# epfml/OptML_course

EPFL Course - Optimization for Machine Learning - CS-439

Repository: https://github.com/epfml/OptML_course
Canonical: https://ross.abutalabs.com/products/optml_course
Language: Jupyter Notebook
License Family: other
Last push: 2026-07-14T07:57:35+00:00

## Health v2 (maintenance only)
Score: 74/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 92, release rhythm 35, longevity 100
- inputs: {"age_days": 3115, "days_push": 50, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1467, forks 346 (observed 2026-08-28T04:04:48.785455+00:00)

## What it is
EPFL's CS-439 'Optimization for Machine Learning' course materials, including lecture slides and lab exercises in Jupyter notebooks. It covers convexity, gradient methods, proximal and stochastic algorithms, duality, second-order methods, and advanced topics like distributed optimization and federated learning.

## Use cases
- learn optimization methods for machine learning
- study gradient descent and stochastic gradient descent theory
- find exercises on convex optimization and duality
- self-study a university course on optimization for data science
- prepare for ML interviews covering optimization algorithms
- learn about proximal and subgradient methods
- understand non-convex optimization and neural network training

## When to choose
- you want structured, university-grade course material on ML optimization
- you prefer learning with slides plus hands-on notebook exercises
- you need coverage of both convex and non-convex optimization theory

## When to avoid
- you need production optimization software or solver libraries
- you want a quick reference rather than a full course
- you need a formally licensed, redistributable resource (no license is specified)

## Facets
- artifact type: learning-resource
- maturity: active
- function: machine-learning, math, developer-tools
- domain: machine-learning, tutorials, education, mathematics
- platform: python, cross-platform
- tags: optimization, course-materials, convex-optimization, gradient-descent, epfl, jupyter-notebooks, lecture-slides, federated-learning, algorithms

## Member repositories
- epfml/OptML_course (main) score 74

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:48.785455+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:34:59.432186+00:00, confidence not recorded.
  - readme: https://github.com/epfml/OptML_course (fetched 2026-08-28T04:04:48.785455+00:00, sha 416da08f569d)
- Data as of 2026-08-30T08:39:29.467469+00:00.