AI-CPT_S-436-536-paul.wilmoth-2026-09-23-10-46-09

Below is a syllabus template that includes WSU's required syllabus elements. Please complete all items highlighted in yellow.

Title of Course [Distributed Machine Learning]

Prefix and Number [AI / CPT_S 436 / 536]

Semester and Year [tbd]

Number of Credit Hours [e]

Prerequisites [For CPT S 436/AI 426—CPT S 437/AI 437 with a C or better; MATH 220 or 225 with a C or better; STAT 360 with a C or better. For CPT S 536-- CPTS 570. ]

Course Details

Day and Time: [tbd]

Meeting Location: [tbd]

Instructor Contact Information

Instructor Name: [tbd]

Instructor Contact Information: [office location, phone, email] [tbd]

Instructor Office Hours: [click here for best practices] [tbd]

TA Name: [tbd]

TA Contact Information: [office location, phone, email]: [tbd]

TA Office Hours: [click here for best practices] [tbd]

Course Description

This course introduces the foundations, algorithms, and practical challenges of distributed machine learning, federated learning, and distributed optimization. Topics include convex optimization; gradient and stochastic-gradient methods; momentum and variance reduction; federated averaging; data and system heterogeneity; communication-efficient learning; personalization; client selection; decentralized learning; differential privacy; Byzantine robustness; and fairness.

Students implement and evaluate distributed and federated learning algorithms using real datasets and examine how statistical heterogeneity, communication limitations, privacy requirements, unreliable participants, and resource constraints affect system performance. Undergraduate students emphasize algorithmic understanding, implementation, experimentation, and application. Graduate students additionally complete rigorous convergence analysis, mathematical derivations, research-oriented evaluation, and critical examination of current literature.

Rationale for Conjoint Offering

Distributed machine learning and federated learning are increasingly important in distributed AI, edge intelligence, privacy-preserving analytics, and large-scale learning systems. The subject is relevant to undergraduate students preparing to develop and apply distributed AI systems and to graduate students conducting advanced research in machine learning, optimization, networking, privacy, and related areas.

Both groups benefit from studying a common set of foundational algorithms, system challenges, applications, and contemporary research. The conjoint format supports a shared learning environment while maintaining appropriate academic differentiation. Undergraduate students focus primarily on algorithmic intuition, implementation, empirical evaluation, and real-world applications. Graduate students are expected to demonstrate greater mathematical depth, conduct rigorous convergence analysis, engage more extensively with research literature, and complete a more independent, research-oriented project.

Dimension	CPT_S 436/AI 436	CPT_S 536
Learning expectations	Explain the design rationale of established distributed and federated learning methods and apply them to representative problems.	In addition to the undergraduate expectations, derive and analyze algorithms, evaluate theoretical guarantees, and critically examine assumptions and limitations.
Mathematical analysis	Understand basic convergence concepts and selected analyses, including the main ideas behind FedAvg.	Complete rigorous convergence analyses and understand detailed mathematical derivations for distributed and federated learning algorithms.
Assignments	Complete core conceptual, implementation, and application-oriented problems.	Complete the core problems and additional graduate-level questions involving proofs, derivations, advanced analysis, and research literature.
Examinations	Complete the conceptual, algorithmic, and foundational mathematical portions of the examinations.	Complete all examination components, including advanced mathematical analysis, proofs, and derivations.
Course project	Develop and evaluate an application-oriented distributed or federated learning system using real data.	Conduct a research-oriented investigation involving deeper literature review, theoretical or methodological analysis, controlled experimentation, and critical evaluation.
Assessment expectations	Evaluated on conceptual understanding, implementation correctness, experimental design, interpretation, and communication.	Evaluated on the same dimensions with additional emphasis on mathematical rigor, independence, research depth, reproducibility, and critical analysis.

Course Materials

Books:

No textbook is required. Recommended references include:

Gauri Joshi, Optimization Algorithms for Distributed Machine Learning. Springer, 2023.
Stephen Boyd and Lieven Vandenberghe, Convex Optimization. Cambridge University Press.
Yurii Nesterov, Introductory Lectures on Convex Optimization: A Basic Course. Springer, 2004.

Other Materials:

Selected research papers, technical reports, lecture notes, datasets, programming notebooks, and supplementary materials will be provided through Canvas or the course website.

