CSCI 1520: Algorithmic Aspects of Machine Learning (Spring 2025)

Basic Information

• Lectures: Tue/Thu 1:00-2:20 pm in CIT 241.
• Instructor: Yu Cheng.
• Email: yu_cheng@brown.edu
• Office Hours: Tuesday 2:30-3:30 pm in CIT 413, or by appointment.
• TAs:
• Harys Dalvi (Head TA). Office Hours: Thursday, 3:00 – 5:00pm in CIT 203.
• Chia-Hong Hsu. Office Hours: Wednesday, 11:00am - 1:00pm in CIT 203.
• Linda Xu. Office Hours: Wednesday, 1:00pm - 3:00pm in CIT 203.
• Michael Youssef. Office Hours: Friday, 11:00am - 1:00pm in CIT 205.
• Textbook:
  • [LRU] Mining of Massive Datasets (Third Edition). Jure Leskovec, Anand Rajaraman, Jeff Ullman.
  • [M] Algorithmic Aspects of Machine Learning. Ankur Moitra.
  • [A] Theory of Deep Learning (book draft). Sanjeev Arora et al.

Course Description

In this course, we will explore the theoretical foundations of machine learning and deep learning, with a focus on the design and analysis of learning algorithms with provable guarantees. Throughout the course, we will (1) discuss data mining and machine learning algorithms for analyzing very large amounts of data, (2) investigate why simple algorithms can solve machine learning problems that are computationally hard in the worst case, and (3) understand the success of deep learning by studying the emerging theory of deep learning. Example topics include locality-sensitive hashing, streaming algorithms, local graph algorithms, non-negative matrix factorization, non-convex optimization, and over-parameterization and implicit regularization in deep learning. Prior knowledge of linear algebra, algorithms and data structures, probability, and statistics is recommended.

Assignments

• Warning: the following assignments and due dates are from the past. If you are taking CSCI 1520 this semester, please refer to the current course webpage.


• Written 1, due on Feb 20 (Thu).
• Coding 1, due on Feb 27 (Thu).
• Written 2, due on Mar 13 (Thu).
• Coding 2, due on Mar 20 (Thu).
• Written 3, due on Apr 17 (Thu).
• Coding 3, due on Apr 24 (Thu).

