Mediaspace scheduled maintenance: Aug 25, 2026 07:00 - 12:00 AM. During this time, videos will be temporarily unavailable. Check status updates.

Course

EE-556: Mathematics of data: from theory to computation

Lectures in this course (118)

Stochastic Gradient Descent Convergence Proof

Explores the convergence proof of Stochastic Gradient Descent with strongly-convex functions and the impact of step-size on convergence properties.

Complexity Analysis of FGD Algorithm

Analyzes the complexity of the FGD algorithm in terms of computational and memory requirements.

Mirror Prox: Optimization and Norms

Explores Mirror Prox optimization, argmin function, norms, and their practical applications in optimization problems.

Algorithms for Composite Optimization

Explores algorithms for composite optimization, including proximal operators and gradient methods, with examples and theoretical bounds.

Constraint Formulation and Lagrangian Dual Optimum

Explains constraint formulation using Lagrangian and augmented Lagrangian functions.

Proximal Operators and Constrained Optimization

Introduces proximal operators, gradient methods, and constrained optimization, exploring their convergence and practical applications.

Constrained Convex Optimization: Min-Max Formulation and Fenchel Conjugation

Explores constrained convex optimization with min-max formulation and Fenchel conjugation.

Parametric Models: Estimation and Optimization

Explores parametric models, estimation techniques, regression models, and score-based classifiers in data analysis.

Time-Data Tradeoffs and Sparse Representations

Explores time-data trade-offs, sparse representations, and convexity in mathematical data analysis.

Trade-offs in Data and Time

Explores trade-offs between data and time in computational problems, emphasizing diminishing returns and continuous trade-offs.

Optimization Trade-offs: Variance Reduction and Statistical Dimension

Explores optimization trade-offs, variance reduction, statistical dimension, and convergence analysis in optimization algorithms.

Deep Learning: Theory and Applications

Explores the mathematics of deep learning, neural networks, and their applications in computer vision tasks, addressing challenges and the need for robustness.

Challenges in DL/ML Applications

Explores challenges in deep learning and machine learning applications, covering surveillance, privacy, manipulation, fairness, interpretability, energy efficiency, cost, and generalization.

Deep Learning: Theory and Practice

By Prof. Volkan Cevher delves into the mathematics of deep learning, exploring model complexity, risk trade-offs, and the generalization mystery.

Implicit Bias in Machine Learning

Explores implicit bias, gradient descent, stability in optimization algorithms, and generalization bounds in machine learning.

Double Descent Curves: Overparametrization

Explores double descent curves and overparametrization in machine learning models, highlighting the risks and benefits.

Deep Learning III

Delves into deep learning optimization, challenges, SGD variants, critical points, overparametrized networks, and adaptive methods.

Adaptive Gradient Methods: Theory and Applications

Explores adaptive gradient methods, their properties, convergence, and comparison with traditional optimization algorithms.

Graphical Model Learning: M-Estimator Examples

Explores graphical model learning with M-estimators, Gaussian process regression, Google PageRank modeling, density estimation, and generalized linear models.

Structures in Non-Convex Optimization

Delves into structures in non-convex optimization, emphasizing scalable optimization for deep learning.