Students will use Python and appropriate machine-learning frameworks and distributed or federated learning libraries. Access to suitable computing resources will be provided or arranged when required.

Fees: None

**Student Learning Outcomes (SLOs) [add more lines if necessary]**
Course Learning Outcomes (students will be able to:)	Activities Supporting the Learning Outcomes	Assessment of the Learning Outcomes
1. Explain the motivations, architectures, and principal challenges of distributed and federated machine learning (6e).	Lectures, readings, case studies, and class discussions	Homework, examinations, and project proposal
2. Apply foundational optimization methods, including gradient descent, stochastic gradient descent, momentum, and variance-reduction methods (1e, 6a).	Worked examples, mathematical exercises, and programming activities	Homework and examinations
3. Implement and compare core distributed and federated learning algorithms, including FedAvg and methods addressing statistical and system heterogeneity (2g, 6a, 6b).	Programming assignments, guided experiments, and demonstrations	Implementation assignments and project
4. Analyze how data heterogeneity, system heterogeneity, communication constraints, client selection, and network structure affect learning performance (2c, 6c).	Algorithm analysis, experiments, case studies, and readings	Homework, examinations, and experimental reports
5. Evaluate approaches for personalization, decentralized learning, communication compression, privacy, robustness, and fairness (2e, 6b, 6e).	Research-paper discussions, implementation exercises, and comparative studies	Homework, project, and examinations
6. Design and conduct reproducible experiments using distributed or federated learning algorithms and real datasets (2e, 6b).	Programming assignments, project milestones, and peer feedback	Code, experimental results, project report, and presentation
7. Communicate the design, assumptions, results, limitations, and implications of a distributed machine-learning system (3b, 6e).	Technical writing, project reviews, class discussions, and presentations	Final project report and presentation

Graduate students must demonstrate these outcomes at a higher level of mathematical depth, independence, experimental rigor, and engagement with current research.

**Course Schedule**

**[Please note that a WSU semester is 15 weeks + Thanksgiving/Spring Break. The schedule below does not include the break.]**
Dates	Lesson Topic	Assignment	Assessment
Week 1 [dates]	Introduction to distributed machine learning; centralized, distributed, decentralized, and federated learning settings; applications and system models	Course orientation and background review	Project overview
Week 2 [dates]	Convex sets, convex functions, optimization problems, smoothness, and optimality	Homework 1 assigned	Topic exploration
Week 3 [dates]	Gradient descent, convergence concepts, step-size selection, and conditioning	Mathematical and programming exercises
Week 4 [dates]	Stochastic gradient descent, momentum, adaptive methods, and variance reduction	Homework 1 due; Homework 2 assigned
Week 5 [dates]	Federated-learning foundations; local training; aggregation; FedAvg	FedAvg implementation laboratory	Project topic due
Week 6 [dates]	Statistical heterogeneity and non-IID data; FedProx, SCAFFOLD, and FedDyn	Homework 2 due; Homework 3 assigned	Proposal development
Week 7 [dates]	System heterogeneity, partial participation, stragglers, and FedNova	Comparative experiment	Project proposal due
Week 8 [dates]	Communication-efficient distributed learning; quantization, sparsification, and compression	Midterm examination
Week 9 [dates]	Personalized federated learning; federated meta-learning and distributed multitask learning	Homework 3 due; Homework 4 assigned	Initial implementation
Week 10 [dates]	Client selection, scheduling, incentives, and resource allocation	Client-selection case study	Project checkpoint
Week 11 [dates]	Decentralized learning over networks; consensus and network topology	Decentralized-learning laboratory	Preliminary results
Week 12 [dates]	Privacy in distributed learning; differential privacy and privacy–utility tradeoffs	Homework 4 due; Homework 5 assigned	Midterm project report due
Week 13 [dates]	Robust distributed learning; Byzantine participants, attacks, and robust aggregation	Robustness experiment	Evaluation and refinement
Week 14 [dates]	Fairness in federated learning; responsible deployment; emerging research directions	Homework 5 due	Final report preparation
Week 15 [dates]	Integration, comparative analysis, and project presentations	Final project presentation	Final report due

Expectations for Student Effort

[Describe how much time students should expect to invest in the course each week. Graduate courses should state: "For each hour of lecture equivalent, students should expect to have a minimum of two hours of work outside of class." Note that Global campus courses will automatically include credit hour equivalents in the syllabus.]

