Tengyu Ma - RankMe

218 papers A* 77A 4Misc 1Journal 118Unranked 16

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Configuration-to-Performance Scaling Law with Neural Ansatz. CoRR Huaqing Zhang, Kaiyue Wen, Tengyu Ma
2026	J	`jnl`	Divide-and-Conquer CoT: RL for Reducing Latency via Parallel Reasoning. CoRR Arvind V. Mahankali, Kaiyue Wen, Tengyu Ma
2025	J	`jnl`	Fantastic Pretraining Optimizers and Where to Find Them. CoRR Kaiyue Wen, David Hall, Tengyu Ma, Percy Liang
2025	A*	`conf`	Non-Asymptotic Length Generalization. ICML Thomas Chen, Tengyu Ma, Zhiyuan Li
2025	J	`jnl`	Non-Asymptotic Length Generalization. CoRR Thomas Chen, Tengyu Ma, Zhiyuan Li
2025	A*	`conf`	STP: Self-play LLM Theorem Provers with Iterative Conjecturing and Proving. ICML Kefan Dong, Tengyu Ma
2025	J	`jnl`	STP: Self-play LLM Theorem Provers with Iterative Conjecturing and Proving. CoRR Kefan Dong, Tengyu Ma
2025	A*	`conf`	Understanding Warmup-Stable-Decay Learning Rates: A River Valley Loss Landscape View. ICLR Kaiyue Wen, Zhiyuan Li, Jason S. Wang, David Leo Wright Hall, Percy Liang, Tengyu Ma
2024	A*	`conf`	Chain of Thought Empowers Transformers to Solve Inherently Serial Problems. ICLR Zhiyuan Liu, Hong Liu, Denny Zhou, Tengyu Ma
2024	J	`jnl`	Chain of Thought Empowers Transformers to Solve Inherently Serial Problems. CoRR Zhiyuan Li, Hong Liu, Denny Zhou, Tengyu Ma
2024	J	`jnl`	Formal Theorem Proving by Rewarding LLMs to Decompose Proofs Hierarchically. CoRR Kefan Dong, Arvind V. Mahankali, Tengyu Ma
2024	A*	`conf`	Large Language Models as Tool Makers. ICLR Tianle Cai, Xuezhi Wang, Tengyu Ma, Xinyun Chen, Denny Zhou
2024	J	`jnl`	Linguistic Calibration of Language Models. CoRR Neil Band, Xuechen Li, Tengyu Ma, Tatsunori Hashimoto
2024	A*	`conf`	Linguistic Calibration of Long-Form Generations. ICML Neil Band, Xuechen Li, Tengyu Ma, Tatsunori Hashimoto
2024	A*	`conf`	One Step of Gradient Descent is Provably the Optimal In-Context Learner with One Layer of Linear Self-Attention. ICLR Arvind V. Mahankali, Tatsunori Hashimoto, Tengyu Ma
2024	A*	`conf`	Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training. ICLR Hong Liu, Zhiyuan Li, David Leo Wright Hall, Percy Liang, Tengyu Ma
2024	J	`jnl`	Understanding Warmup-Stable-Decay Learning Rates: A River Valley Loss Landscape Perspective. CoRR Kaiyue Wen, Zhiyuan Li, Jason S. Wang, David Hall, Percy Liang, Tengyu Ma
2023	A*	`conf`	A theoretical study of inductive biases in contrastive learning. ICLR Jeff Z. HaoChen, Tengyu Ma
2023	A*	`conf`	Asymptotic Instance-Optimal Algorithms for Interactive Decision Making. ICLR Kefan Dong, Tengyu Ma
2023	A*	`conf`	Beyond NTK with Vanilla Gradient Descent: A Mean-Field Analysis of Neural Networks with Polynomial Width, Samples, and Time. NeurIPS Arvind V. Mahankali, Haochen Zhang, Kefan Dong, Margalit Glasgow, Tengyu Ma
2023	J	`jnl`	Beyond NTK with Vanilla Gradient Descent: A Mean-Field Analysis of Neural Networks with Polynomial Width, Samples, and Time. CoRR Arvind V. Mahankali, Jeff Z. HaoChen, Kefan Dong, Margalit Glasgow, Tengyu Ma
2023	A*	`conf`	Data Selection for Language Models via Importance Resampling. NeurIPS Sang Michael Xie, Shibani Santurkar, Tengyu Ma, Percy Liang
2023	J	`jnl`	Data Selection for Language Models via Importance Resampling. CoRR Sang Michael Xie, Shibani Santurkar, Tengyu Ma, Percy Liang
2023	A*	`conf`	DoReMi: Optimizing Data Mixtures Speeds Up Language Model Pretraining. NeurIPS Sang Michael Xie, Hieu Pham, Xuanyi Dong, Nan Du, Hanxiao Liu, Yifeng Lu, Percy Liang, Quoc V. Le, Tengyu Ma, Adams Wei Yu
2023	J	`jnl`	DoReMi: Optimizing Data Mixtures Speeds Up Language Model Pretraining. CoRR Sang Michael Xie, Hieu Pham, Xuanyi Dong, Nan Du, Hanxiao Liu, Yifeng Lu, Percy Liang, Quoc V. Le, Tengyu Ma, Adams Wei Yu
2023	A*	`conf`	First Steps Toward Understanding the Extrapolation of Nonlinear Models to Unseen Domains. ICLR Kefan Dong, Tengyu Ma
