Is Optimization the Right Language to Understand Deep Learning? - Sanjeev Arora
Explore deep learning optimization, generalization, and neural tangent kernels with Sanjeev Arora. Gain insights into training wide networks and matrix completion techniques.
Finding Low-Rank Matrices - From Matrix Completion to Recent Trends
Explore low-rank matrix recovery, from matrix completion to recent trends, covering theoretical foundations and applications in signal processing and machine learning.
The Convex Geometry of Blind Deconvolution and Matrix Completion Revisited
Explores convex geometry in blind deconvolution and matrix completion, analyzing dimensional factors in noise bounds and proposing alternative error scaling approaches for low-rank matrix recovery problems.
Louis Theran: Rigidity of Random Graphs in Higher Dimensions
Explore rigidity properties of random graphs in higher dimensions and their connection to matrix completion, with insights on thresholds and optimal conditions.
Power of Active Sampling for Unsupervised Learning
Explore active sampling techniques for unsupervised learning, focusing on matrix completion, graphical models, and clustering. Learn about statistical tradeoffs and computational complexity.
Generalization in Deep Learning Through the Lens of Implicit Rank Minimization
Explores implicit regularization in deep learning through matrix and tensor factorizations, revealing tendencies towards low ranks. Discusses implications for generalization and potential improvements in neural network design.
Analyzing Optimization and Generalization in Deep Learning via Dynamics of Gradient Descent
Explore deep learning optimization and generalization through gradient descent dynamics, focusing on implicit preconditioning and its impact on matrix completion problems.
Implicit Regularization I
Explore implicit regularization in deep learning, covering boosting, complexity control, optimization landscapes, and stochastic gradient descent for effective model training.
Can Non-Convex Optimization Be Robust?
Explore non-convex optimization's robustness, examining locally optimizable functions, perturbed objectives, and matrix completion. Insights on empirical vs. population risk and semi-random adversaries.
Nonconvex Optimization in Matrix Optimization and Distributionally Robust Optimization
Explore nonconvex optimization in matrix and distributionally robust contexts, covering algorithms, complexity, and applications in machine learning with Stephen Wright.
Better Understanding of Non-convex Methods in Machine Learning
Exploring non-convex optimization in machine learning, focusing on matrix completion and neural network architectures. Insights into algorithmic approaches for complex, high-dimensional models.
Inference and Uncertainty Quantification for Noisy Matrix Completion - Lecture 5
Explore inference and uncertainty quantification for noisy matrix completion, focusing on de-biased estimators and their distributional characterizations for optimal confidence interval construction.
Random Initialization and Implicit Regularization in Nonconvex Statistical Estimation - Lecture 2
Explore nonconvex optimization in statistical estimation, focusing on gradient descent's convergence to optimal solutions without explicit regularization or careful initialization.
Distance Metric Learning and Outlier Detection in Data Mining - Spring 2023
Delve into advanced data mining concepts, focusing on distance metric learning, outlier detection techniques, and practical applications of DBSCAN for effective data analysis.
Matrix Completion and PageRank in Data Mining - Spring 2023
Dive into matrix completion techniques and PageRank algorithms, exploring fundamental concepts for data mining and graph analysis applications.