Completed
Matus Telgarsky - A Perceptron Trio - IPAM at UCLA
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
Computational vs Statistical Gaps in Learning and Optimization
Automatically move to the next video in the Classroom when playback concludes
- 1 Sitan Chen - Provably learning a multi-head attention layer - IPAM at UCLA
- 2 Jelani Nelson - New local differentially private protocols for frequency and mean estimation
- 3 Andrea Montanari - Solving overparametrized systems of nonlinear equations - IPAM at UCLA
- 4 Ankur Moitra - Learning from Dynamics - IPAM at UCLA
- 5 Surbhi Goel - Beyond Worst-case Guarantees for Sequential Prediction: Robustness via Abstention
- 6 Matus Telgarsky - A Perceptron Trio - IPAM at UCLA
- 7 Raghu Meka - Complexity of Sparse Linear Regression - IPAM at UCLA
- 8 Jelena Diakonikolas - Robust Learning of a Neuron: Bridging Computational Gaps Using Optimization
- 9 Vatsal Sharan - Memory as a lens to understand efficient learning and optimization - IPAM at UCLA
- 10 Cynthia Rush - Is It Easier to Count Communities Than Find Them? - IPAM at UCLA
- 11 Giang Tran - Fast Multipole Attention: A Divide-and-Conquer Attention Mechanism for Long Sequences
- 12 Arya Mazumdar - Sample complexity of estimation in logistic regression - IPAM at UCLA
- 13 Abhineet Agarwal - Understanding and overcoming the statistical limitations of decision trees
- 14 Vasilis Kontonis - Smoothed Analysis for Learning Concepts with Low Intrinsic Dimension
- 15 Thien Le - On the hardness of learning under symmetries - IPAM at UCLA
- 16 Pravesh Kothari - Algorithms Approaching the Threshold for Semirandom Planted Clique - IPAM at UCLA
- 17 Adel Javanmard - Learning from Aggregate Responses - IPAM at UCLA
- 18 Omer Reingold - Algorithmic Fairness, Loss Minimization and Outcome Indistinguishability
- 19 Ravi Kumar - Learning-Augmented Online Optimization - IPAM at UCLA
- 20 Wasim Huleihel - Testing Dependency of Databases - IPAM at UCLA
- 21 Pasin Manurangasi - Complex Adversarially Robust Proper Learning of Halfspaces w/ Agnostic Noise