2023	A*	`conf`	How Sharpness-Aware Minimization Minimizes Sharpness? ICLR Kaiyue Wen, Tengyu Ma, Zhiyuan Li
2023	J	`jnl`	Large Language Models as Tool Makers. CoRR Tianle Cai, Xuezhi Wang, Tengyu Ma, Xinyun Chen, Denny Zhou
2023	J	`jnl`	Larger language models do in-context learning differently. CoRR Jerry W. Wei, Jason Wei, Yi Tay, Dustin Tran, Albert Webson, Yifeng Lu, Xinyun Chen, Hanxiao Liu, Da Huang, Denny Zhou, Tengyu Ma
2023	A*	`conf`	Max-Margin Works while Large Margin Fails: Generalization without Uniform Convergence. ICLR Margalit Glasgow, Colin Wei, Mary Wootters, Tengyu Ma
2023	J	`jnl`	One Step of Gradient Descent is Provably the Optimal In-Context Learner with One Layer of Linear Self-Attention. CoRR Arvind V. Mahankali, Tatsunori B. Hashimoto, Tengyu Ma
2023	A*	`conf`	Same Pre-training Loss, Better Downstream: Implicit Bias Matters for Language Models. ICML Hong Liu, Sang Michael Xie, Zhiyuan Li, Tengyu Ma
2023	A*	`conf`	Sharpness Minimization Algorithms Do Not Only Minimize Sharpness To Achieve Better Generalization. NeurIPS Kaiyue Wen, Zhiyuan Li, Tengyu Ma
2023	J	`jnl`	Sharpness Minimization Algorithms Do Not Only Minimize Sharpness To Achieve Better Generalization. CoRR Kaiyue Wen, Zhiyuan Li, Tengyu Ma
2023	J	`jnl`	Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training. CoRR Hong Liu, Zhiyuan Li, David Hall, Percy Liang, Tengyu Ma
2023	A*	`conf`	Symbol tuning improves in-context learning in language models. EMNLP Jerry W. Wei, Le Hou, Andrew K. Lampinen, Xiangning Chen, Da Huang, Yi Tay, Xinyun Chen, Yifeng Lu, Denny Zhou, Tengyu Ma, Quoc V. Le
2023	J	`jnl`	Symbol tuning improves in-context learning in language models. CoRR Jerry W. Wei, Le Hou, Andrew K. Lampinen, Xiangning Chen, Da Huang, Yi Tay, Xinyun Chen, Yifeng Lu, Denny Zhou, Tengyu Ma, Quoc V. Le
2023	J	`jnl`	The Inductive Bias of Flatness Regularization for Deep Matrix Factorization. CoRR Khashayar Gatmiry, Zhiyuan Li, Ching-Yao Chuang, Sashank J. Reddi, Tengyu Ma, Stefanie Jegelka
2023	J	`jnl`	Toward L CoRR Kefan Dong, Tengyu Ma
2023	A*	`conf`	Toward L_∞Recovery of Nonlinear Functions: A Polynomial Sample Complexity Bound for Gaussian Random Fields. COLT Kefan Dong, Tengyu Ma
2023	A*	`conf`	What is the Inductive Bias of Flatness Regularization? A Study of Deep Matrix Factorization Models. NeurIPS Khashayar Gatmiry, Zhiyuan Li, Tengyu Ma, Sashank J. Reddi, Stefanie Jegelka, Ching-Yao Chuang
2023	A*	`conf`	What learning algorithm is in-context learning? Investigations with linear models. ICLR Ekin Akyürek, Dale Schuurmans, Jacob Andreas, Tengyu Ma, Denny Zhou
2022	J	`jnl`	A Theoretical Study of Inductive Biases in Contrastive Learning. CoRR Jeff Z. HaoChen, Tengyu Ma
2022	A*	`conf`	An Explanation of In-context Learning as Implicit Bayesian Inference. ICLR Sang Michael Xie, Aditi Raghunathan, Percy Liang, Tengyu Ma
2022	J	`jnl`	Asymptotic Instance-Optimal Algorithms for Interactive Decision Making. CoRR Kefan Dong, Tengyu Ma
2022	A*	`conf`	Beyond Separability: Analyzing the Linear Transferability of Contrastive Representations to Related Subpopulations. NeurIPS Jeff Z. HaoChen, Colin Wei, Ananya Kumar, Tengyu Ma
2022	J	`jnl`	Beyond Separability: Analyzing the Linear Transferability of Contrastive Representations to Related Subpopulations. CoRR Jeff Z. HaoChen, Colin Wei, Ananya Kumar, Tengyu Ma
2022	A	`conf`	Calibrated ensembles can mitigate accuracy tradeoffs under distribution shift. UAI Ananya Kumar, Tengyu Ma, Percy Liang, Aditi Raghunathan
2022	J	`jnl`	Calibrated ensembles can mitigate accuracy tradeoffs under distribution shift. CoRR Ananya Kumar, Tengyu Ma, Percy Liang, Aditi Raghunathan
2022	A*	`conf`	Connect, Not Collapse: Explaining Contrastive Learning for Unsupervised Domain Adaptation. ICML Kendrick Shen, Robbie M. Jones, Ananya Kumar, Sang Michael Xie, Jeff Z. HaoChen, Tengyu Ma, Percy Liang
