Model Selection and Local Geometry

Related lectures (30)

Page 1 of 3

Explores causal inference, directed graphs, and fairness in algorithms, emphasizing conditional independence and the implications of DAGs.

Covers the fundamentals of connectivity in graph theory, including paths, cycles, and spanning trees.

Explores the properties of undirected and directed graphs, emphasizing connectivity and network topology modeling.

Covers graph algorithms, modeling relationships between objects, and traversal techniques like BFS and DFS.

Explores coordination among agents in networked control systems through graph theory and real-world examples.

Explores dynamic programming for the Knapsack problem, discussing strategies, algorithms, NP-hardness, and time complexity analysis.

Explores causal inference through learning graph structures for causal reasoning from observational data.

Covers topics like DFS output, edge classification, acyclic graphs, correctness, time analysis, SCCs, and the Topological Sort algorithm.

Covers the concept of the exponential family and discusses forward and backward maps, expensive computations, parameters, functions, and convexity.

Covers the concept of maximum flow-minimum cut in directed graphs with capacity constraints.