RL theory workshop 2023: Quanquan Gu

(55:12)

Quanquan Gu - Self-Play Preference Optimization for Language Model Alignment

(33:28)

Quanquan Gu: \

(44:7)

Quanquan Gu: On the Implicit Bias of Stochastic Gradient Descent with Moderate Learning Rate

(1:5:46)

Quanquan Gu: Benign Overfitting in Two-layer Convolutional Neural Networks

(57:2)

11/09/2021 -- Quanquan Gu (UCLA)

(1:2:25)

Quanquan Gu 20240312

(1:7:12)

OWCryo-EM Mar 2024. Quanquan Gu. CryoSTAR: Leveraging Structural Prior and Constraints

(48:16)

CAIDA Talk - February 27, 2024 - Quanquan Gu

(59:33)

On the Convergence of Monte Carlo Methods with Stochastic Gradients

(36:31)

CLOSING THE GENERALIZATION GAP OF ADAPTIVE GRADIENT METHODS IN TRAINING DEEP NEURAL NETWORKS

(59:42)

RL Theory Seminar: Dongruo Zhou

(1:16:33)

Fast Newton Hard Thresholding Pursuit for Sparsity Constrained Nonconvex Optimization

(1:57)

Epidemic Model Guided Machine Learning for COVID-19 Forecasts

(1:37:55)

[2024 Best AI Paper] Self-Play Preference Optimization for Language Model Alignment

(13:13)

[w4g0050] Causal Graph ODE: Continuous Treatment Effect Modeling in Multi-agent Dynamical Systems

(2:54)

Quanquan Liu - Differential Privacy from Locally Adjustable Graph Algorithms

(41:7)

Is Neuron Coverage a Meaningful Measure for Testing Deep Neural Networks? (Teaser, ESEC/FSE 2020)

(1:59)