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

Home

Lecture

Stochastic Gradient Descent: Non-convex Optimization Techniques

About
Privacy
Disclaimer

Graph Chatbot

Related lectures (37)

Convex Optimization: Gradient Descent Log in to Mediaspace to watch this video

Explores VC dimension, gradient descent, convex sets, and Lipschitz functions in convex optimization.

Gradient Descent: Optimization Techniques Log in to Mediaspace to watch this video

Explores gradient descent, loss functions, and optimization techniques in neural network training.

Non-Convex Optimization: Techniques and Applications Log in to Mediaspace to watch this video

Covers non-convex optimization techniques and their applications in machine learning.

Projection Matrices: Min-Cut and Gradient Descent Log in to Mediaspace to watch this video

Explores projection matrices in the context of min-cut and gradient descent algorithms, emphasizing their role in optimization.

Geodesic Convexity: Theory and Applications Log in to Mediaspace to watch this video

Explores geodesic convexity in metric spaces and its applications, discussing properties and the stability of inequalities.

Optimal Power Flow and Chebyshev Introduction Log in to Mediaspace to watch this video

Covers Optimal Power Flow solutions, SDP, Chebyshev's inequality, and probability distributions.

Constrained optimization: the basics Log in to Mediaspace to watch this video

Covers the basics of constrained optimization, including tangent directions, trust-region subproblems, and necessary optimality conditions.

Neural networks under SGD Log in to Mediaspace to watch this video

Explores the optimization of neural networks using Stochastic Gradient Descent (SGD) and the concept of dual risk versus empirical risk.

Scalable and Trustworthy Learning: Challenges and Solutions Log in to Mediaspace to watch this video

Explores challenges and solutions for scalable and trustworthy learning in heterogeneous networks, emphasizing data heterogeneity, privacy, fairness, and robustness.

Convex Optimization: Notation and Matrix Norms Log in to Mediaspace to watch this video

Introduces Convex Optimization notation, convex functions, vector norms, and matrix properties.

Relations Between Events Log in to Mediaspace to watch this video

Explores relations between events, disjunctive constraints, and modeling with binary variables in optimization problems.

Prime Number Theorem Log in to Mediaspace to watch this video

Explores the proof of the Prime Number Theorem and its implications in number theory.

Minimum Spanning Trees Log in to Mediaspace to watch this video

Covers the implementation and analysis of disjoint sets data structure and introduces the concept of minimum spanning trees.

Deep Neural Networks and Splines Log in to Mediaspace to watch this video

Covers the fundamentals of deep neural networks and splines, exploring their properties, implications, and applications in modern machine learning.

Hoare Logic: Foundations and Applications Log in to Mediaspace to watch this video

Covers Hoare Logic, its foundations, applications, and significance in program verification.

Linear Models: Part 1 Log in to Mediaspace to watch this video

Covers linear models, including regression, derivatives, gradients, hyperplanes, and classification transition, with a focus on minimizing risk and evaluation metrics.

Mean Value Theorem (Mittelwertsatz)Log in to Mediaspace to watch this video

Covers the Mean Value Theorem in differential calculus, focusing on critical points and global extrema within intervals.

Page 2 of 2