Tengyu Ma

发表

Random Walks on Context Spaces: Towards an Explanation of the Mysteries of Semantic Word Embeddings pdf

Sanjeev Arora, Yuanzhi Li, Yingyu Liang, 2015, ArXiv.

Polynomial-Time Tensor Decompositions with Sum-of-Squares

Tengyu Ma, Jonathan Shi, David Steurer, 2016, 2016 IEEE 57th Annual Symposium on Foundations of Computer Science (FOCS).

Optimal Design of Process Flexibility for General Production Systems pdf

Xi Chen, Yuan Zhou, Tengyu Ma, 2018, Oper. Res..

Generalization and Equilibrium in Generative Adversarial Nets (GANs)

Yingyu Liang, Tengyu Ma, Sanjeev Arora, 2017, ICML.

Beyond Lazy Training for Over-parameterized Tensor Decomposition pdf

Tengyu Ma, Jason D. Lee, Xiang Wang, 2020, NeurIPS.

A Model-based Approach for Sample-efficient Multi-task Reinforcement Learning pdf

Tengyu Ma, Nicholas C. Landolfi, Garrett Thomas, 2019, ArXiv.

The Simulated Greedy Algorithm for Several Submodular Matroid Secretary Problems

Tengyu Ma, Yajun Wang, Bo Tang, 2013, STACS.

Matrix Completion has No Spurious Local Minimum

Tengyu Ma, Jason D. Lee, Rong Ge, 2016, NIPS.

Improved Sample Complexities for Deep Neural Networks and Robust Classification via an All-Layer Margin

Colin Wei, Tengyu Ma, Tengyu Ma, 2020, ICLR.

Better Generalization with On-the-fly Dataset Denoising

Tengyu Ma, Yann Dauphin, Jiaming Song, 2018 .

Identity Matters in Deep Learning pdf

Tengyu Ma, Moritz Hardt, Tengyu Ma, 2016, ICLR.

Provable learning of noisy-OR networks

Sanjeev Arora, Tengyu Ma, Andrej Risteski, 2016, STOC.

Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss

Colin Wei, Tengyu Ma, Adrien Gaidon, 2019, NeurIPS.

Optimal Regularization Can Mitigate Double Descent pdf

Tengyu Ma, Prayaag Venkat, Preetum Nakkiran, 2020, ICLR.

Improved Sample Complexities for Deep Networks and Robust Classification via an All-Layer Margin pdf

Colin Wei, Tengyu Ma, 2019, ArXiv.

The Implicit and Explicit Regularization Effects of Dropout pdf

Colin Wei, Tengyu Ma, Sham Kakade, 2020, ICML.

Learning Self-Correctable Policies and Value Functions from Demonstrations with Negative Sampling pdf

Tengyu Ma, Huazhe Xu, Yuping Luo, 2019, ICLR.

Finding Approximate Local Minima for Nonconvex Optimization in Linear Time pdf

Tengyu Ma, Zeyuan Allen Zhu, Naman Agarwal, 2016, ArXiv.

Why Do Local Methods Solve Nonconvex Problems?

Tengyu Ma, Tengyu Ma, 2020, Beyond the Worst-Case Analysis of Algorithms.

In-N-Out: Pre-Training and Self-Training using Auxiliary Information for Out-of-Distribution Robustness pdf

Tengyu Ma, Fereshte Khani, Percy Liang, 2020, ICLR.

Distributed Stochastic Variance Reduced Gradient Methods pdf

Tengyu Ma, Qihang Lin, Jason D. Lee, 2015, ArXiv.

Learning Over-Parametrized Two-Layer ReLU Neural Networks beyond NTK pdf

Yuanzhi Li, Tengyu Ma, Hongyang R. Zhang, 2020, COLT 2020.

Variable-Viewpoint Representations for 3D Object Recognition pdf

Maithilee Kunda, Tengyu Ma, Xiaohan Wang, 2020, ArXiv.

On the Expressivity of Neural Networks for Deep Reinforcement Learning

Tengyu Ma, Kefan Dong, Yuping Luo, 2020, ICML.

Sum-of-Squares Lower Bounds for Sparse PCA

Avi Wigderson, Tengyu Ma, A. Wigderson, 2015, NIPS.