2022	J	`jnl`	Connect, Not Collapse: Explaining Contrastive Learning for Unsupervised Domain Adaptation. CoRR Kendrick Shen, Robbie Jones, Ananya Kumar, Sang Michael Xie, Jeff Z. HaoChen, Tengyu Ma, Percy Liang
2022	A*	`conf`	DR3: Value-Based Deep Reinforcement Learning Requires Explicit Regularization. ICLR Aviral Kumar, Rishabh Agarwal, Tengyu Ma, Aaron C. Courville, George Tucker, Sergey Levine
2022	A*	`conf`	Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution. ICLR Ananya Kumar, Aditi Raghunathan, Robbie Matthew Jones, Tengyu Ma, Percy Liang
2022	J	`jnl`	Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution. CoRR Ananya Kumar, Aditi Raghunathan, Robbie Jones, Tengyu Ma, Percy Liang
2022	J	`jnl`	First Steps Toward Understanding the Extrapolation of Nonlinear Models to Unseen Domains. CoRR Kefan Dong, Tengyu Ma
2022	J	`jnl`	How Does Sharpness-Aware Minimization Minimize Sharpness? CoRR Kaiyue Wen, Tengyu Ma, Zhiyuan Li
2022	A*	`conf`	Iterative Feature Matching: Toward Provable Domain Generalization with Logarithmic Environments. NeurIPS Yining Chen, Elan Rosenfeld, Mark Sellke, Tengyu Ma, Andrej Risteski
2022	J	`jnl`	Max-Margin Works while Large Margin Fails: Generalization without Uniform Convergence. CoRR Margalit Glasgow, Colin Wei, Mary Wootters, Tengyu Ma
2022	A*	`conf`	Near-Optimal Algorithms for Autonomous Exploration and Multi-Goal Stochastic Shortest Path. ICML Haoyuan Cai, Tengyu Ma, Simon S. Du
2022	J	`jnl`	Near-Optimal Algorithms for Autonomous Exploration and Multi-Goal Stochastic Shortest Path. CoRR Haoyuan Cai, Tengyu Ma, Simon S. Du
2022	J	`jnl`	On the optimization landscape of tensor decompositions. Math. Program. Rong Ge, Tengyu Ma
2022	A*	`conf`	Plan Better Amid Conservatism: Offline Multi-Agent Reinforcement Learning with Actor Rectification. ICML Ling Pan, Longbo Huang, Tengyu Ma, Huazhe Xu
2022	J	`jnl`	Safe Reinforcement Learning by Imagining the Near Future. CoRR Garrett Thomas, Yuping Luo, Tengyu Ma
2022	J	`jnl`	Same Pre-training Loss, Better Downstream: Implicit Bias Matters for Language Models. CoRR Hong Liu, Sang Michael Xie, Zhiyuan Li, Tengyu Ma
2022	A*	`conf`	Self-supervised Learning is More Robust to Dataset Imbalance. ICLR Hong Liu, Jeff Z. HaoChen, Adrien Gaidon, Tengyu Ma
2022	A	`conf`	Sharp Bounds for Federated Averaging (Local SGD) and Continuous Perspective. AISTATS Margalit R. Glasgow, Honglin Yuan, Tengyu Ma
2022	A*	`conf`	Statistically Meaningful Approximation: a Case Study on Approximating Turing Machines with Transformers. NeurIPS Colin Wei, Yining Chen, Tengyu Ma
2022	J	`jnl`	What learning algorithm is in-context learning? Investigations with linear models. CoRR Ekin Akyürek, Dale Schuurmans, Jacob Andreas, Tengyu Ma, Denny Zhou
2021	A	`conf`	Active Online Learning with Hidden Shifting Domains. AISTATS Yining Chen, Haipeng Luo, Tengyu Ma, Chicheng Zhang
2021	J	`jnl`	An Explanation of In-context Learning as Implicit Bayesian Inference. CoRR Sang Michael Xie, Aditi Raghunathan, Percy Liang, Tengyu Ma
2021	A*	`conf`	Calibrating Predictions to Decisions: A Novel Approach to Multi-Class Calibration. NeurIPS Shengjia Zhao, Michael P. Kim, Roshni Sahoo, Tengyu Ma, Stefano Ermon
2021	J	`jnl`	Calibrating Predictions to Decisions: A Novel Approach to Multi-Class Calibration. CoRR Shengjia Zhao, Michael P. Kim, Roshni Sahoo, Tengyu Ma, Stefano Ermon
2021	A*	`conf`	Composed Fine-Tuning: Freezing Pre-Trained Denoising Autoencoders for Improved Generalization. ICML Sang Michael Xie, Tengyu Ma, Percy Liang
2021	J	`jnl`	DR3: Value-Based Deep Reinforcement Learning Requires Explicit Regularization. CoRR Aviral Kumar, Rishabh Agarwal, Tengyu Ma, Aaron C. Courville, George Tucker, Sergey Levine
2021	A*	`conf`	Document-Level Relation Extraction with Adaptive Thresholding and Localized Context Pooling. AAAI Wenxuan Zhou, Kevin Huang, Tengyu Ma, Jing Huang
