X

Distributed Optimization and Machine Learning

By Prof. Mayank Baranwal   |   IIT Bombay
Learners enrolled: 2092   |  Exam registration: 119
ABOUT THE COURSE:
Centralized access to information and its subsequent processing is often computationally prohibitive over large networks due to communication overhead and the scale of the problem. Consequently, such systems rely on control and optimization algorithms that are fully distributed or even decentralized in nature. This course will provide a comprehensive overview of design and analysis of distributed optimization algorithms and their applications to machine learning. The aim is to revisit classical control and optimization algorithms for centralized optimization and discuss how these can be extended to distributed setting to accommodate the effects of communication constraints, network topology, computational resources, and robustness. Topics include graph theory, iterative methods for convex problems, synchronous and asynchronous setups, consensus algorithms, and distributed machine learning. We will also explore some recent literature in this area that exploits control theory for design of accelerated distributed optimization algorithms.

INTENDED AUDIENCE: MTech and PhD students in broad areas of optimization and data science

PREREQUISITES: A background in convex optimization and differential equations is preferred

INDUSTRY SUPPORT: Tata Consultancy Services, Microsoft, Google, Amazon, IBM, etc.
Summary
Course Status : Completed
Course Type : Elective
Language for course content : English
Duration : 12 weeks
Category :
  • Computer Science and Engineering
  • Electrical, Electronics and Communications Engineering
  • Mathematics
  • Communication and Signal Processing
  • Control and Instrumentation
Credit Points : 3
Level : Postgraduate
Start Date : 22 Jul 2024
End Date : 11 Oct 2024
Enrollment Ends : 05 Aug 2024
Exam Registration Ends : 16 Aug 2024
Exam Date : 26 Oct 2024 IST

Note: This exam date is subject to change based on seat availability. You can check final exam date on your hall ticket.


Page Visits



Course layout

Week 1:
1. Introduction to Distributed Optimization
2. Mathematical Optimization, Convex Sets and Convex Functions

Week 2: 
1. Strong Convexity and Its Implications
2. Constrained Optimization Problems: Primal and Lagrangian Dual

Week 3: 
1. KKT Conditions and Primal/Dual Methods
2. Analysis of Gradient Descent

Week 4: 
1. Analysis of Accelerated Optimization Algorithms
2. Optimization Algorithms as Dynamical Systems and Introduction to Stability Theory

Week 5: 
1. Lyapunov Analysis of Gradient Flows
2. Gradient Flows for Equality Constrained Optimization and Saddle-Point Problems

Week 6: 
1. Accelerated Gradient Flows
2. Augmented Lagrangian and Method of Multipliers

Week 7: 
1. ADMM (Alternating Direction Method of Multipliers)
2. Dual Ascent and Dual Decomposition

Week 8: 
1. Introduction to Graph Theory
2. Distributed Consensus

Week 9: 
1. Continuous-Time Analysis of Consensus Algorithms
2. Distributed Optimization Problem (Economic Dispatch Problem)

Week 10: 
1. Distributed Optimization Algorithms
2. Introduction to Neural Networks and Ring-Allreduce Algorithm

Week 11: 
1. Introduction to Federated Learning
2. Data Heterogeneity in Federated Learning

Week 12: 
1. Computational Heterogeneity in Federated Learning
2. Robustness in Federated Learning

Books and references

1. Boyd, Stephen P., and Lieven Vandenberghe. Convex optimization. Cambridge university press, 2004.
2. Nedić, A. (2018). Distributed Optimization Over Networks. In: Facchinei, F., Pang, JS. (eds) Multi-agent Optimization. Lecture Notes in Mathematics(), vol 2224. Springer, Cham. https://doi.org/10.1007/978-3-319-97142-1_1

Instructor bio

Prof. Mayank Baranwal

IIT Bombay
Prof. Mayank Baranwal is an Adjunct Assistant Professor with the Systems and Control group at the Indian Institute of Technology (IIT), Bombay. He is also a Senior Scientist with the research division of Tata Consultancy Services (TCS) in Mumbai, and holds a Guest appointment with the Indian Institute of Management (IIM), Mumbai. Prior to joining IIT Bombay, he was a postdoctoral scholar in the Department of Electrical and Computer Engineering at the University of Michigan, Ann Arbor. He received his Bachelors in Mechanical Engineering in 2011 from Indian Institute of Technology, Kanpur, and MS in Mechanical Science and Engineering in 2014, MS in Mathematics in 2015 and PhD in Mechanical Science and Engineering in 2018, all from the University of Illinois at Urbana-Champaign. His research interests are in modeling, optimization, control and inference in network systems with applications to distributed optimization, supply-chain network, power networks, control of microgrids, bioinformatics and computational biology, and deep learning theory. Mayank is a recipient of the Institute Silver Medal in 2011 (from IIT Kanpur), the ME Outstanding Publication Award in 2017 (from the University of Illinois), the Young Scientist Award in 2022 (Tata Consultancy Services), the Gold Award for Best Smart Technology in Electricity Transmission in 2023 (India Smart Grid Forum), and the 3rd prize in L2RPN Delft 2023 challenge.

Course certificate

The course is free to enroll and learn from. But if you want a certificate, you have to register and write the proctored exam conducted by us in person at any of the designated exam centres.
The exam is optional for a fee of Rs 1000/- (Rupees one thousand only).
Date and Time of Exams: 
26 October 2024 Morning session 9am to 12 noon; Afternoon Session 2pm to 5pm.
Registration url: Announcements will be made when the registration form is open for registrations.
The online registration form has to be filled and the certification exam fee needs to be paid. More details will be made available when the exam registration form is published. If there are any changes, it will be mentioned then.
Please check the form for more details on the cities where the exams will be held, the conditions you agree to when you fill the form etc.

CRITERIA TO GET A CERTIFICATE

Average assignment score = 25% of average of best 8 assignments out of the total 12 assignments given in the course.
Exam score = 75% of the proctored certification exam score out of 100

Final score = Average assignment score + Exam score

YOU WILL BE ELIGIBLE FOR A CERTIFICATE ONLY IF AVERAGE ASSIGNMENT SCORE >=10/25 AND EXAM SCORE >= 30/75. If one of the 2 criteria is not met, you will not get the certificate even if the Final score >= 40/100.

Certificate will have your name, photograph and the score in the final exam with the breakup.It will have the logos of NPTEL and IIT Bombay .It will be e-verifiable at nptel.ac.in/noc.

Only the e-certificate will be made available. Hard copies will not be dispatched.

Once again, thanks for your interest in our online courses and certification. Happy learning.

- NPTEL team


MHRD logo Swayam logo

DOWNLOAD APP

Goto google play store

FOLLOW US