Course materials

Lectures

  • Lecture 1: Introduction, Feb 7, 2020, 10:00-12:00.

<Slides>

  • Lecture 2: Centralized Convex ML (part 1: deterministic algorithms), Feb 12, 2020, 10:00-12:00.

<Slides>

  • Lecture 3: Centralized Convex ML (part 2: stochastic algorithms), Feb 19, 2020, 10:00-12:00.

<Slides>

  • Lecture 4: Computer Assignment Session and Homework (part 1), Feb 26, 2020, 10:00-12:00.
  • Lecture 5: Centralized Nonconvex ML, March 6, 2020, 10:00-12:00.

<Slides >

  • Lecture 6: Distributed ML, March 6, 2020, 13:00-15:00.

<Slides>

  • Lecture 7: ADMM, April 8, 2020, 10:00-12:00.

<Slides>

  • Lecture 8: Communication Efficiency, April 15, 2020, 10:00-12:00.

<Slides>

  • Lecture 9: Computer Assignment Session and Homework (part 2), April 22, 2020, 10:00-12:00.
  • Lecture 10: Deep Neural Networks, April 29, 2020, 10:00-12:00.

<Slides>

  • Lectures 11-13, May 18, 2020, 09:00-18:00
    • Lecture 11: Special Topic 1: Large-scale MLoN
    • Lecture 12: Special Topic 2: Application areas: Federated learning and privacy-preserving distributed MLoN
    • Lecture 13: Special Topic 3: Security in MLoN
  • Lectures 14-16, May 19, 2020, 09:00-18:00
    • Lecture 14: Special Topic 4: Online MLoNs
    • Lecture 15: Special Topic 5: Robust MLoN
    • Lecture 16: Application areas and open research problems

Location for Lecture 1: Q21, Malvinas vag 6B, 2nd floor, KTH Main Campus

Location for Lectures 2-3: Q22, Malvinas vag 6B, 2nd floor, KTH Main Campus

Location for Lecture 4: Q31, Malvinas vag 6B, 3rd floor, KTH Main Campus

Location for Lecture 5-6: Q22, Malvinas vag 6B, 2nd floor, KTH Main Campus

Location for Lecture 7-16: Online via Zoom

All lectures

The slides for all lectures are available on our github repository. The slides will be ready before every lecture.

Download all the lecture slides of 2019 from here.

Watch all the lectures of 2019 from in here

Assignments

  • Homework 1 - Due date on February 19, 2020
  • Homework 2 - Due date on February 26, 2020
  • CA 1 and CA 2 - Due date on March 4, 2020
  • Homework 3 - Due date on March 13, 2020
  • CA 3 and CA 4 - Due date on March 27, 2020
  • CA 5 - Due date on April 22, 2020
  • CA 6 - Due date on April 29, 2020
  • CA7 - Due date on May 20, 2020

Readings

  • S. Bubeck. "Convex optimization: Algorithms and complexity." Foundations and Trends in Machine Learning, 2015.
  • L. Bottou, F. Curtis, J. Norcedal, “Optimization methods for large-scale machine learning”, SIAM Rev., 2018.
  • S. Boyd et al. "Distributed optimization and statistical learning via the alternating direction method of multipliers." Foundations and Trends in Machine learning, 2011.
  • M. I. Jordan, J. D. Lee, and Y. Yang. "Communication-efficient distributed statistical inference," Journal of the American Statistical Association, 2018.
  • V. Smith et al. "CoCoA: A general framework for communication-efficient distributed optimization." Journal of Machine Learning Research, 2018.
  • D. Alistarh et al. "QSGD: Communication-efficient SGD via gradient quantization and encoding." Advances in Neural Information Processing Systems, 2017.
  • M. Schmidt, N. Le Roux, and F. Bach. "Minimizing finite sums with the stochastic average gradient." Mathematical Programming, 2017.
  • S. Boyd et al. "Randomized gossip algorithms," IEEE Transactions on Information Theory, 2006.
  • K. Seaman et al. "Optimal algorithms for smooth and strongly convex distributed optimization in networks," ICML, 2017.
  • I. Goodfellow, Y. Bengio, A. Courville, “Deep Learning”, MIT press 2016