Ma, Tengyu

Tengyu Ma

Title	Sources
Asymptotic behavior of solutions to a class of fourth-order nonlinear evolution equations with dispersive and dissipative terms
Beyond Lazy Training for Over-parameterized Tensor Decomposition
Data-dependent Sample Complexity of Deep Neural Networks via Lipschitz Augmentation
Federated Accelerated Stochastic Gradient Descent
Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss
Matrix Completion has No Spurious Local Minimum
Model-based Adversarial Meta-Reinforcement Learning
MOPO: Model-based Offline Policy Optimization
A Non-generative Framework and Convex Relaxations for Unsupervised Learning
On a conjecture of Butler and Graham
On Communication Cost of Distributed Statistical Estimation and Dimensionality
On the Optimization Landscape of Tensor Decompositions
Regularization Matters: Generalization and Optimization of Neural Nets v.s. their Induced Kernel
Self-training Avoids Using Spurious Features Under Domain Shift
Stability criteria on delay-dependent robust stability for uncertain neutral stochastic nonlinear systems with time-delay
Sum-of-Squares Lower Bounds for Sparse PCA
Towards Explaining the Regularization Effect of Initial Large Learning Rate in Training Neural Networks
Variable-Viewpoint Representations for Object Recognition
Verified Uncertainty Calibration