Zeyuan Allen-Zhu
3.66K subscribers
49:04
Physics of Language Models: Part 2.2, How to Learn From Mistakes on Grade-School Math Problems
Zeyuan Allen-Zhu
916 views • 3 weeks ago
1:00:53
Physics of Language Models: Part 2.1, Grade-School Math and the Hidden Reasoning Process
Zeyuan Allen-Zhu
5.6K views • 1 month ago
1:53:43
ICML 2024 Tutorial: Physics of Language Models
Zeyuan Allen-Zhu
28K views • 2 months ago
1:39:15
Physics of Language Models: Part 1, Context-Free Grammar
Zeyuan Allen-Zhu
9.3K views • 11 months ago
1:18:49
Physics of Language Models: Part 3.1 + 3.2, Knowledge Storage, Extraction and Manipulation
Zeyuan Allen-Zhu
7K views • 11 months ago
1:08:41
Why Does Deep Learning Perform Deep Learning - MSR AI Seminar 08/11/2020
Zeyuan Allen-Zhu
4.1K views • 4 years ago
1:11:59
Backward Feature Correction: How Deep Learning Performs Deep Learning (May 2020 by Yuanzhi Li)
Zeyuan Allen-Zhu
1.5K views • 4 years ago
10:05
Katyusha X: Practical Momentum Method for Stochastic Sum-of-Nonconvex Optimization
Zeyuan Allen-Zhu
771 views • 6 years ago
47:08
Optimal Experimental Design via A New Regret Minimization Framework
Zeyuan Allen-Zhu
678 views • 6 years ago
52:31
How to Swing By Saddle Points: Faster Non-Convex Optimization Than SGD
Zeyuan Allen-Zhu
1K views • 6 years ago
2:06:28
ICML 2017 Tutorial: Recent Advances in Stochastic Convex and Non-Convex Optimization (audio fixed)
Zeyuan Allen-Zhu
7.3K views • 6 years ago
33:20
First Efficient Convergence for Streaming k-PCA: a Global, Gap-Free, and Near-Optimal Rate
Zeyuan Allen-Zhu
369 views • 7 years ago
2:06:28
ICML 2017 Tutorial: Recent Advances in Stochastic Convex and Non-Convex Optimization
Zeyuan Allen-Zhu
4K views • 7 years ago
15:10
Natasha: Faster Non-Convex Stochastic Optimization via Strongly Non-Convex Parameter
Zeyuan Allen-Zhu
404 views • 7 years ago
18:28
Follow the Compressed Leader: Faster Online Learning of Eigenvectors and Faster MMWU
Zeyuan Allen-Zhu
332 views • 7 years ago
5:10
Optimal Black-Box Reductions Between Optimization Objectives
Zeyuan Allen-Zhu
491 views • 7 years ago
8:11
LazySVD: Even Faster SVD Decomposition Yet Without Agonizing Pain
Zeyuan Allen-Zhu
1.1K views • 7 years ago
43:47
Three ICML 2016 Talks on Optimization
Zeyuan Allen-Zhu
2K views • 8 years ago
19:06
Nearly-Linear Time Positive LP Solver with Faster Convergence Rate (STOC 2015)
Zeyuan Allen-Zhu
606 views • 9 years ago
26:43
Using Optimization to Solve Positive LPs Faster in Parallel
Zeyuan Allen-Zhu
317 views • 9 years ago
23:44
Linear Coupling of Gradient and Mirror Descent
Zeyuan Allen-Zhu
3.2K views • 9 years ago
17:26
Knightian Self Uncertainty in the VCG Mechanism for Unrestricted Combinatorial Auctions
Zeyuan Allen-Zhu
488 views • 10 years ago
End of Videos