2021	—	`conf`	Entity and Evidence Guided Document-Level Relation Extraction. RepL4NLP@ACL-IJCNLP Kevin Huang, Peng Qi, Guangtao Wang, Tengyu Ma, Jing Huang
2021	A*	`conf`	Fine-Grained Gap-Dependent Bounds for Tabular MDPs via Adaptive Multi-Step Bootstrap. COLT Haike Xu, Tengyu Ma, Simon S. Du
2021	J	`jnl`	Fine-Grained Gap-Dependent Bounds for Tabular MDPs via Adaptive Multi-Step Bootstrap. CoRR Haike Xu, Tengyu Ma, Simon S. Du
2021	A*	`conf`	Heteroskedastic and Imbalanced Deep Learning with Adaptive Regularization. ICLR Kaidi Cao, Yining Chen, Junwei Lu, Nikos Aréchiga, Adrien Gaidon, Tengyu Ma
2021	A*	`conf`	In-N-Out: Pre-Training and Self-Training using Auxiliary Information for Out-of-Distribution Robustness. ICLR Sang Michael Xie, Ananya Kumar, Robbie Jones, Fereshte Khani, Tengyu Ma, Percy Liang
2021	J	`jnl`	Iterative Feature Matching: Toward Provable Domain Generalization with Logarithmic Environments. CoRR Yining Chen, Elan Rosenfeld, Mark Sellke, Tengyu Ma, Andrej Risteski
2021	J	`jnl`	Joint System-Wise Optimization for Pipeline Goal-Oriented Dialog System. CoRR Zichuan Lin, Jing Huang, Bowen Zhou, Xiaodong He, Tengyu Ma
2021	A*	`conf`	Label Noise SGD Provably Prefers Flat Global Minimizers. NeurIPS Alex Damian, Tengyu Ma, Jason D. Lee
2021	J	`jnl`	Label Noise SGD Provably Prefers Flat Global Minimizers. CoRR Alex Damian, Tengyu Ma, Jason D. Lee
2021	A*	`conf`	Learning Barrier Certificates: Towards Safe Reinforcement Learning with Zero Training-time Violations. NeurIPS Yuping Luo, Tengyu Ma
2021	J	`jnl`	Learning Barrier Certificates: Towards Safe Reinforcement Learning with Zero Training-time Violations. CoRR Yuping Luo, Tengyu Ma
2021	A*	`conf`	Optimal Regularization can Mitigate Double Descent. ICLR Preetum Nakkiran, Prayaag Venkat, Sham M. Kakade, Tengyu Ma
2021	J	`jnl`	Plan Better Amid Conservatism: Offline Multi-Agent Reinforcement Learning with Actor Rectification. CoRR Ling Pan, Longbo Huang, Tengyu Ma, Huazhe Xu
2021	A*	`conf`	Provable Guarantees for Self-Supervised Deep Learning with Spectral Contrastive Loss. NeurIPS Jeff Z. HaoChen, Colin Wei, Adrien Gaidon, Tengyu Ma
2021	J	`jnl`	Provable Guarantees for Self-Supervised Deep Learning with Spectral Contrastive Loss. CoRR Jeff Z. HaoChen, Colin Wei, Adrien Gaidon, Tengyu Ma
2021	A*	`conf`	Provable Model-based Nonlinear Bandit and Reinforcement Learning: Shelve Optimism, Embrace Virtual Curvature. NeurIPS Kefan Dong, Jiaqi Yang, Tengyu Ma
2021	J	`jnl`	Provable Model-based Nonlinear Bandit and Reinforcement Learning: Shelve Optimism, Embrace Virtual Curvature. CoRR Kefan Dong, Jiaqi Yang, Tengyu Ma
2021	A*	`conf`	Safe Reinforcement Learning by Imagining the Near Future. NeurIPS Garrett Thomas, Yuping Luo, Tengyu Ma
2021	J	`jnl`	Self-supervised Learning is More Robust to Dataset Imbalance. CoRR Hong Liu, Jeff Z. HaoChen, Adrien Gaidon, Tengyu Ma
2021	A*	`conf`	Shape Matters: Understanding the Implicit Bias of the Noise Covariance. COLT Jeff Z. HaoChen, Colin Wei, Jason D. Lee, Tengyu Ma
2021	J	`jnl`	Sharp Bounds for Federated Averaging (Local SGD) and Continuous Perspective. CoRR Margalit Glasgow, Honglin Yuan, Tengyu Ma
2021	J	`jnl`	Statistically Meaningful Approximation: a Case Study on Approximating Turing Machines with Transformers. CoRR Colin Wei, Yining Chen, Tengyu Ma
2021	A*	`conf`	Theoretical Analysis of Self-Training with Deep Networks on Unlabeled Data. ICLR Colin Wei, Kendrick Shen, Yining Chen, Tengyu Ma
2021	—	`conf`	Variance-reduced First-order Meta-learning for Natural Language Processing Tasks. NAACL-HLT Lingxiao Wang, Kevin Huang, Tengyu Ma, Quanquan Gu, Jing Huang
2021	J	`jnl`	Why Do Local Methods Solve Nonconvex Problems? CoRR Tengyu Ma
2021	A*	`conf`	Why Do Pretrained Language Models Help in Downstream Tasks? An Analysis of Head and Prompt Tuning. NeurIPS Colin Wei, Sang Michael Xie, Tengyu Ma
