Skip to content
Projects

RayXBuilds/Machine-Learning-Papers

View on GitHub

RayXBuilds/Machine-Learning-Papers has 71 GitHub stars and 37 forks. GitHot measured 0 stars in 24 hours and 0 in 7 days. Last checked 2026-11-16 20:34 UTC. Last push 2026-11-07.

How these counts are measured

Measured star growth

in 24h
0
in 7 days
0
in 15 days
Collecting history
in 1 month
Collecting history

Net star changes over overlapping periods, not daily totals. Missing measurements are left blank. Stars measure attention, not software quality.

About

Machine Learning Classic Papers(机器学习经典论文)

Machine Learning

README.en.md

Original

Machine-Learning-Papers

简体中文 | English

Machine learning papers, Chinese reading guides, and an archival library, organized by topic.

Browse by topic · Classic reading paths · Daily additions · Archived PDFs · Contribution guide

This README provides an English overview. Reading guides, topic indexes, daily records, and contribution instructions are currently written primarily in Chinese; paper links lead to the original sources.

Where to start

  • Explore a field: use the topic table below. Each reading guide has its own file.
  • Study systematically: follow the classic reading paths, with suggested prerequisites and reading order.
  • Find recent additions: browse the daily records, which link to the corresponding topic entries.
  • Locate an older file: consult the path migration map or the original 2018 index.

Topics

Topic Scope Reading guides Archived PDFs
Mathematics, Learning Theory & Probabilistic Models Learning theory, optimization, probabilistic inference, graphical models 1 9
Classical Machine Learning Classification, regression, ensembles, clustering, feature selection, active/online/transfer learning 5 34
Deep Learning & Representation Learning Network training, optimization, self-supervised representations, neural network fundamentals 4 3
Computer Vision Image classification, detection, tracking, human motion, visual encoders 4 7
Natural Language Processing & Large Language Models Text, sequences, language models, retrieval augmentation, adaptation, alignment 8 15
Generative Models VAEs, GANs, diffusion models 4 0
Multimodal Learning Image–text alignment and cross-modal representations 1 0
Reinforcement Learning & Decision-Making Policy and value learning, bandits, planning 3 6
Graph Learning & Network Analysis Graph neural networks, community detection, link mining 2 9
Recommender Systems Collaborative filtering, matrix factorization, ALS, neural recommendation 2 6
Machine Learning Systems Distributed training, computing frameworks, parameter servers 1 10
Data Mining & Data Management Time series, data streams, patterns and rules, web mining, entity matching 1 25
Domain Applications Robotics, bioinformatics, finance, sustainability, business applications 1 20
Evaluation & Experimental Methods Experimental design, A/B testing, validation, metrics 11 3

As of November 7, 2026: 48 independent reading guides and 147 archived PDFs. The PDFs include translations and technical documents, so the file count does not represent 147 distinct papers. Indexes and counts are maintained as new entries are added.

Repository layout

papers/<topic>/<year>-<slug>.md       One canonical reading guide per paper or article
library/<topic>/<subtopic>/*.pdf     Existing archival materials, organized by topic
docs/classics.md                     Classic reading paths, with original anchors preserved
docs/daily/YYYY/MM/YYYY-MM-DD.md      Links to daily additions and revisions
docs/migration.md                    Old-to-new file path mapping

Each article has one primary file. Tags and index links connect it to other topics without duplicating its content. Daily records contain brief summaries and links; full reading guides live in the topic directories. See the contribution guide for classification rules and the article template.

Directory reorganization · October 26, 2026

The original 36 root-level categories were consolidated into 14 topic entry points. ALS materials now belong to recommender systems; Ray and other computing frameworks belong to machine learning systems; probabilistic and graphical models are grouped under foundations; and policy iteration belongs to reinforcement learning. All 147 archived PDFs retain their original contents, and the 26 reading guides now have separate files.

PDF paths have changed. The migration guide provides a complete mapping and a link to the repository before the move. The historical index is retained as a source record; its bibliographic information has not been fully reverified.

Ongoing maintenance

Latest additions include one new guide to a preprint first submitted within the past seven days. November 7, 2026 · Hinted scaling laws for performance forecasting

A Codex automation runs daily at 11:00 Beijing time (Asia/Shanghai, UTC+8) to search for, verify, and select up to five machine learning papers or technical articles. New guides are stored by topic and linked from the daily records. No empty record is created when there are no suitable additions. Scheduling is handled by the Codex task; this repository does not currently contain a GitHub Actions scheduler.

Original-paper guides for SVMs, EM, and boosting have been added. Priorities include coverage of model evaluation, data leakage, probability calibration, and interpretability; and verification of historical references and translation sources. A reading guide is not a full translation, an experimental reproduction, or a claim that the paper has been read in depth.

Attribution and rights

Papers and translations remain the property of their respective rights holders. New entries provide original-source links and short, original reading guides rather than additional copies of papers. Organizing this collection does not grant new rights to third-party materials. Suggestions and corrections are welcome through Issues; please include the original source.