For each hour of lecture equivalent, students should expect a minimum of two hours of work outside class. For this three-credit course, students should plan for approximately six or more hours per week outside scheduled class meetings for readings, mathematical exercises, programming assignments, experiments, and project work.

Graduate students should expect additional time for research-paper analysis, mathematical derivations, graduate-level assignment components, and the research-oriented course project.

Grading [add more lines if necessary]

Assignment Breakdown
Type of Assignment (tests, papers, etc)	Points	Percent of Overall Grade
Homework assignments—mathematical, conceptual, and implementation	30	30%
Midterm examination	15	15%
Final examination	15	15%
Project proposal and checkpoint	5	5%
Project implementation and final report	25	25%
Project presentation	10	10%

CPT_S 536

Assignment Category	Points	Percent of Overall Grade
Homework assignments—including graduate-level analysis and derivations	30	30%
Midterm examination	20	20%
Final examination	25	25%
Project proposal and checkpoint	5	5%
Research project, final report, and presentation	20	20%

Undergraduate and graduate students participate in the same core learning activities. Graduate students complete additional required questions involving mathematical derivations, convergence analysis, advanced methods, and critical evaluation of research. When a common examination is used, graduate-level sections are required for CPT_S 536 students and are not required for CPT_S 436/AI 436 students.

Grading Schema
Grade	Percent	Grade	Percent
A	93.00–100%	C	73.00–76.99%
A-	90.00–92.99%	C-	70.00–72.99%
B+	87.00–89.99%	D+	67.00–69.99%
B	83.00–86.99%	D	60.00–66.99%
B-	80.00–82.99%	F	Below 60.00%
C+	77.00–79.99%

The final course percentage will be calculated using full precision and rounded once to the nearest whole number. A fractional portion of 0.50 or higher will be rounded up, while a fractional portion below 0.50 will be rounded down. For example, 89.50% will be rounded to 90% and will earn an A−, while 89.49% will be rounded to 89% and will earn a B+.

Attendance and Make-Up Policy

[Provide details on how attendance affects final course grades. Indicate whether and how missed exams, laboratory sessions, etc. can be made up. Sample attendance statement: “Students should make all reasonable efforts to attend all class meetings. However, in the event a student is unable to attend a class, it is the responsibility of the student to inform the instructor as soon as possible, explain the reason for the absence (and provide documentation, if appropriate), and make up class work missed within a reasonable amount of time, if allowed. Missing class meetings may result in reducing the overall grade in the class.” ] [

Students should make all reasonable efforts to attend and participate in class meetings. Students who cannot attend a class or scheduled assessment should notify the instructor as soon as possible. Requests for excused absences, make-up assessments, or deadline accommodations due to illness, emergencies, university-recognized absences, or approved accommodations will be handled in accordance with applicable university policies.

Students are responsible for reviewing missed course materials and completing permitted make-up work within the timeframe established by the instructor.

Academic Integrity Statement

You are responsible for reading WSU's Academic Integrity Policy, which is based on Washington State law. If you cheat in your work in this class you will:

Students are responsible for reading and following WSU’s Academic Integrity Policy. Academic misconduct may result in a failing grade for the affected assignment or examination and a report to the Center for Community Standards.

Students have the right to appeal an academic-integrity decision and may not withdraw from the course until the appeals process has concluded. Questions about permitted collaboration, source use, programming assistance, or other academic-integrity matters should be directed to the instructor before submitting the work.

Use of Generative AI Tools

Generative AI tools may be used for learning support, such as concept clarification, brainstorming, debugging assistance, code readability, and writing feedback, when permitted by the instructor. These tools must not replace the student’s own mathematical reasoning, implementation, experimental analysis, interpretation, or decision-making.

Students must understand and be able to explain all submitted code, derivations, reports, figures, results, and conclusions. Substantial use of generative AI must be acknowledged in accordance with assignment instructions. Generative AI tools may not be used during examinations unless explicitly authorized by the instructor.

Graduate Student Rights and Responsibilities

Students enrolled in CPT_S 536 are expected to understand and follow the WSU Graduate School’s policies concerning academic integrity, student rights, academic performance, and graduate-student responsibilities.