2021	J	`jnl`	Why Do Pretrained Language Models Help in Downstream Tasks? An Analysis of Head and Prompt Tuning. CoRR Colin Wei, Sang Michael Xie, Tengyu Ma
2020	J	`jnl`	Active Online Domain Adaptation. CoRR Yining Chen, Haipeng Luo, Tengyu Ma, Chicheng Zhang
2020	A*	`conf`	Beyond Lazy Training for Over-parameterized Tensor Decomposition. NeurIPS Xiang Wang, Chenwei Wu, Jason D. Lee, Tengyu Ma, Rong Ge
2020	J	`jnl`	Beyond Lazy Training for Over-parameterized Tensor Decomposition. CoRR Xiang Wang, Chenwei Wu, Jason D. Lee, Tengyu Ma, Rong Ge
2020	J	`jnl`	Document-Level Relation Extraction with Adaptive Thresholding and Localized Context Pooling. CoRR Wenxuan Zhou, Kevin Huang, Tengyu Ma, Jing Huang
2020	J	`jnl`	Entity and Evidence Guided Relation Extraction for DocRED. CoRR Kevin Huang, Guangtao Wang, Tengyu Ma, Jing Huang
2020	A*	`conf`	Federated Accelerated Stochastic Gradient Descent. NeurIPS Honglin Yuan, Tengyu Ma
2020	J	`jnl`	Federated Accelerated Stochastic Gradient Descent. CoRR Honglin Yuan, Tengyu Ma
2020	J	`jnl`	Heteroskedastic and Imbalanced Deep Learning with Adaptive Regularization. CoRR Kaidi Cao, Yining Chen, Junwei Lu, Nikos Aréchiga, Adrien Gaidon, Tengyu Ma
2020	A*	`conf`	Improved Sample Complexities for Deep Neural Networks and Robust Classification via an All-Layer Margin. ICLR Colin Wei, Tengyu Ma
2020	J	`jnl`	In-N-Out: Pre-Training and Self-Training using Auxiliary Information for Out-of-Distribution Robustness. CoRR Sang Michael Xie, Ananya Kumar, Robbie Jones, Fereshte Khani, Tengyu Ma, Percy Liang
2020	A*	`conf`	Individual Calibration with Randomized Forecasting. ICML Shengjia Zhao, Tengyu Ma, Stefano Ermon
2020	J	`jnl`	Individual Calibration with Randomized Forecasting. CoRR Shengjia Zhao, Tengyu Ma, Stefano Ermon
2020	A*	`conf`	Learning Over-Parametrized Two-Layer Neural Networks beyond NTK. COLT Yuanzhi Li, Tengyu Ma, Hongyang R. Zhang
2020	J	`jnl`	Learning Over-Parametrized Two-Layer ReLU Neural Networks beyond NTK. CoRR Yuanzhi Li, Tengyu Ma, Hongyang R. Zhang
2020	A*	`conf`	Learning Self-Correctable Policies and Value Functions from Demonstrations with Negative Sampling. ICLR Yuping Luo, Huazhe Xu, Tengyu Ma
2020	A*	`conf`	MOPO: Model-based Offline Policy Optimization. NeurIPS Tianhe Yu, Garrett Thomas, Lantao Yu, Stefano Ermon, James Y. Zou, Sergey Levine, Chelsea Finn, Tengyu Ma
2020	J	`jnl`	MOPO: Model-based Offline Policy Optimization. CoRR Tianhe Yu, Garrett Thomas, Lantao Yu, Stefano Ermon, James Zou, Sergey Levine, Chelsea Finn, Tengyu Ma
2020	J	`jnl`	Meta-learning Transferable Representations with a Single Target Domain. CoRR Hong Liu, Jeff Z. HaoChen, Colin Wei, Tengyu Ma
2020	A*	`conf`	Model-based Adversarial Meta-Reinforcement Learning. NeurIPS Zichuan Lin, Garrett Thomas, Guangwen Yang, Tengyu Ma
2020	J	`jnl`	Model-based Adversarial Meta-Reinforcement Learning. CoRR Zichuan Lin, Garrett Thomas, Guangwen Yang, Tengyu Ma
2020	A*	`conf`	On the Expressivity of Neural Networks for Deep Reinforcement Learning. ICML Kefan Dong, Yuping Luo, Tianhe Yu, Chelsea Finn, Tengyu Ma
2020	J	`jnl`	Optimal Regularization Can Mitigate Double Descent. CoRR Preetum Nakkiran, Prayaag Venkat, Sham M. Kakade, Tengyu Ma
2020	—	`conf`	Robust and On-the-Fly Dataset Denoising for Image Classification. ECCV (29) Jiaming Song, Yann N. Dauphin, Michael Auli, Tengyu Ma
2020	J	`jnl`	Robust and On-the-fly Dataset Denoising for Image Classification. CoRR Jiaming Song, Lunjia Hu, Yann N. Dauphin, Michael Auli, Tengyu Ma
2020	A*	`conf`	Self-training Avoids Using Spurious Features Under Domain Shift. NeurIPS Yining Chen, Colin Wei, Ananya Kumar, Tengyu Ma
2020	J	`jnl`	Self-training Avoids Using Spurious Features Under Domain Shift. CoRR Yining Chen, Colin Wei, Ananya Kumar, Tengyu Ma
2020	J	`jnl`	Shape Matters: Understanding the Implicit Bias of the Noise Covariance. CoRR Jeff Z. HaoChen, Colin Wei, Jason D. Lee, Tengyu Ma