On the Ability of Neural Nets to Express Distributions pdf

Tengyu Ma, Andrej Risteski, Rong Ge, 2017, COLT.

Verified Uncertainty Calibration

Tengyu Ma, Percy Liang, Ananya Kumar, 2019, NeurIPS.

On the Margin Theory of Feedforward Neural Networks pdf

Qiang Liu, Colin Wei, Tengyu Ma, 2018, ArXiv.

Online Learning of Eigenvectors

Tengyu Ma, Elad Hazan, Dan Garber, 2015, ICML.

Decomposing Overcomplete 3rd Order Tensors using Sum-of-Squares Algorithms pdf

Tengyu Ma, Rong Ge, Tengyu Ma, 2015, APPROX-RANDOM.

A La Carte Embedding: Cheap but Effective Induction of Semantic Feature Vectors pdf

Mikhail Khodak, Sanjeev Arora, Yingyu Liang, 2018, ACL.

Theoretical Analysis of Self-Training with Deep Networks on Unlabeled Data pdf

Colin Wei, Tengyu Ma, Yining Chen, 2020, ArXiv.

Understanding Self-Training for Gradual Domain Adaptation pdf

Tengyu Ma, Percy Liang, Ananya Kumar, 2020, ICML.

Non-convex Optimization for Machine Learning: Design, Analysis, and Understanding

Tengyu Ma, Tengyu Ma, 2017 .

Communication lower bounds for statistical estimation problems via a distributed data processing inequality

David P. Woodruff, Mark Braverman, Tengyu Ma, 2015, STOC.

Model-based Adversarial Meta-Reinforcement Learning pdf

Guangwen Yang, Tengyu Ma, Garrett Thomas, 2020, NeurIPS.

Lower Bound for High-Dimensional Statistical Learning Problem via Direct-Sum Theorem pdf

Tengyu Ma, Ankit Garg, Huy L. Nguyen, 2014, ArXiv.

A Simple but Tough-to-Beat Baseline for Sentence Embeddings

Sanjeev Arora, Yingyu Liang, Tengyu Ma, 2017, ICLR.

Federated Accelerated Stochastic Gradient Descent pdf

Tengyu Ma, Honglin Yuan, Tengyu Ma, 2020, NeurIPS.

Robust and On-the-fly Dataset Denoising for Image Classification pdf

Tengyu Ma, Yann Dauphin, Lunjia Hu, 2020, ECCV.

Gradient Descent Learns Linear Dynamical Systems pdf

Tengyu Ma, Benjamin Recht, Moritz Hardt, 2016, J. Mach. Learn. Res..

Data-dependent Sample Complexity of Deep Neural Networks via Lipschitz Augmentation

Colin Wei, Tengyu Ma, Tengyu Ma, 2019, NeurIPS.

Finding approximate local minima faster than gradient descent

Tengyu Ma, Zeyuan Allen Zhu, Naman Agarwal, 2016, STOC.

CS229 Lecture notes

Tengyu Ma, Andrew Kian Poh. Ng, Tengyu Ma, 2007 .

The Toybox Dataset of Egocentric Visual Object Transformations

Maithilee Kunda, Tengyu Ma, Xiaohan Wang, 2018, 1806.06034.

On a conjecture of Butler and Graham

Tengyu Ma, Xiaoming Sun, Huacheng Yu, 2013, Des. Codes Cryptogr..

A Non-generative Framework and Convex Relaxations for Unsupervised Learning

Tengyu Ma, Elad Hazan, 2016, NIPS.

Linear Algebraic Structure of Word Senses, with Applications to Polysemy

Sanjeev Arora, Yuanzhi Li, Yingyu Liang, 2016, TACL.

Provable Bounds for Learning Some Deep Representations pdf

Aditya Bhaskara, Sanjeev Arora, Tengyu Ma, 2013, ICML.

Observer-Based Finite-Time Adaptive Sliding Mode Control for Itô Stochastic Jump Systems With Actuator Degradation

Tengyu Ma, Huayi Li, Longsuo Li, 2020, IEEE Access.

Towards Explaining the Regularization Effect of Initial Large Learning Rate in Training Neural Networks

Colin Wei, Yuanzhi Li, Tengyu Ma, 2019, NeurIPS.