Schedule

• Week 1 (Jan 20): Introduction.
  • Introduction to the Course (Lecture 1).
• Week 2 (Jan 27): Finding Similar Items I (Chapter 3 of [LRU]).
  • Set Similarity and MinHash (Lecture 2).
  • Locality Sensitive Hashing (Lecture 3).
  • [1] A. Z. Broder. On the Resemblance and Containment of Documents. SEQUENCES 1997.
• Week 3 (Feb 3): Finding Similar Items II (Chapter 3 of [LRU]).
  • Locality-Sensitive Functions and Amplification (Lecture 4).
  • Bloom Filter (Lecture 5).
  • [2] P. Indyk, R. Motwani. Approximate Nearest Neighbors: Towards Removing the Curse of Dimensionality. STOC 1998.
• Week 4 (Feb 10): Algorithms for Data Streams (Chapter 4 of [LRU]).
  • Counting Distinct Elements (Lecture 6).
  • PageRank (Lecture 7).
  • [3] P. Flajolet, G. N. Martin. Probabilistic Counting Algorithms for Data Base Applications. JCSS 1985.
• Week 5 (Feb 17): Network Analysis I (Chapters 5 and 10 of [LRU]).
  • Personalized PageRank (Lecture 8).
  • [4] L. Page, S. Brin, R. Motwani, T. Winograd. The PageRank Citation Ranking: Bringing Order to the Web. 1999.
• Week 6 (Feb 24): Network Analysis II (Chapters 5 and 10 of [LRU]).
  • Local Graph Algorithms (Lecture 9).
  • Singular Value Decomposition (Lecture 10).
  • [5] R. Andersen, F. Chung, K. Lang. Local Graph Partitioning using PageRank Vectors. FOCS 2006.
• Week 7 (Mar 3): Nonnegative Matrix Factorization I (Chapter 1 of [M], Chapter 11 of [LRU]).
  • Topic Modeling (Lecture 11).
  • Nonnegative Matrix Factorization (Lecture 12).
  • [6] S. Arora, R. Ge, R. Kannan, A. Moitra. Computing a Nonnegative Matrix Factorization -- Provably. STOC 2012.
• Week 8 (Mar 10): Nonnegative Matrix Factorization II (Chapter 1 of [M], Chapter 11 of [LRU]).
  • Separability (Lecture 13).
  • Algorithms for Separable NMF (Lecture 14).
  • [7] S. Arora, R. Ge, A. Moitra. Learning Topic Models -- Going Beyond SVD. FOCS 2012.
• Week 9 (Mar 17): Non-Convex Optimization I (Chapter 7 of [A], Chapter 9 of [LRU], Chapter 8 of [M]).
  • Matrix Completion (Lecture 15).
  • Ask Me Anything (Lecture 16).
  • [8] R. Ge, C. Jin, Y. Zheng. No Spurious Local Minima in Nonconvex Low Rank Problems: A Unified Geometric Analysis. ICML 2017.
• Week 10 (Mar 24): No classes. Spring Recess.
• Week 11 (Mar 31): Non-Convex Optimization II (Chapter 7 of [A], Chapter 9 of [LRU], Chapter 8 of [M]).
  • Non-Convex Matrix Factorization (Lecture 17).
  • Tractable Non-Convex Problems (Lecture 18).
  • [9] Y. Zhang, Q. Qu, J. Wright. From Symmetry to Geometry: Tractable Nonconvex Problems. 2020.
• Week 12 (Apr 7): Theory of Deep Learning I (Chapters 9 and 10 of [A]).
  • Implicit Regularization (Lecture 19).
  • Neural Tangent Kernels (Lecture 20).
  • [10] D. Soudry, E. Hoffer, M. S. Nacson, S. Gunasekar, N. Srebro. The Implicit Bias of Gradient Descent on Separable Data. ICLR 2018.
  • [11] S. Arora, S. S. Du, W. Hu, Z. Li, R. Wang. Fine-Grained Analysis of Optimization and Generalization for Overparameterized Two-Layer Neural Networks. ICML 2019.
• Week 13 (Apr 14): Theory of Deep Learning II (Chapters 9 and 10 of [A]).
  • Self-Supervised Learning (Lecture 21).
  • Transformers Learn In-Context (Lecture 22).
  • [12] C. Tosh, A. Krishnamurthy, D. Hsu. Contrastive Estimation Reveals Topic Posterior Information to Linear Models. JMLR 2021.
  • [13] J. V. Oswald, E. Niklasson, E. Randazzo, J. Sacramento, A. Mordvintsev, A. Zhmoginov, M. Vladymyrov. Transformers Learn In-Context by Gradient Descent. ICML 2023.
• Week 14 (Apr 21): Theory of Deep Learning III (Chapters 9 and 10 of [A]).
  • TBD (Lecture 23).
  • TBD (Lecture 24).
• Additional Readings (optional):
  • Locality-Sensitive Hashing:
    • A. Gionis, P. Indyk, R. Motwani. Similarity Search in High Dimensions via Hashing. VLDB 1999.
    • A. Z. Broder, M. Charikar, A. M. Frieze, M. Mitzenmacher. Min-Wise Independent Permutations. STOC 1998.
    • M. Datar, N. Immorlica, P. Indyk, V. S. Mirrokni. Locality-Sensitive Hashing Scheme Based on p-Stable Distributions. SCG 2004.
    • R. O'Donnell, Y. Wu, Y. Zhou. Optimal Lower Bounds for Locality Sensitive Hashing (Except When q Is Tiny). ICS 2011.
    • A. Andoni, I. Razenshteyn. Optimal Data-Dependent Hashing for Approximate Near Neighbors. STOC 2015.
  • Streaming Algorithms:
    • B. H. Bloom. Space/Time Trade-Offs in Hash Coding With Allowable Errors. Commun. ACM. 1970.
    • J. S. Vitter. Random Sampling With a Reservoir. TOMS 1985.
    • N. Alon, Y. Matias, M. Szegedy. The Space Complexity of Approximating the Frequency Moments. STOC 1996.