2020	J	`jnl`	Simplifying Models with Unlabeled Output Data. CoRR Sang Michael Xie, Tengyu Ma, Percy Liang
2020	A*	`conf`	The Implicit and Explicit Regularization Effects of Dropout. ICML Colin Wei, Sham M. Kakade, Tengyu Ma
2020	J	`jnl`	The Implicit and Explicit Regularization Effects of Dropout. CoRR Colin Wei, Sham M. Kakade, Tengyu Ma
2020	J	`jnl`	Theoretical Analysis of Self-Training with Deep Networks on Unlabeled Data. CoRR Colin Wei, Kendrick Shen, Yining Chen, Tengyu Ma
2020	A*	`conf`	Understanding Self-Training for Gradual Domain Adaptation. ICML Ananya Kumar, Tengyu Ma, Percy Liang
2020	J	`jnl`	Understanding Self-Training for Gradual Domain Adaptation. CoRR Ananya Kumar, Tengyu Ma, Percy Liang
2020	—	`ch.`	Why Do Local Methods Solve Nonconvex Problems? Beyond the Worst-Case Analysis of Algorithms Tengyu Ma
2019	J	`jnl`	A Model-based Approach for Sample-efficient Multi-task Reinforcement Learning. CoRR Nicholas C. Landolfi, Garrett Thomas, Tengyu Ma
2019	—	`conf`	Algorithmic Framework for Model-based Deep Reinforcement Learning with Theoretical Guarantees. ICLR (Poster) Yuping Luo, Huazhe Xu, Yuanzhi Li, Yuandong Tian, Trevor Darrell, Tengyu Ma
2019	—	`conf`	Approximability of Discriminators Implies Diversity in GANs. ICLR (Poster) Yu Bai, Tengyu Ma, Andrej Risteski
2019	J	`jnl`	Bootstrapping the Expressivity with Model-based Planning. CoRR Kefan Dong, Yuping Luo, Tengyu Ma
2019	A*	`conf`	Data-dependent Sample Complexity of Deep Neural Networks via Lipschitz Augmentation. NeurIPS Colin Wei, Tengyu Ma
2019	J	`jnl`	Data-dependent Sample Complexity of Deep Neural Networks via Lipschitz Augmentation. CoRR Colin Wei, Tengyu Ma
2019	—	`conf`	Fixup Initialization: Residual Learning Without Normalization. ICLR (Poster) Hongyi Zhang, Yann N. Dauphin, Tengyu Ma
2019	J	`jnl`	Fixup Initialization: Residual Learning Without Normalization. CoRR Hongyi Zhang, Yann N. Dauphin, Tengyu Ma
2019	J	`jnl`	Improved Sample Complexities for Deep Networks and Robust Classification via an All-Layer Margin. CoRR Colin Wei, Tengyu Ma
2019	A*	`conf`	Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss. NeurIPS Kaidi Cao, Colin Wei, Adrien Gaidon, Nikos Aréchiga, Tengyu Ma
2019	J	`jnl`	Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss. CoRR Kaidi Cao, Colin Wei, Adrien Gaidon, Nikos Aréchiga, Tengyu Ma
2019	J	`jnl`	Learning Self-Correctable Policies and Value Functions from Demonstrations with Negative Sampling. CoRR Yuping Luo, Huazhe Xu, Tengyu Ma
2019	A*	`conf`	On the Performance of Thompson Sampling on Logistic Bandits. COLT Shi Dong, Tengyu Ma, Benjamin Van Roy
2019	J	`jnl`	On the Performance of Thompson Sampling on Logistic Bandits. CoRR Shi Dong, Tengyu Ma, Benjamin Van Roy
2019	J	`jnl`	Optimal Design of Process Flexibility for General Production Systems. Oper. Res. Xi Chen, Tengyu Ma, Jiawei Zhang, Yuan Zhou
2019	A*	`conf`	Regularization Matters: Generalization and Optimization of Neural Nets v.s. their Induced Kernel. NeurIPS Colin Wei, Jason D. Lee, Qiang Liu, Tengyu Ma
2019	A*	`conf`	Towards Explaining the Regularization Effect of Initial Large Learning Rate in Training Neural Networks. NeurIPS Yuanzhi Li, Colin Wei, Tengyu Ma
2019	J	`jnl`	Towards Explaining the Regularization Effect of Initial Large Learning Rate in Training Neural Networks. CoRR Yuanzhi Li, Colin Wei, Tengyu Ma
2019	A*	`conf`	Verified Uncertainty Calibration. NeurIPS Ananya Kumar, Percy Liang, Tengyu Ma
2019	J	`jnl`	Verified Uncertainty Calibration. CoRR Ananya Kumar, Percy Liang, Tengyu Ma
2018	—	`conf`	A La Carte Embedding: Cheap but Effective Induction of Semantic Feature Vectors. ACL (1) Mikhail Khodak, Nikunj Saunshi, Yingyu Liang, Tengyu Ma, Brandon Stewart, Sanjeev Arora
2018	J	`jnl`	A La Carte Embedding: Cheap but Effective Induction of Semantic Feature Vectors. CoRR Mikhail Khodak, Nikunj Saunshi, Yingyu Liang, Tengyu Ma, Brandon Stewart, Sanjeev Arora