Document-Level Relation Extraction with Adaptive Thresholding and Localized Context Pooling pdf

Jing Huang, Tengyu Ma, Wenxuan Zhou, 2020, AAAI.

Why are deep nets reversible: A simple theory, with implications for training pdf

Sanjeev Arora, Yingyu Liang, Tengyu Ma, 2015, ArXiv.

On the Performance of Thompson Sampling on Logistic Bandits

Tengyu Ma, Shi Dong, Benjamin Van Roy, 2019, COLT.

RAND-WALK: A Latent Variable Model Approach to Word Embeddings

Sanjeev Arora, Yuanzhi Li, Yingyu Liang, 2015 .

Algorithmic Framework for Model-based Deep Reinforcement Learning with Theoretical Guarantees pdf

Yuandong Tian, Trevor Darrell, Yuanzhi Li, 2018, ICLR.

Algorithmic Regularization in Over-parameterized Matrix Sensing and Neural Networks with Quadratic Activations

Hongyang Zhang, Yuanzhi Li, Tengyu Ma, 2017, COLT.

Regularization Matters: Generalization and Optimization of Neural Nets v.s. their Induced Kernel

Colin Wei, Tengyu Ma, Qiang Liu, 2018, NeurIPS.

Heteroskedastic and Imbalanced Deep Learning with Adaptive Regularization pdf

Junwei Lu, Tengyu Ma, Nikos Arechiga, 2020, ArXiv.

Entity and Evidence Guided Relation Extraction for DocRED pdf

Tengyu Ma, Guangtao Wang, Jing Huang, 2020, ArXiv.

Stochastic Variance Reduced Gradient Methods by Sampling Extra Data with Replacement

Tianbao Yang, Tengyu Ma, Qihang Lin, 2017 .

Approximability of Discriminators Implies Diversity in GANs pdf

Yu Bai, Tengyu Ma, Andrej Risteski, 2018, ICLR.

Seeing Neural Networks Through a Box of Toys: The Toybox Dataset of Visual Object Transformations pdf

Maithilee Kunda, Tengyu Ma, Xiaohan Wang, 2018, ArXiv.

Active Online Domain Adaptation pdf

Haipeng Luo, Tengyu Ma, Chicheng Zhang, 2020, ArXiv.

MOPO: Model-based Offline Policy Optimization pdf

Lantao Yu, Stefano Ermon, Tengyu Ma, 2020, NeurIPS.

Simple, Efficient, and Neural Algorithms for Sparse Coding pdf

Sanjeev Arora, Tengyu Ma, Ankur Moitra, 2015, COLT.

More Algorithms for Provable Dictionary Learning pdf

Aditya Bhaskara, Sanjeev Arora, Tengyu Ma, 2014, ArXiv.

The Simulated Greedy Algorithm for Several Submodular Matroid Secretary Problems

Tengyu Ma, Yajun Wang, Bo Tang, 2011, Theory of Computing Systems.

Meta-learning Transferable Representations with a Single Target Domain pdf

Colin Wei, Tengyu Ma, Hong Liu, 2020, ArXiv.

Learning One-hidden-layer Neural Networks with Landscape Design pdf

Tengyu Ma, Jason D. Lee, Rong Ge, 2017, ICLR.

Bootstrapping the Expressivity with Model-based Planning pdf

Tengyu Ma, Yuping Luo, Kefan Dong, 2019, ArXiv.

A Latent Variable Model Approach to PMI-based Word Embeddings

Sanjeev Arora, Yuanzhi Li, Yingyu Liang, 2015, TACL.

Distributed Stochastic Variance Reduced Gradient Methods and A Lower Bound for Communication Complexity

Tianbao Yang, Tengyu Ma, Qihang Lin, 2015 .

On the optimization landscape of tensor decompositions

Tengyu Ma, Rong Ge, Tengyu Ma, 2017, Mathematical Programming.

Algorithmic Regularization in Over-parameterized Matrix Recovery pdf

Yuanzhi Li, Tengyu Ma, Hongyang Zhang, 2017, ArXiv.

