合

Zhiliang Chen, Gregory Kang Ruey Lau, Chuan-Sheng Foo, Bryan Kian Hsiang Low

Subjects: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI) ; Machine Learning (stat.ML)

[40] arXiv:2502.00277 (cross-list from cs.LG) [cn-pdf, pdf, html, other]

Title: Regularized Langevin Dynamics for Combinatorial Optimization Show Chinese title

Title: 组合优化的正则化朗之万动力学

Shengyu Feng, Yiming Yang

Comments: ICML 2025

Journal-ref: International conference on machine learning, 2025, PMLR

Subjects: Machine Learning (cs.LG) ; Machine Learning (stat.ML)

[41] arXiv:2502.00279 (cross-list from cs.LG) [cn-pdf, pdf, html, other]

Title: Improving realistic semi-supervised learning with doubly robust estimation Show Chinese title

Title: 通过双重稳健估计改进现实中的半监督学习

Khiem Pham, Charles Herrmann, Ramin Zabih

Subjects: Machine Learning (cs.LG) ; Machine Learning (stat.ML)

[42] arXiv:2502.00280 (cross-list from cs.LG) [cn-pdf, pdf, html, other]

Title: On the study of frequency control and spectral bias in Wavelet-Based Kolmogorov Arnold networks: A path to physics-informed KANs Show Chinese title

Title: 关于小波基 Kolmogorov-Arnold 网络中频率控制和光谱偏置的研究：通往物理学启发的 KANs 的途径

Juan Daniel Meshir, Abel Palafox, Edgar Alejandro Guerrero

Comments: 29 pages, 13 figures

Subjects: Machine Learning (cs.LG) ; Numerical Analysis (math.NA)

[43] arXiv:2502.00281 (cross-list from cs.LG) [cn-pdf, pdf, html, other]

Title: Sigmoid Self-Attention has Lower Sample Complexity than Softmax Self-Attention: A Mixture-of-Experts Perspective Show Chinese title

Title: Sigmoid自注意力的样本复杂度低于Softmax自注意力：从专家混合的角度来看

Fanqi Yan, Huy Nguyen, Pedram Akbarian, Nhat Ho, Alessandro Rinaldo

Comments: Fanqi Yan, Huy Nguyen contributed equally to this work. 49 pages, 2 figures, 1 table

Subjects: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI)

[44] arXiv:2502.00282 (cross-list from cs.LG) [cn-pdf, pdf, html, other]

Title: GraphMinNet: Learning Dependencies in Graphs with Light Complexity Minimal Architecture Show Chinese title

Title: GraphMinNet：学习图依赖关系的轻量级复杂度最小架构

Md Atik Ahamed, Andrew Cheng, Qiang Ye, Qiang Cheng

Subjects: Machine Learning (cs.LG)

[45] arXiv:2502.00285 (cross-list from cs.LG) [cn-pdf, pdf, html, other]

Title: K Nearest Neighbor-Guided Trajectory Similarity Learning Show Chinese title

Title: K最近邻引导的轨迹相似性学习

Yanchuan Chang, Xu Cai, Christian S. Jensen, Jianzhong Qi

Subjects: Machine Learning (cs.LG) ; Computer Vision and Pattern Recognition (cs.CV) ; Databases (cs.DB)

[46] arXiv:2502.00288 (cross-list from cs.LG) [cn-pdf, pdf, html, other]

Title: Learning from Suboptimal Data in Continuous Control via Auto-Regressive Soft Q-Network Show Chinese title

Title: 从次优数据中学习连续控制的自回归软Q网络

Jijia Liu, Feng Gao, Qingmin Liao, Chao Yu, Yu Wang

Comments: Accepted by ICML 2025

Subjects: Machine Learning (cs.LG) ; Robotics (cs.RO)

[47] arXiv:2502.00298 (cross-list from cs.LG) [cn-pdf, pdf, html, other]

Title: The Price of Linear Time: Error Analysis of Structured Kernel Interpolation Show Chinese title

Title: 线性时间的价格：结构化核插值的误差分析

Alexander Moreno, Justin Xiao, Jonathan Mei

Subjects: Machine Learning (cs.LG) ; Machine Learning (stat.ML)

[48] arXiv:2502.00300 (cross-list from cs.LG) [cn-pdf, pdf, other]

Title: Uncertainty Quantification of Wind Gust Predictions in the Northeast United States: An Evidential Neural Network and Explainable Artificial Intelligence Approach Show Chinese title

Title: 东北美国风速预测的不确定性量化：一种证据神经网络和可解释人工智能的方法

Israt Jahan, John S. Schreck, David John Gagne, Charlie Becker, Marina Astitha

Journal-ref: Environmental Modelling & Software, Volume 193, 2025, 106595, ISSN 1364-8152

Subjects: Machine Learning (cs.LG) ; Atmospheric and Oceanic Physics (physics.ao-ph) ; Machine Learning (stat.ML)

[49] arXiv:2502.00304 (cross-list from cs.LG) [cn-pdf, pdf, html, other]

Title: HoP: Homeomorphic Polar Learning for Hard Constrained Optimization Show Chinese title

Title: HoP: 针对硬约束优化的同胚极学习

Ke Deng, Hanwen Zhang, Jin Lu, Haijian Sun

Comments: in submission

Subjects: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI) ; Optimization and Control (math.OC)

[50] arXiv:2502.00311 (cross-list from cs.LG) [cn-pdf, pdf, html, other]

Title: Sparse Gradient Compression for Fine-Tuning Large Language Models Show Chinese title

Title: 稀疏梯度压缩用于微调大型语言模型

David H. Yang, Mohammad Mohammadi Amiri, Tejaswini Pedapati, Subhajit Chaudhury, Pin-Yu Chen

Subjects: Machine Learning (cs.LG)