Understanding the fundamentals of distributed optimization and machine learning
This 12-week comprehensive course offers an in-depth overview of designing and analysing distributed optimisation algorithms for machine learning applications. Centralised processing over large networks is computationally prohibitive due to communication overhead and scale. Thus, distributed or decentralised control and optimisation algorithms are essential. The course revisits classical algorithms for centralised optimisation and extends them to distributed settings, addressing 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 with recent literature on accelerated distributed optimisation algorithms.
The course provides a comprehensive curriculum to dive into various aspects of distributed optimisation and machine learning. Here's a glimpse of the key topics covered:
It is designed for individuals with a foundation in specific areas to ensure they can grasp the concepts effectively and will be an ideal choice for those who wish to understand and apply their knowledge of:
Field of Study: | Distributed Optimization And Machine Learning |
Type: | Free Course |
Duration: | 12 Weeks |
Mode of Learning: | Online |
Average Salary Offered: | The average salary offered in this field ranges from ₹ 2.6 LPA to ₹ 14 LPA depending upon your skills, experience, and level of knowledge. |
Employment Roles: |
|