    • P. Gopalan, T. S. Jayram, R. Krauthgamer, R. Kumar. Estimating the Sortedness of a Data Stream. SODA 2007.
    • E. Kushilevitz, N. Nisan. Communication Complexity (book). 1996.
  • Network Analysis:
    • S. Brin, L. Page. The Anatomy of a Large-Scale Hypertextual Web Search Engine. Comput. Networks. 1998.
    • J. Shi, J. Malik. Normalized Cuts and Image Segmentation. CVPR 1997.
    • R. Andersen, C. Borgs, J. T. Chayes, J. E. Hopcroft, V. S. Mirrokni, S.-H. Teng. Local Computation of PageRank Contributions. WAW 2007.
    • D. A. Spielman. Spectral and Algebraic Graph Theory (book draft). 2019.
    • S.-H. Teng. Scalable Algorithms for Data and Network Analysis (book). 2016.
  • Nonnegative Matrix Factorization:
    • S. Arora, R. Ge, Y. Halpern, D. Mimno, A. Moitra, D. Sontag, Y. Wu, M. Zhu. A Practical Algorithm for Topic Modeling with Provable Guarantees. ICML 2013.
    • S. A. Vavasis. On the Complexity of Nonnegative Matrix Factorization. SIOPT 2009.
    • D. D. Lee, H. S. Seung. Learning the Parts of Objects by Nonnegative Matrix Factorization. Nature 1999.
    • D. D. Lee, H. S. Seung. Algorithms for Non-negative Matrix Factorization. NIPS 2000.
    • N. Gillis. Nonnegative Matrix Factorization (book). 2020.
  • Non-Convex Optimization:
    • R. Ge, J. D. Lee, T. Ma. Matrix Completion has No Spurious Local Minimum. NIPS 2016.
    • J. Sun, Q. Qu, J. Wright. Complete Dictionary Recovery Over the Sphere I: Overview and the Geometric Picture. IEEE Trans. Inf. Theory. 2017.
    • R. Ge, T. Ma. On the Optimization Landscape of Tensor Decompositions. NIPS 2017.
    • C. Jin, R. Ge, P. Netrapalli, S. M. Kakade, M. I. Jordan. How to Escape Saddle Points Efficiently. ICML 2017.
    • S. Bubeck. Convex Optimization: Algorithms and Complexity (monograph). Found. Trends Mach. Learn. 2015.
  • Theoretical Deep Learning:
    • S. S. Du, X. Zhai, B. Póczos, A. Singh. Gradient Descent Provably Optimizes Over-parameterized Neural Networks. ICLR 2019.
    • Z. Allen-Zhu, Y. Li, Z. Song. A Convergence Theory for Deep Learning via Over-Parameterization. ICML 2019.
    • C. Zhang, S. Bengio, M. Hardt, B. Recht, O. Vinyals. Understanding Deep Learning (Still) Requires Rethinking Generalization. Commun. ACM. 2021.
    • R. Balestriero et al. A Cookbook of Self-Supervised Learning. 2023.
    • J. D. Lee, Q. Lei, N. Saunshi, J. Zhuo. Predicting What You Already Know Helps: Provable Self-Supervised Learning. NeurIPS 2021.
    • M. Chidambaram, C. Wu, Y. Cheng, R. Ge. Hiding Data Helps: On the Benefits of Masking for Sparse Coding. ICML 2023.
    • A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, Ł. Kaiser, I. Polosukhin. Attention Is All You Need. NIPS 2017.
    • M. Belkin, D. Hsu, S. Ma, S. Mandal. Reconciling Modern Machine Learning and the Bias-Variance Trade-off. PNAS 2019.

Grading

• Homework assignments (70%): The course includes 3 written assignments and 3 coding assignments. Students are encouraged to discuss with others, but each student must write up their solutions independently and acknowledge who they worked with.
• Final exam (30%): May 7th (Wed), 9:00-11:00am.
• Bonus points (18%): There are extra-credit questions in all assignments and the final exam.

Academic Integrity

Academic achievement is evaluated on the basis of work that a student produces independently. A student who obtains credit for work, words, or ideas that are not the products of their own effort is dishonest. Such dishonesty undermines the integrity of the academic standards of the University. Infringement of the Academic Code entails penalties ranging from reprimand to suspension, dismissal, or expulsion from the University. Students who have questions about any aspect of the Academic Code should consult the instructor or an academic dean.

Disability Policies

Brown University is committed to full inclusion of all students. Students who need accommodations should reach out to Student Accessibility Services (SAS) for assistance (sas@brown.edu, 401-863-9588, Brown SAS Website).

Religious Holidays

Students who wish to observe their religious holidays shall inform the instructor within the first four weeks of the semester, unless the religious holiday is observed in the first four weeks. In such cases, students shall notify the instructor at least five days in advance of the date when they will be absent. The instructor shall make every reasonable effort to honor the request.