2018	J	`jnl`	Algorithmic Framework for Model-based Reinforcement Learning with Theoretical Guarantees. CoRR Huazhe Xu, Yuanzhi Li, Yuandong Tian, Trevor Darrell, Tengyu Ma
2018	A*	`conf`	Algorithmic Regularization in Over-parameterized Matrix Sensing and Neural Networks with Quadratic Activations. COLT Yuanzhi Li, Tengyu Ma, Hongyang Zhang
2018	J	`jnl`	Approximability of Discriminators Implies Diversity in GANs. CoRR Yu Bai, Tengyu Ma, Andrej Risteski
2018	A*	`conf`	Generalization and equilibrium in generative adversarial nets (GANs) (invited talk). STOC Tengyu Ma
2018	J	`jnl`	Gradient Descent Learns Linear Dynamical Systems. J. Mach. Learn. Res. Moritz Hardt, Tengyu Ma, Benjamin Recht
2018	—	`conf`	Learning One-hidden-layer Neural Networks with Landscape Design. ICLR (Poster) Rong Ge, Jason D. Lee, Tengyu Ma
2018	J	`jnl`	Linear Algebraic Structure of Word Senses, with Applications to Polysemy. Trans. Assoc. Comput. Linguistics Sanjeev Arora, Yuanzhi Li, Yingyu Liang, Tengyu Ma, Andrej Risteski
2018	J	`jnl`	On the Margin Theory of Feedforward Neural Networks. CoRR Colin Wei, Jason D. Lee, Qiang Liu, Tengyu Ma
2018	J	`jnl`	Optimal Design of Process Flexibility for General Production Systems. CoRR Xi Chen, Tengyu Ma, Jiawei Zhang, Yuan Zhou
2017	—	`conf`	A Simple but Tough-to-Beat Baseline for Sentence Embeddings. ICLR (Poster) Sanjeev Arora, Yingyu Liang, Tengyu Ma
2017	J	`jnl`	Algorithmic Regularization in Over-parameterized Matrix Recovery. CoRR Yuanzhi Li, Tengyu Ma, Hongyang Zhang
2017	J	`jnl`	Distributed Stochastic Variance Reduced Gradient Methods by Sampling Extra Data with Replacement. J. Mach. Learn. Res. Jason D. Lee, Qihang Lin, Tengyu Ma, Tianbao Yang
2017	A*	`conf`	Finding approximate local minima faster than gradient descent. STOC Naman Agarwal, Zeyuan Allen Zhu, Brian Bullins, Elad Hazan, Tengyu Ma
2017	A*	`conf`	Generalization and Equilibrium in Generative Adversarial Nets (GANs). ICML Sanjeev Arora, Rong Ge, Yingyu Liang, Tengyu Ma, Yi Zhang
2017	J	`jnl`	Generalization and Equilibrium in Generative Adversarial Nets (GANs). CoRR Sanjeev Arora, Rong Ge, Yingyu Liang, Tengyu Ma, Yi Zhang
2017	—	`conf`	Identity Matters in Deep Learning. ICLR (Poster) Moritz Hardt, Tengyu Ma
2017	J	`jnl`	Learning One-hidden-layer Neural Networks with Landscape Design. CoRR Rong Ge, Jason D. Lee, Tengyu Ma
2017	—	`—`	Non-convex Optimization for Machine Learning: Design, Analysis, and Understanding Tengyu Ma
2017	A*	`conf`	On the Ability of Neural Nets to Express Distributions. COLT Holden Lee, Rong Ge, Tengyu Ma, Andrej Risteski, Sanjeev Arora
2017	—	`conf`	On the Optimization Landscape of Tensor Decompositions. NIPS Rong Ge, Tengyu Ma
2017	J	`jnl`	On the Optimization Landscape of Tensor Decompositions. CoRR Rong Ge, Tengyu Ma
2017	J	`jnl`	On the ability of neural nets to express distributions. CoRR Holden Lee, Rong Ge, Andrej Risteski, Tengyu Ma, Sanjeev Arora
2017	A*	`conf`	Provable learning of noisy-OR networks. STOC Sanjeev Arora, Rong Ge, Tengyu Ma, Andrej Risteski
2016	J	`jnl`	A Latent Variable Model Approach to PMI-based Word Embeddings. Trans. Assoc. Comput. Linguistics Sanjeev Arora, Yuanzhi Li, Yingyu Liang, Tengyu Ma, Andrej Risteski
2016	—	`conf`	A Non-generative Framework and Convex Relaxations for Unsupervised Learning. NIPS Elad Hazan, Tengyu Ma
2016	J	`jnl`	A Non-generative Framework and Convex Relaxations for Unsupervised Learning. CoRR Elad Hazan, Tengyu Ma
2016	A*	`conf`	Communication lower bounds for statistical estimation problems via a distributed data processing inequality. STOC Mark Braverman, Ankit Garg, Tengyu Ma, Huy L. Nguyen, David P. Woodruff
2016	J	`jnl`	Finding Approximate Local Minima for Nonconvex Optimization in Linear Time. CoRR Naman Agarwal, Zeyuan Allen Zhu, Brian Bullins, Elad Hazan, Tengyu Ma