Composed Fine-Tuning: Freezing Pre-Trained Denoising Autoencoders for Improved Generalization pdf

Tengyu Ma, Percy Liang, Sang Michael Xie, 2020, ICML.

Explaining Adversarial Examples with Knowledge Representation

Tengyu Ma, Xingyu Zhou, Huahong Zhang, 2018 .

Fixup Initialization: Residual Learning Without Normalization pdf

Tengyu Ma, Hongyi Zhang, Yann Dauphin, 2019, ICLR.

Self-training Avoids Using Spurious Features Under Domain Shift pdf

Colin Wei, Tengyu Ma, Ananya Kumar, 2020, NeurIPS.

A New Variation of Hat Guessing Games pdf

Tengyu Ma, Xiaoming Sun, Huacheng Yu, 2011, COCOON.

On Communication Cost of Distributed Statistical Estimation and Dimensionality

Tengyu Ma, Ankit Garg, Huy L. Nguyen, 2014, NIPS.

Provable Algorithms for Inference in Topic Models

Sanjeev Arora, Tengyu Ma, Ankur Moitra, 2016, ICML.

Shape Matters: Understanding the Implicit Bias of the Noise Covariance pdf

Colin Wei, Tengyu Ma, Jason D. Lee, 2020, COLT.

MiW: A domain specific modeling environment for complex molecular systems

Tengyu Ma, Janos Sallai, 2017, ICCS.

Fine-Grained Gap-Dependent Bounds for Tabular MDPs via Adaptive Multi-Step Bootstrap pdf

Tengyu Ma, Simon S. Du, Haike Xu, 2021, COLT.

Calibrating Predictions to Decisions: A Novel Approach to Multi-Class Calibration pdf

Stefano Ermon, Tengyu Ma, Shengjia Zhao, 2021, NeurIPS.

Variance-reduced First-order Meta-learning for Natural Language Processing Tasks

Tengyu Ma, Quanquan Gu, Lingxiao Wang, 2021, NAACL.

Active Online Learning with Hidden Shifting Domains

Haipeng Luo, Tengyu Ma, Chicheng Zhang, 2021, AISTATS.

Joint System-Wise Optimization for Pipeline Goal-Oriented Dialog System pdf

Tengyu Ma, Zichuan Lin, Bowen Zhou, 2021, ArXiv.

Provable Guarantees for Self-Supervised Deep Learning with Spectral Contrastive Loss pdf

Colin Wei, Tengyu Ma, Adrien Gaidon, 2021, ArXiv.

Optimal Regularization Can Mitigate Double Descent pdf

Tengyu Ma, Prayaag Venkat, Preetum Nakkiran, 2021, ICLR.

Document-Level Relation Extraction with Adaptive Thresholding and Localized Context Pooling

Tengyu Ma, Wenxuan Zhou, Kevin Huang, 2020, AAAI.

Theoretical Analysis of Self-Training with Deep Networks on Unlabeled Data pdf

Colin Wei, Tengyu Ma, Kendrick Shen, 2020, ICLR.

Label Noise SGD Provably Prefers Flat Global Minimizers pdf

Tengyu Ma, Jason D. Lee, Alex Damian, 2021, NeurIPS.

Provable Model-based Nonlinear Bandit and Reinforcement Learning: Shelve Optimism, Embrace Virtual Curvature pdf

Tengyu Ma, Kefan Dong, Jiaqi Yang, 2021, ArXiv.

Random walks on discourse spaces: a new generative language model with applications to semantic word embeddings

Sanjeev Arora, Yingyu Liang, Tengyu Ma, 2015 .

Improved Sample Complexities for Deep Networks and Robust Classification via an All-Layer Margin pdf

Colin Wei, Tengyu Ma, Tengyu Ma, 2019, ICLR.

Learning Over-Parametrized Two-Layer Neural Networks beyond NTK

Tengyu Ma, Yuanzhi Li, Hongyang R. Zhang, 2020, COLT.

Individual Calibration with Randomized Forecasting

Stefano Ermon, Tengyu Ma, Shengjia Zhao, 2020, ICML.

On the Expressivity of Neural Networks for Deep Reinforcement Learning

Tengyu Ma, Kefan Dong, Yuping Luo, 2019, ICML.