Explore a lecture by Aarti Singh from Carnegie Mellon University on computationally tractable and near-optimal design of experiments, presented as part of the Computational Challenges in Machine Learning series at the Simons Institute. Delve into advanced concepts in experimental design, focusing on methods that balance computational efficiency with near-optimal performance. Gain insights into cutting-edge approaches for tackling complex experimental design problems in machine learning and data science.
Computationally Tractable and Near Optimal Design of Experiments
Overview
Syllabus
Computationally Tractable and Near Optimal Design of Experiments
Taught by
Simons Institute
Related Courses
-
Power of Active Sampling for Unsupervised Learning
-
Sample-Complexity of Estimating Convolutional and Recurrent Neural Networks
-
Long-context Attention in Near-Linear Time
-
Affective Computing
-
Tractable Learning in Structured Probability Spaces
-
Probabilistic Circuits: Deep Probabilistic Models with Tractable Inference