2016	J	`jnl`	Gradient Descent Learns Linear Dynamical Systems. CoRR Moritz Hardt, Tengyu Ma, Benjamin Recht
2016	J	`jnl`	Identity Matters in Deep Learning. CoRR Moritz Hardt, Tengyu Ma
2016	J	`jnl`	Linear Algebraic Structure of Word Senses, with Applications to Polysemy. CoRR Sanjeev Arora, Yuanzhi Li, Yingyu Liang, Tengyu Ma, Andrej Risteski
2016	—	`conf`	Matrix Completion has No Spurious Local Minimum. NIPS Rong Ge, Jason D. Lee, Tengyu Ma
2016	J	`jnl`	Matrix Completion has No Spurious Local Minimum. CoRR Rong Ge, Jason D. Lee, Tengyu Ma
2016	A*	`conf`	Polynomial-Time Tensor Decompositions with Sum-of-Squares. FOCS Tengyu Ma, Jonathan Shi, David Steurer
2016	J	`jnl`	Polynomial-time Tensor Decompositions with Sum-of-Squares. CoRR Tengyu Ma, Jonathan Shi, David Steurer
2016	A*	`conf`	Provable Algorithms for Inference in Topic Models. ICML Sanjeev Arora, Rong Ge, Frederic Koehler, Tengyu Ma, Ankur Moitra
2016	J	`jnl`	Provable Algorithms for Inference in Topic Models. CoRR Sanjeev Arora, Rong Ge, Frederic Koehler, Tengyu Ma, Ankur Moitra
2016	J	`jnl`	Provable learning of Noisy-or Networks. CoRR Sanjeev Arora, Rong Ge, Tengyu Ma, Andrej Risteski
2016	J	`jnl`	The Simulated Greedy Algorithm for Several Submodular Matroid Secretary Problems. Theory Comput. Syst. Tengyu Ma, Bo Tang, Yajun Wang
2015	J	`jnl`	Communication Lower Bounds for Statistical Estimation Problems via a Distributed Data Processing Inequality. CoRR Mark Braverman, Ankit Garg, Tengyu Ma, Huy L. Nguyen, David P. Woodruff
2015	—	`conf`	Decomposing Overcomplete 3rd Order Tensors using Sum-of-Squares Algorithms. APPROX-RANDOM Rong Ge, Tengyu Ma
2015	J	`jnl`	Decomposing Overcomplete 3rd Order Tensors using Sum-of-Squares Algorithms. CoRR Rong Ge, Tengyu Ma
2015	J	`jnl`	Distributed Stochastic Variance Reduced Gradient Methods. CoRR Jason D. Lee, Tengyu Ma, Qihang Lin
2015	A*	`conf`	Online Learning of Eigenvectors. ICML Dan Garber, Elad Hazan, Tengyu Ma
2015	J	`jnl`	Random Walks on Context Spaces: Towards an Explanation of the Mysteries of Semantic Word Embeddings. CoRR Sanjeev Arora, Yuanzhi Li, Yingyu Liang, Tengyu Ma, Andrej Risteski
2015	A*	`conf`	Simple, Efficient, and Neural Algorithms for Sparse Coding. COLT Sanjeev Arora, Rong Ge, Tengyu Ma, Ankur Moitra
2015	J	`jnl`	Simple, Efficient, and Neural Algorithms for Sparse Coding. CoRR Sanjeev Arora, Rong Ge, Tengyu Ma, Ankur Moitra
2015	—	`conf`	Sum-of-Squares Lower Bounds for Sparse PCA. NIPS Tengyu Ma, Avi Wigderson
2015	J	`jnl`	Sum-of-Squares Lower Bounds for Sparse PCA. CoRR Tengyu Ma, Avi Wigderson
2015	J	`jnl`	Why are deep nets reversible: A simple theory, with implications for training. CoRR Sanjeev Arora, Yingyu Liang, Tengyu Ma
2014	J	`jnl`	Lower Bound for High-Dimensional Statistical Learning Problem via Direct-Sum Theorem. CoRR Ankit Garg, Tengyu Ma, Huy L. Nguyen
2014	J	`jnl`	More Algorithms for Provable Dictionary Learning. CoRR Sanjeev Arora, Aditya Bhaskara, Rong Ge, Tengyu Ma
2014	—	`conf`	On Communication Cost of Distributed Statistical Estimation and Dimensionality. NIPS Ankit Garg, Tengyu Ma, Huy L. Nguyen
2014	A*	`conf`	Provable Bounds for Learning Some Deep Representations. ICML Sanjeev Arora, Aditya Bhaskara, Rong Ge, Tengyu Ma
2013	J	`jnl`	On a conjecture of Butler and Graham. Des. Codes Cryptogr. Tengyu Ma, Xiaoming Sun, Huacheng Yu
2013	J	`jnl`	Provable Bounds for Learning Some Deep Representations. CoRR Sanjeev Arora, Aditya Bhaskara, Rong Ge, Tengyu Ma
2013	A	`conf`	The Simulated Greedy Algorithm for Several Submodular Matroid Secretary Problems. STACS Tengyu Ma, Bo Tang, Yajun Wang
2011	J	`jnl`	A New Variation of Hat Guessing Games CoRR Tengyu Ma, Xiaoming Sun, Huacheng Yu
2011	Misc	`conf`	A New Variation of Hat Guessing Games. COCOON Tengyu Ma, Xiaoming Sun, Huacheng Yu
2011	J	`jnl`	On a Conjecture of Butler and Graham CoRR Tengyu Ma, Xiaoming Sun, Huacheng Yu