Name: UCLA Artificial General Intelligence Lab
Type: User
Company: Department of Computer Science, UCLA
Bio: The artificial general intelligence lab (formerly known as statistical machine learning lab) at UCLA is led by Prof. Quanquan Gu in the computer science dept.
Blog: http://web.cs.ucla.edu/~qgu
UCLA Artificial General Intelligence Lab's Projects
Fast Algorithm for Sparse Tensor-variate Gaussian Graphical Models via Alternating Gradient Descent
Benign Overfitting in Two-layer Convolutional Neural Networks
Collaborative Learning with Incomplete and Noisy Knowledge
High-dimensional Time Series Clustering via Cross-Predictability
Fundamentals of Artificial Intelligence
Machine Learning
Machine Learning
A web app for ranking computer science departments according to their research output in selective venues.
Nearly Optimal Algorithms for Linear Contextual Bandits with Adversarial Corruptions
A Simple and Provably Efficient Algorithm for Asynchronous Federated Contextual Linear Bandits
Fast Local minimA finding with third-order SmootHness (FLASH)
A Frank-Wolfe Framework for Efficient and Effective Adversarial Attacks (AAAI'20)
local minima finding algorithm that can escape from saddle point in one step
new deep learning algorithms based Hamiltonian Monte Carlo and Adam
Computationally Efficient Horizon-Free Reinforcement Learning for Linear Mixture MDPs
Locally Differentially Private Reinforcement Learning for Linear Mixture Markov Decision Processes
Towards Understanding the Mixture-of-Experts Layer in Deep Learning
Risk Bounds of Multi-Pass SGD for Least Squares in the Interpolation Regime
fast nonconvex algorithm for covariate-adjusted precision matrix estimation/conditional Gaussian graphical model estimation
fast nonconvex algorithm for inductive matrix completion
nonconvex Low-rank matrix factorization
fast nonconvex algorithm for latent variable Gaussian graphical models
fast nonconvex algorithm for robust PCA
Partially Adaptive Momentum Estimation method in the paper "Closing the Generalization Gap of Adaptive Gradient Methods in Training Deep Neural Networks" (accepted by IJCAI 2020)