![](https://dblp1.uni-trier.de/img/logo.ua.320x120.png)
![](https://dblp1.uni-trier.de/img/dropdown.dark.16x16.png)
![](https://dblp1.uni-trier.de/img/peace.dark.16x16.png)
Остановите войну!
for scientists:
![search dblp search dblp](https://dblp1.uni-trier.de/img/search.dark.16x16.png)
![search dblp](https://dblp1.uni-trier.de/img/search.dark.16x16.png)
default search action
Tengyu Ma 0001
Person information
- affiliation: Stanford University, CA, USA
Other persons with the same name
- Tengyu Ma 0002
— Harbin Institute of Technology, Harbin, China
- Tengyu Ma 0003 — Vanderbilt University, TN, USA
- Tengyu Ma 0004
— Dalian University of Technology, School of Software Technology, China
Refine list
![note](https://dblp1.uni-trier.de/img/note-mark.dark.12x12.png)
refinements active!
zoomed in on ?? of ?? records
view refined list in
export refined list as
2020 – today
- 2024
- [c94]Zhiyuan Liu, Hong Liu, Denny Zhou, Tengyu Ma:
Chain of Thought Empowers Transformers to Solve Inherently Serial Problems. ICLR 2024 - [c93]Tianle Cai, Xuezhi Wang, Tengyu Ma, Xinyun Chen, Denny Zhou:
Large Language Models as Tool Makers. ICLR 2024 - [c92]Hong Liu, Zhiyuan Li, David Leo Wright Hall, Percy Liang, Tengyu Ma:
Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training. ICLR 2024 - [c91]Arvind V. Mahankali, Tatsunori Hashimoto, Tengyu Ma:
One Step of Gradient Descent is Provably the Optimal In-Context Learner with One Layer of Linear Self-Attention. ICLR 2024 - [i103]Zhiyuan Li, Hong Liu, Denny Zhou, Tengyu Ma:
Chain of Thought Empowers Transformers to Solve Inherently Serial Problems. CoRR abs/2402.12875 (2024) - [i102]Neil Band, Xuechen Li, Tengyu Ma, Tatsunori Hashimoto:
Linguistic Calibration of Language Models. CoRR abs/2404.00474 (2024) - 2023
- [c90]Kefan Dong, Tengyu Ma:
Toward L_∞Recovery of Nonlinear Functions: A Polynomial Sample Complexity Bound for Gaussian Random Fields. COLT 2023: 2877-2918 - [c89]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:
Symbol tuning improves in-context learning in language models. EMNLP 2023: 968-979 - [c88]Ekin Akyürek, Dale Schuurmans, Jacob Andreas, Tengyu Ma, Denny Zhou:
What learning algorithm is in-context learning? Investigations with linear models. ICLR 2023 - [c87]Kefan Dong, Tengyu Ma:
First Steps Toward Understanding the Extrapolation of Nonlinear Models to Unseen Domains. ICLR 2023 - [c86]Kefan Dong, Tengyu Ma:
Asymptotic Instance-Optimal Algorithms for Interactive Decision Making. ICLR 2023 - [c85]Margalit Glasgow, Colin Wei, Mary Wootters, Tengyu Ma:
Max-Margin Works while Large Margin Fails: Generalization without Uniform Convergence. ICLR 2023 - [c84]Jeff Z. HaoChen, Tengyu Ma:
A theoretical study of inductive biases in contrastive learning. ICLR 2023 - [c83]Kaiyue Wen, Tengyu Ma, Zhiyuan Li:
How Sharpness-Aware Minimization Minimizes Sharpness? ICLR 2023 - [c82]Hong Liu, Sang Michael Xie, Zhiyuan Li, Tengyu Ma:
Same Pre-training Loss, Better Downstream: Implicit Bias Matters for Language Models. ICML 2023: 22188-22214 - [c81]Khashayar Gatmiry, Zhiyuan Li, Tengyu Ma, Sashank Reddi, Stefanie Jegelka, Ching-Yao Chuang:
What is the Inductive Bias of Flatness Regularization? A Study of Deep Matrix Factorization Models. NeurIPS 2023 - [c80]Arvind V. Mahankali, Haochen Zhang, Kefan Dong, Margalit Glasgow, Tengyu Ma:
Beyond NTK with Vanilla Gradient Descent: A Mean-Field Analysis of Neural Networks with Polynomial Width, Samples, and Time. NeurIPS 2023 - [c79]Kaiyue Wen, Zhiyuan Li, Tengyu Ma:
Sharpness Minimization Algorithms Do Not Only Minimize Sharpness To Achieve Better Generalization. NeurIPS 2023 - [c78]Sang Michael Xie, Hieu Pham, Xuanyi Dong, Nan Du, Hanxiao Liu, Yifeng Lu, Percy Liang, Quoc V. Le, Tengyu Ma, Adams Wei Yu:
DoReMi: Optimizing Data Mixtures Speeds Up Language Model Pretraining. NeurIPS 2023 - [c77]Sang Michael Xie, Shibani Santurkar, Tengyu Ma, Percy Liang:
Data Selection for Language Models via Importance Resampling. NeurIPS 2023 - [i101]Sang Michael Xie, Shibani Santurkar, Tengyu Ma, Percy Liang:
Data Selection for Language Models via Importance Resampling. CoRR abs/2302.03169 (2023) - [i100]Jerry W. Wei, Jason Wei, Yi Tay, Dustin Tran, Albert Webson, Yifeng Lu, Xinyun Chen, Hanxiao Liu, Da Huang, Denny Zhou, Tengyu Ma:
Larger language models do in-context learning differently. CoRR abs/2303.03846 (2023) - [i99]Kefan Dong, Tengyu Ma:
Toward L∞-recovery of Nonlinear Functions: A Polynomial Sample Complexity Bound for Gaussian Random Fields. CoRR abs/2305.00322 (2023) - [i98]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:
Symbol tuning improves in-context learning in language models. CoRR abs/2305.08298 (2023) - [i97]Sang Michael Xie, Hieu Pham, Xuanyi Dong, Nan Du, Hanxiao Liu, Yifeng Lu, Percy Liang, Quoc V. Le, Tengyu Ma, Adams Wei Yu:
DoReMi: Optimizing Data Mixtures Speeds Up Language Model Pretraining. CoRR abs/2305.10429 (2023) - [i96]Hong Liu, Zhiyuan Li, David Hall, Percy Liang, Tengyu Ma:
Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training. CoRR abs/2305.14342 (2023) - [i95]Tianle Cai, Xuezhi Wang, Tengyu Ma, Xinyun Chen, Denny Zhou:
Large Language Models as Tool Makers. CoRR abs/2305.17126 (2023) - [i94]Khashayar Gatmiry, Zhiyuan Li, Ching-Yao Chuang, Sashank Reddi, Tengyu Ma, Stefanie Jegelka:
The Inductive Bias of Flatness Regularization for Deep Matrix Factorization. CoRR abs/2306.13239 (2023) - [i93]Arvind V. Mahankali, Jeff Z. HaoChen, Kefan Dong, Margalit Glasgow, Tengyu Ma:
Beyond NTK with Vanilla Gradient Descent: A Mean-Field Analysis of Neural Networks with Polynomial Width, Samples, and Time. CoRR abs/2306.16361 (2023) - [i92]Arvind V. Mahankali, Tatsunori B. Hashimoto, Tengyu Ma:
One Step of Gradient Descent is Provably the Optimal In-Context Learner with One Layer of Linear Self-Attention. CoRR abs/2307.03576 (2023) - [i91]Kaiyue Wen, Zhiyuan Li, Tengyu Ma:
Sharpness Minimization Algorithms Do Not Only Minimize Sharpness To Achieve Better Generalization. CoRR abs/2307.11007 (2023) - 2022
- [j8]Rong Ge
, Tengyu Ma:
On the optimization landscape of tensor decompositions. Math. Program. 193(2): 713-759 (2022) - [c76]Margalit R. Glasgow, Honglin Yuan, Tengyu Ma:
Sharp Bounds for Federated Averaging (Local SGD) and Continuous Perspective. AISTATS 2022: 9050-9090 - [c75]Aviral Kumar, Rishabh Agarwal, Tengyu Ma, Aaron C. Courville, George Tucker, Sergey Levine:
DR3: Value-Based Deep Reinforcement Learning Requires Explicit Regularization. ICLR 2022 - [c74]Ananya Kumar, Aditi Raghunathan, Robbie Matthew Jones, Tengyu Ma, Percy Liang:
Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution. ICLR 2022 - [c73]Hong Liu, Jeff Z. HaoChen, Adrien Gaidon, Tengyu Ma:
Self-supervised Learning is More Robust to Dataset Imbalance. ICLR 2022 - [c72]Sang Michael Xie, Aditi Raghunathan, Percy Liang, Tengyu Ma:
An Explanation of In-context Learning as Implicit Bayesian Inference. ICLR 2022 - [c71]Haoyuan Cai, Tengyu Ma, Simon S. Du:
Near-Optimal Algorithms for Autonomous Exploration and Multi-Goal Stochastic Shortest Path. ICML 2022: 2434-2456 - [c70]Ling Pan, Longbo Huang, Tengyu Ma, Huazhe Xu:
Plan Better Amid Conservatism: Offline Multi-Agent Reinforcement Learning with Actor Rectification. ICML 2022: 17221-17237 - [c69]Kendrick Shen, Robbie M. Jones, Ananya Kumar, Sang Michael Xie, Jeff Z. HaoChen, Tengyu Ma, Percy Liang:
Connect, Not Collapse: Explaining Contrastive Learning for Unsupervised Domain Adaptation. ICML 2022: 19847-19878 - [c68]Yining Chen, Elan Rosenfeld, Mark Sellke, Tengyu Ma, Andrej Risteski:
Iterative Feature Matching: Toward Provable Domain Generalization with Logarithmic Environments. NeurIPS 2022 - [c67]Jeff Z. HaoChen, Colin Wei, Ananya Kumar, Tengyu Ma:
Beyond Separability: Analyzing the Linear Transferability of Contrastive Representations to Related Subpopulations. NeurIPS 2022 - [c66]Colin Wei, Yining Chen, Tengyu Ma:
Statistically Meaningful Approximation: a Case Study on Approximating Turing Machines with Transformers. NeurIPS 2022 - [c65]Ananya Kumar, Tengyu Ma, Percy Liang, Aditi Raghunathan:
Calibrated ensembles can mitigate accuracy tradeoffs under distribution shift. UAI 2022: 1041-1051 - [i90]Garrett Thomas, Yuping Luo, Tengyu Ma:
Safe Reinforcement Learning by Imagining the Near Future. CoRR abs/2202.07789 (2022) - [i89]Ananya Kumar, Aditi Raghunathan, Robbie Jones, Tengyu Ma, Percy Liang:
Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution. CoRR abs/2202.10054 (2022) - [i88]Kendrick Shen, Robbie Jones, Ananya Kumar, Sang Michael Xie, Jeff Z. HaoChen, Tengyu Ma, Percy Liang:
Connect, Not Collapse: Explaining Contrastive Learning for Unsupervised Domain Adaptation. CoRR abs/2204.00570 (2022) - [i87]Jeff Z. HaoChen, Colin Wei, Ananya Kumar, Tengyu Ma:
Beyond Separability: Analyzing the Linear Transferability of Contrastive Representations to Related Subpopulations. CoRR abs/2204.02683 (2022) - [i86]Haoyuan Cai, Tengyu Ma, Simon S. Du:
Near-Optimal Algorithms for Autonomous Exploration and Multi-Goal Stochastic Shortest Path. CoRR abs/2205.10729 (2022) - [i85]Kefan Dong, Tengyu Ma:
Asymptotic Instance-Optimal Algorithms for Interactive Decision Making. CoRR abs/2206.02326 (2022) - [i84]Margalit Glasgow, Colin Wei, Mary Wootters, Tengyu Ma:
Max-Margin Works while Large Margin Fails: Generalization without Uniform Convergence. CoRR abs/2206.07892 (2022) - [i83]Ananya Kumar, Tengyu Ma, Percy Liang, Aditi Raghunathan:
Calibrated ensembles can mitigate accuracy tradeoffs under distribution shift. CoRR abs/2207.08977 (2022) - [i82]Hong Liu, Sang Michael Xie, Zhiyuan Li, Tengyu Ma:
Same Pre-training Loss, Better Downstream: Implicit Bias Matters for Language Models. CoRR abs/2210.14199 (2022) - [i81]Kaiyue Wen, Tengyu Ma, Zhiyuan Li:
How Does Sharpness-Aware Minimization Minimize Sharpness? CoRR abs/2211.05729 (2022) - [i80]Kefan Dong, Tengyu Ma:
First Steps Toward Understanding the Extrapolation of Nonlinear Models to Unseen Domains. CoRR abs/2211.11719 (2022) - [i79]Jeff Z. HaoChen, Tengyu Ma:
A Theoretical Study of Inductive Biases in Contrastive Learning. CoRR abs/2211.14699 (2022) - [i78]Ekin Akyürek, Dale Schuurmans, Jacob Andreas, Tengyu Ma, Denny Zhou:
What learning algorithm is in-context learning? Investigations with linear models. CoRR abs/2211.15661 (2022) - 2021
- [c64]Wenxuan Zhou, Kevin Huang, Tengyu Ma, Jing Huang:
Document-Level Relation Extraction with Adaptive Thresholding and Localized Context Pooling. AAAI 2021: 14612-14620 - [c63]Yining Chen, Haipeng Luo, Tengyu Ma, Chicheng Zhang:
Active Online Learning with Hidden Shifting Domains. AISTATS 2021: 2053-2061 - [c62]Jeff Z. HaoChen, Colin Wei, Jason D. Lee, Tengyu Ma:
Shape Matters: Understanding the Implicit Bias of the Noise Covariance. COLT 2021: 2315-2357 - [c61]Haike Xu, Tengyu Ma, Simon S. Du:
Fine-Grained Gap-Dependent Bounds for Tabular MDPs via Adaptive Multi-Step Bootstrap. COLT 2021: 4438-4472 - [c60]Kaidi Cao, Yining Chen, Junwei Lu, Nikos Aréchiga, Adrien Gaidon, Tengyu Ma:
Heteroskedastic and Imbalanced Deep Learning with Adaptive Regularization. ICLR 2021 - [c59]Preetum Nakkiran, Prayaag Venkat, Sham M. Kakade, Tengyu Ma:
Optimal Regularization can Mitigate Double Descent. ICLR 2021 - [c58]Colin Wei, Kendrick Shen, Yining Chen, Tengyu Ma:
Theoretical Analysis of Self-Training with Deep Networks on Unlabeled Data. ICLR 2021 - [c57]Sang Michael Xie, Ananya Kumar, Robbie Jones, Fereshte Khani, Tengyu Ma, Percy Liang:
In-N-Out: Pre-Training and Self-Training using Auxiliary Information for Out-of-Distribution Robustness. ICLR 2021 - [c56]Sang Michael Xie, Tengyu Ma, Percy Liang:
Composed Fine-Tuning: Freezing Pre-Trained Denoising Autoencoders for Improved Generalization. ICML 2021: 11424-11435 - [c55]Lingxiao Wang, Kevin Huang, Tengyu Ma, Quanquan Gu, Jing Huang:
Variance-reduced First-order Meta-learning for Natural Language Processing Tasks. NAACL-HLT 2021: 2609-2615 - [c54]Jeff Z. HaoChen, Colin Wei, Adrien Gaidon, Tengyu Ma:
Provable Guarantees for Self-Supervised Deep Learning with Spectral Contrastive Loss. NeurIPS 2021: 5000-5011 - [c53]Garrett Thomas, Yuping Luo, Tengyu Ma:
Safe Reinforcement Learning by Imagining the Near Future. NeurIPS 2021: 13859-13869 - [c52]Colin Wei, Sang Michael Xie, Tengyu Ma:
Why Do Pretrained Language Models Help in Downstream Tasks? An Analysis of Head and Prompt Tuning. NeurIPS 2021: 16158-16170 - [c51]Shengjia Zhao, Michael P. Kim, Roshni Sahoo, Tengyu Ma, Stefano Ermon:
Calibrating Predictions to Decisions: A Novel Approach to Multi-Class Calibration. NeurIPS 2021: 22313-22324 - [c50]Yuping Luo, Tengyu Ma:
Learning Barrier Certificates: Towards Safe Reinforcement Learning with Zero Training-time Violations. NeurIPS 2021: 25621-25632 - [c49]Kefan Dong, Jiaqi Yang, Tengyu Ma:
Provable Model-based Nonlinear Bandit and Reinforcement Learning: Shelve Optimism, Embrace Virtual Curvature. NeurIPS 2021: 26168-26182 - [c48]Alex Damian, Tengyu Ma, Jason D. Lee:
Label Noise SGD Provably Prefers Flat Global Minimizers. NeurIPS 2021: 27449-27461 - [c47]Kevin Huang, Peng Qi, Guangtao Wang, Tengyu Ma, Jing Huang:
Entity and Evidence Guided Document-Level Relation Extraction. RepL4NLP@ACL-IJCNLP 2021: 307-315 - [i77]Kefan Dong, Jiaqi Yang, Tengyu Ma:
Provable Model-based Nonlinear Bandit and Reinforcement Learning: Shelve Optimism, Embrace Virtual Curvature. CoRR abs/2102.04168 (2021) - [i76]Haike Xu, Tengyu Ma, Simon S. Du:
Fine-Grained Gap-Dependent Bounds for Tabular MDPs via Adaptive Multi-Step Bootstrap. CoRR abs/2102.04692 (2021) - [i75]Tengyu Ma:
Why Do Local Methods Solve Nonconvex Problems? CoRR abs/2103.13462 (2021) - [i74]Jeff Z. HaoChen, Colin Wei, Adrien Gaidon, Tengyu Ma:
Provable Guarantees for Self-Supervised Deep Learning with Spectral Contrastive Loss. CoRR abs/2106.04156 (2021) - [i73]Zichuan Lin, Jing Huang, Bowen Zhou, Xiaodong He, Tengyu Ma:
Joint System-Wise Optimization for Pipeline Goal-Oriented Dialog System. CoRR abs/2106.04835 (2021) - [i72]Alex Damian, Tengyu Ma, Jason D. Lee:
Label Noise SGD Provably Prefers Flat Global Minimizers. CoRR abs/2106.06530 (2021) - [i71]Colin Wei, Sang Michael Xie, Tengyu Ma:
Why Do Pretrained Language Models Help in Downstream Tasks? An Analysis of Head and Prompt Tuning. CoRR abs/2106.09226 (2021) - [i70]Yining Chen, Elan Rosenfeld, Mark Sellke, Tengyu Ma, Andrej Risteski:
Iterative Feature Matching: Toward Provable Domain Generalization with Logarithmic Environments. CoRR abs/2106.09913 (2021) - [i69]Shengjia Zhao, Michael P. Kim, Roshni Sahoo, Tengyu Ma, Stefano Ermon:
Calibrating Predictions to Decisions: A Novel Approach to Multi-Class Calibration. CoRR abs/2107.05719 (2021) - [i68]Colin Wei, Yining Chen, Tengyu Ma:
Statistically Meaningful Approximation: a Case Study on Approximating Turing Machines with Transformers. CoRR abs/2107.13163 (2021) - [i67]Yuping Luo, Tengyu Ma:
Learning Barrier Certificates: Towards Safe Reinforcement Learning with Zero Training-time Violations. CoRR abs/2108.01846 (2021) - [i66]Hong Liu, Jeff Z. HaoChen, Adrien Gaidon, Tengyu Ma:
Self-supervised Learning is More Robust to Dataset Imbalance. CoRR abs/2110.05025 (2021) - [i65]Sang Michael Xie, Aditi Raghunathan, Percy Liang, Tengyu Ma:
An Explanation of In-context Learning as Implicit Bayesian Inference. CoRR abs/2111.02080 (2021) - [i64]Margalit Glasgow, Honglin Yuan, Tengyu Ma:
Sharp Bounds for Federated Averaging (Local SGD) and Continuous Perspective. CoRR abs/2111.03741 (2021) - [i63]Ling Pan, Longbo Huang, Tengyu Ma, Huazhe Xu:
Plan Better Amid Conservatism: Offline Multi-Agent Reinforcement Learning with Actor Rectification. CoRR abs/2111.11188 (2021) - [i62]Aviral Kumar, Rishabh Agarwal, Tengyu Ma, Aaron C. Courville, George Tucker, Sergey Levine:
DR3: Value-Based Deep Reinforcement Learning Requires Explicit Regularization. CoRR abs/2112.04716 (2021) - 2020
- [c46]Yuanzhi Li, Tengyu Ma, Hongyang R. Zhang:
Learning Over-Parametrized Two-Layer Neural Networks beyond NTK. COLT 2020: 2613-2682 - [c45]Jiaming Song, Yann N. Dauphin, Michael Auli, Tengyu Ma:
Robust and On-the-Fly Dataset Denoising for Image Classification. ECCV (29) 2020: 556-572 - [c44]Yuping Luo, Huazhe Xu, Tengyu Ma:
Learning Self-Correctable Policies and Value Functions from Demonstrations with Negative Sampling. ICLR 2020 - [c43]Colin Wei, Tengyu Ma:
Improved Sample Complexities for Deep Neural Networks and Robust Classification via an All-Layer Margin. ICLR 2020 - [c42]Kefan Dong, Yuping Luo, Tianhe Yu, Chelsea Finn, Tengyu Ma:
On the Expressivity of Neural Networks for Deep Reinforcement Learning. ICML 2020: 2627-2637 - [c41]Ananya Kumar, Tengyu Ma, Percy Liang:
Understanding Self-Training for Gradual Domain Adaptation. ICML 2020: 5468-5479 - [c40]Colin Wei, Sham M. Kakade, Tengyu Ma:
The Implicit and Explicit Regularization Effects of Dropout. ICML 2020: 10181-10192 - [c39]Shengjia Zhao, Tengyu Ma, Stefano Ermon:
Individual Calibration with Randomized Forecasting. ICML 2020: 11387-11397 - [c38]Yining Chen, Colin Wei, Ananya Kumar, Tengyu Ma:
Self-training Avoids Using Spurious Features Under Domain Shift. NeurIPS 2020 - [c37]Zichuan Lin, Garrett Thomas, Guangwen Yang, Tengyu Ma:
Model-based Adversarial Meta-Reinforcement Learning. NeurIPS 2020 - [c36]Xiang Wang, Chenwei Wu, Jason D. Lee, Tengyu Ma, Rong Ge:
Beyond Lazy Training for Over-parameterized Tensor Decomposition. NeurIPS 2020 - [c35]Tianhe Yu, Garrett Thomas, Lantao Yu, Stefano Ermon, James Y. Zou, Sergey Levine, Chelsea Finn, Tengyu Ma:
MOPO: Model-based Offline Policy Optimization. NeurIPS 2020 - [c34]Honglin Yuan, Tengyu Ma:
Federated Accelerated Stochastic Gradient Descent. NeurIPS 2020 - [p1]Tengyu Ma:
Why Do Local Methods Solve Nonconvex Problems? Beyond the Worst-Case Analysis of Algorithms 2020: 465-485 - [i61]Ananya Kumar, Tengyu Ma, Percy Liang:
Understanding Self-Training for Gradual Domain Adaptation. CoRR abs/2002.11361 (2020) - [i60]Colin Wei, Sham M. Kakade, Tengyu Ma:
The Implicit and Explicit Regularization Effects of Dropout. CoRR abs/2002.12915 (2020) - [i59]Preetum Nakkiran, Prayaag Venkat, Sham M. Kakade, Tengyu Ma:
Optimal Regularization Can Mitigate Double Descent. CoRR abs/2003.01897 (2020) - [i58]Jiaming Song, Lunjia Hu, Yann N. Dauphin, Michael Auli, Tengyu Ma:
Robust and On-the-fly Dataset Denoising for Image Classification. CoRR abs/2003.10647 (2020) - [i57]Tianhe Yu, Garrett Thomas, Lantao Yu, Stefano Ermon, James Zou, Sergey Levine, Chelsea Finn, Tengyu Ma:
MOPO: Model-based Offline Policy Optimization. CoRR abs/2005.13239 (2020) - [i56]Jeff Z. HaoChen, Colin Wei, Jason D. Lee, Tengyu Ma:
Shape Matters: Understanding the Implicit Bias of the Noise Covariance. CoRR abs/2006.08680 (2020) - [i55]Zichuan Lin, Garrett Thomas, Guangwen Yang, Tengyu Ma:
Model-based Adversarial Meta-Reinforcement Learning. CoRR abs/2006.08875 (2020) - [i54]Honglin Yuan, Tengyu Ma:
Federated Accelerated Stochastic Gradient Descent. CoRR abs/2006.08950 (2020) - [i53]Yining Chen, Colin Wei, Ananya Kumar, Tengyu Ma:
Self-training Avoids Using Spurious Features Under Domain Shift. CoRR abs/2006.10032 (2020) - [i52]Shengjia Zhao, Tengyu Ma, Stefano Ermon:
Individual Calibration with Randomized Forecasting. CoRR abs/2006.10288 (2020) - [i51]Yining Chen, Haipeng Luo, Tengyu Ma, Chicheng Zhang:
Active Online Domain Adaptation. CoRR abs/2006.14481 (2020) - [i50]Kaidi Cao, Yining Chen, Junwei Lu, Nikos Aréchiga, Adrien Gaidon, Tengyu Ma:
Heteroskedastic and Imbalanced Deep Learning with Adaptive Regularization. CoRR abs/2006.15766 (2020) - [i49]Sang Michael Xie, Tengyu Ma, Percy Liang:
Simplifying Models with Unlabeled Output Data. CoRR abs/2006.16205 (2020) - [i48]Yuanzhi Li, Tengyu Ma, Hongyang R. Zhang:
Learning Over-Parametrized Two-Layer ReLU Neural Networks beyond NTK. CoRR abs/2007.04596 (2020) - [i47]Kevin Huang, Guangtao Wang, Tengyu Ma, Jing Huang:
Entity and Evidence Guided Relation Extraction for DocRED. CoRR abs/2008.12283 (2020) - [i46]Colin Wei, Kendrick Shen, Yining Chen, Tengyu Ma:
Theoretical Analysis of Self-Training with Deep Networks on Unlabeled Data. CoRR abs/2010.03622 (2020) - [i45]Wenxuan Zhou
, Kevin Huang, Tengyu Ma, Jing Huang:
Document-Level Relation Extraction with Adaptive Thresholding and Localized Context Pooling. CoRR abs/2010.11304 (2020) - [i44]Xiang Wang, Chenwei Wu, Jason D. Lee, Tengyu Ma, Rong Ge:
Beyond Lazy Training for Over-parameterized Tensor Decomposition. CoRR abs/2010.11356 (2020) - [i43]Hong Liu, Jeff Z. HaoChen, Colin Wei, Tengyu Ma:
Meta-learning Transferable Representations with a Single Target Domain. CoRR abs/2011.01418 (2020) - [i42]Sang Michael Xie, Ananya Kumar, Robbie Jones, Fereshte Khani, Tengyu Ma, Percy Liang:
In-N-Out: Pre-Training and Self-Training using Auxiliary Information for Out-of-Distribution Robustness. CoRR abs/2012.04550 (2020)
2010 – 2019
- 2019
- [j7]Xi Chen
, Tengyu Ma, Jiawei Zhang
, Yuan Zhou
:
Optimal Design of Process Flexibility for General Production Systems. Oper. Res. 67(2): 516-531 (2019) - [c33]Shi Dong, Tengyu Ma, Benjamin Van Roy:
On the Performance of Thompson Sampling on Logistic Bandits. COLT 2019: 1158-1160 - [c32]Yu Bai, Tengyu Ma, Andrej Risteski:
Approximability of Discriminators Implies Diversity in GANs. ICLR (Poster) 2019 - [c31]Yuping Luo, Huazhe Xu, Yuanzhi Li, Yuandong Tian, Trevor Darrell, Tengyu Ma:
Algorithmic Framework for Model-based Deep Reinforcement Learning with Theoretical Guarantees. ICLR (Poster) 2019 - [c30]Hongyi Zhang, Yann N. Dauphin, Tengyu Ma:
Fixup Initialization: Residual Learning Without Normalization. ICLR (Poster) 2019 - [c29]Kaidi Cao, Colin Wei, Adrien Gaidon, Nikos Aréchiga, Tengyu Ma:
Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss. NeurIPS 2019: 1565-1576 - [c28]Ananya Kumar, Percy Liang, Tengyu Ma:
Verified Uncertainty Calibration. NeurIPS 2019: 3787-3798 - [c27]Colin Wei, Jason D. Lee, Qiang Liu, Tengyu Ma:
Regularization Matters: Generalization and Optimization of Neural Nets v.s. their Induced Kernel. NeurIPS 2019: 9709-9721 - [c26]Colin Wei, Tengyu Ma:
Data-dependent Sample Complexity of Deep Neural Networks via Lipschitz Augmentation. NeurIPS 2019: 9722-9733 - [c25]Yuanzhi Li, Colin Wei, Tengyu Ma:
Towards Explaining the Regularization Effect of Initial Large Learning Rate in Training Neural Networks. NeurIPS 2019: 11669-11680 - [i41]Hongyi Zhang, Yann N. Dauphin, Tengyu Ma:
Fixup Initialization: Residual Learning Without Normalization. CoRR abs/1901.09321 (2019) - [i40]Colin Wei, Tengyu Ma:
Data-dependent Sample Complexity of Deep Neural Networks via Lipschitz Augmentation. CoRR abs/1905.03684 (2019) - [i39]Shi Dong, Tengyu Ma, Benjamin Van Roy:
On the Performance of Thompson Sampling on Logistic Bandits. CoRR abs/1905.04654 (2019) - [i38]Kaidi Cao, Colin Wei, Adrien Gaidon, Nikos Aréchiga, Tengyu Ma:
Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss. CoRR abs/1906.07413 (2019) - [i37]Yuanzhi Li, Colin Wei, Tengyu Ma:
Towards Explaining the Regularization Effect of Initial Large Learning Rate in Training Neural Networks. CoRR abs/1907.04595 (2019) - [i36]Nicholas C. Landolfi, Garrett Thomas, Tengyu Ma:
A Model-based Approach for Sample-efficient Multi-task Reinforcement Learning. CoRR abs/1907.04964 (2019) - [i35]Yuping Luo, Huazhe Xu, Tengyu Ma:
Learning Self-Correctable Policies and Value Functions from Demonstrations with Negative Sampling. CoRR abs/1907.05634 (2019) - [i34]Ananya Kumar, Percy Liang, Tengyu Ma:
Verified Uncertainty Calibration. CoRR abs/1909.10155 (2019) - [i33]Colin Wei, Tengyu Ma:
Improved Sample Complexities for Deep Networks and Robust Classification via an All-Layer Margin. CoRR abs/1910.04284 (2019) - [i32]Kefan Dong, Yuping Luo, Tengyu Ma:
Bootstrapping the Expressivity with Model-based Planning. CoRR abs/1910.05927 (2019) - 2018
- [j6]Moritz Hardt, Tengyu Ma, Benjamin Recht:
Gradient Descent Learns Linear Dynamical Systems. J. Mach. Learn. Res. 19: 29:1-29:44 (2018) - [j5]Sanjeev Arora, Yuanzhi Li, Yingyu Liang, Tengyu Ma, Andrej Risteski:
Linear Algebraic Structure of Word Senses, with Applications to Polysemy. Trans. Assoc. Comput. Linguistics 6: 483-495 (2018) - [c24]Mikhail Khodak, Nikunj Saunshi, Yingyu Liang, Tengyu Ma, Brandon Stewart, Sanjeev Arora:
A La Carte Embedding: Cheap but Effective Induction of Semantic Feature Vectors. ACL (1) 2018: 12-22 - [c23]Yuanzhi Li, Tengyu Ma, Hongyang Zhang:
Algorithmic Regularization in Over-parameterized Matrix Sensing and Neural Networks with Quadratic Activations. COLT 2018: 2-47 - [c22]Rong Ge, Jason D. Lee, Tengyu Ma:
Learning One-hidden-layer Neural Networks with Landscape Design. ICLR (Poster) 2018 - [c21]Tengyu Ma:
Generalization and equilibrium in generative adversarial nets (GANs) (invited talk). STOC 2018: 2 - [i31]Mikhail Khodak, Nikunj Saunshi, Yingyu Liang, Tengyu Ma, Brandon Stewart, Sanjeev Arora:
A La Carte Embedding: Cheap but Effective Induction of Semantic Feature Vectors. CoRR abs/1805.05388 (2018) - [i30]Xi Chen, Tengyu Ma, Jiawei Zhang, Yuan Zhou:
Optimal Design of Process Flexibility for General Production Systems. CoRR abs/1806.02894 (2018) - [i29]Yu Bai, Tengyu Ma, Andrej Risteski:
Approximability of Discriminators Implies Diversity in GANs. CoRR abs/1806.10586 (2018) - [i28]Huazhe Xu, Yuanzhi Li, Yuandong Tian, Trevor Darrell, Tengyu Ma:
Algorithmic Framework for Model-based Reinforcement Learning with Theoretical Guarantees. CoRR abs/1807.03858 (2018) - [i27]Colin Wei, Jason D. Lee, Qiang Liu, Tengyu Ma:
On the Margin Theory of Feedforward Neural Networks. CoRR abs/1810.05369 (2018) - 2017
- [j4]Jason D. Lee, Qihang Lin, Tengyu Ma, Tianbao Yang:
Distributed Stochastic Variance Reduced Gradient Methods by Sampling Extra Data with Replacement. J. Mach. Learn. Res. 18: 122:1-122:43 (2017) - [c20]Holden Lee, Rong Ge, Tengyu Ma, Andrej Risteski, Sanjeev Arora:
On the Ability of Neural Nets to Express Distributions. COLT 2017: 1271-1296 - [c19]Sanjeev Arora, Yingyu Liang, Tengyu Ma:
A Simple but Tough-to-Beat Baseline for Sentence Embeddings. ICLR (Poster) 2017 - [c18]Moritz Hardt, Tengyu Ma:
Identity Matters in Deep Learning. ICLR (Poster) 2017 - [c17]Sanjeev Arora, Rong Ge, Yingyu Liang, Tengyu Ma, Yi Zhang:
Generalization and Equilibrium in Generative Adversarial Nets (GANs). ICML 2017: 224-232 - [c16]Rong Ge, Tengyu Ma:
On the Optimization Landscape of Tensor Decompositions. NIPS 2017: 3653-3663 - [c15]Sanjeev Arora, Rong Ge, Tengyu Ma, Andrej Risteski:
Provable learning of noisy-OR networks. STOC 2017: 1057-1066 - [c14]Naman Agarwal, Zeyuan Allen Zhu, Brian Bullins, Elad Hazan
, Tengyu Ma:
Finding approximate local minima faster than gradient descent. STOC 2017: 1195-1199 - [i26]Holden Lee, Rong Ge, Andrej Risteski, Tengyu Ma, Sanjeev Arora:
On the ability of neural nets to express distributions. CoRR abs/1702.07028 (2017) - [i25]Sanjeev Arora, Rong Ge, Yingyu Liang, Tengyu Ma, Yi Zhang:
Generalization and Equilibrium in Generative Adversarial Nets (GANs). CoRR abs/1703.00573 (2017) - [i24]Rong Ge, Tengyu Ma:
On the Optimization Landscape of Tensor Decompositions. CoRR abs/1706.05598 (2017) - [i23]Rong Ge, Jason D. Lee, Tengyu Ma:
Learning One-hidden-layer Neural Networks with Landscape Design. CoRR abs/1711.00501 (2017) - [i22]Yuanzhi Li, Tengyu Ma, Hongyang Zhang:
Algorithmic Regularization in Over-parameterized Matrix Recovery. CoRR abs/1712.09203 (2017) - 2016
- [j3]Tengyu Ma, Bo Tang, Yajun Wang:
The Simulated Greedy Algorithm for Several Submodular Matroid Secretary Problems. Theory Comput. Syst. 58(4): 681-706 (2016) - [j2]Sanjeev Arora, Yuanzhi Li, Yingyu Liang, Tengyu Ma, Andrej Risteski:
A Latent Variable Model Approach to PMI-based Word Embeddings. Trans. Assoc. Comput. Linguistics 4: 385-399 (2016) - [c13]Tengyu Ma, Jonathan Shi, David Steurer
:
Polynomial-Time Tensor Decompositions with Sum-of-Squares. FOCS 2016: 438-446 - [c12]Sanjeev Arora, Rong Ge, Frederic Koehler, Tengyu Ma, Ankur Moitra:
Provable Algorithms for Inference in Topic Models. ICML 2016: 2859-2867 - [c11]Rong Ge, Jason D. Lee, Tengyu Ma:
Matrix Completion has No Spurious Local Minimum. NIPS 2016: 2973-2981 - [c10]Elad Hazan, Tengyu Ma:
A Non-generative Framework and Convex Relaxations for Unsupervised Learning. NIPS 2016: 3306-3314 - [c9]Mark Braverman, Ankit Garg, Tengyu Ma, Huy L. Nguyen, David P. Woodruff:
Communication lower bounds for statistical estimation problems via a distributed data processing inequality. STOC 2016: 1011-1020 - [i21]Sanjeev Arora, Yuanzhi Li, Yingyu Liang, Tengyu Ma, Andrej Risteski:
Linear Algebraic Structure of Word Senses, with Applications to Polysemy. CoRR abs/1601.03764 (2016) - [i20]Rong Ge, Jason D. Lee, Tengyu Ma:
Matrix Completion has No Spurious Local Minimum. CoRR abs/1605.07272 (2016) - [i19]Sanjeev Arora, Rong Ge, Frederic Koehler, Tengyu Ma, Ankur Moitra:
Provable Algorithms for Inference in Topic Models. CoRR abs/1605.08491 (2016) - [i18]Moritz Hardt, Tengyu Ma, Benjamin Recht:
Gradient Descent Learns Linear Dynamical Systems. CoRR abs/1609.05191 (2016) - [i17]Elad Hazan, Tengyu Ma:
A Non-generative Framework and Convex Relaxations for Unsupervised Learning. CoRR abs/1610.01132 (2016) - [i16]Tengyu Ma, Jonathan Shi, David Steurer:
Polynomial-time Tensor Decompositions with Sum-of-Squares. CoRR abs/1610.01980 (2016) - [i15]Naman Agarwal, Zeyuan Allen Zhu, Brian Bullins, Elad Hazan, Tengyu Ma:
Finding Approximate Local Minima for Nonconvex Optimization in Linear Time. CoRR abs/1611.01146 (2016) - [i14]Moritz Hardt, Tengyu Ma:
Identity Matters in Deep Learning. CoRR abs/1611.04231 (2016) - [i13]Sanjeev Arora, Rong Ge, Tengyu Ma, Andrej Risteski:
Provable learning of Noisy-or Networks. CoRR abs/1612.08795 (2016) - 2015
- [c8]Rong Ge, Tengyu Ma:
Decomposing Overcomplete 3rd Order Tensors using Sum-of-Squares Algorithms. APPROX-RANDOM 2015: 829-849 - [c7]Sanjeev Arora, Rong Ge, Tengyu Ma, Ankur Moitra:
Simple, Efficient, and Neural Algorithms for Sparse Coding. COLT 2015: 113-149 - [c6]Dan Garber, Elad Hazan, Tengyu Ma:
Online Learning of Eigenvectors. ICML 2015: 560-568 - [c5]Tengyu Ma, Avi Wigderson:
Sum-of-Squares Lower Bounds for Sparse PCA. NIPS 2015: 1612-1620 - [i12]Sanjeev Arora, Yuanzhi Li, Yingyu Liang, Tengyu Ma, Andrej Risteski:
Random Walks on Context Spaces: Towards an Explanation of the Mysteries of Semantic Word Embeddings. CoRR abs/1502.03520 (2015) - [i11]Sanjeev Arora, Rong Ge, Tengyu Ma, Ankur Moitra:
Simple, Efficient, and Neural Algorithms for Sparse Coding. CoRR abs/1503.00778 (2015) - [i10]Rong Ge, Tengyu Ma:
Decomposing Overcomplete 3rd Order Tensors using Sum-of-Squares Algorithms. CoRR abs/1504.05287 (2015) - [i9]Mark Braverman, Ankit Garg, Tengyu Ma, Huy L. Nguyen, David P. Woodruff:
Communication Lower Bounds for Statistical Estimation Problems via a Distributed Data Processing Inequality. CoRR abs/1506.07216 (2015) - [i8]Tengyu Ma, Avi Wigderson:
Sum-of-Squares Lower Bounds for Sparse PCA. CoRR abs/1507.06370 (2015) - [i7]Jason D. Lee, Tengyu Ma, Qihang Lin:
Distributed Stochastic Variance Reduced Gradient Methods. CoRR abs/1507.07595 (2015) - [i6]Sanjeev Arora, Yingyu Liang, Tengyu Ma:
Why are deep nets reversible: A simple theory, with implications for training. CoRR abs/1511.05653 (2015) - 2014
- [c4]Sanjeev Arora, Aditya Bhaskara, Rong Ge, Tengyu Ma:
Provable Bounds for Learning Some Deep Representations. ICML 2014: 584-592 - [c3]Ankit Garg, Tengyu Ma, Huy L. Nguyen:
On Communication Cost of Distributed Statistical Estimation and Dimensionality. NIPS 2014: 2726-2734 - [i5]Sanjeev Arora, Aditya Bhaskara, Rong Ge, Tengyu Ma:
More Algorithms for Provable Dictionary Learning. CoRR abs/1401.0579 (2014) - [i4]Ankit Garg, Tengyu Ma, Huy L. Nguyen:
Lower Bound for High-Dimensional Statistical Learning Problem via Direct-Sum Theorem. CoRR abs/1405.1665 (2014) - 2013
- [j1]Tengyu Ma, Xiaoming Sun, Huacheng Yu:
On a conjecture of Butler and Graham. Des. Codes Cryptogr. 69(3): 265-274 (2013) - [c2]Tengyu Ma, Bo Tang, Yajun Wang:
The Simulated Greedy Algorithm for Several Submodular Matroid Secretary Problems. STACS 2013: 478-489 - [i3]Sanjeev Arora, Aditya Bhaskara, Rong Ge, Tengyu Ma:
Provable Bounds for Learning Some Deep Representations. CoRR abs/1310.6343 (2013) - 2011
- [c1]Tengyu Ma, Xiaoming Sun
, Huacheng Yu:
A New Variation of Hat Guessing Games. COCOON 2011: 616-626 - [i2]Tengyu Ma, Xiaoming Sun, Huacheng Yu:
A New Variation of Hat Guessing Games. CoRR abs/1101.0869 (2011) - [i1]Tengyu Ma, Xiaoming Sun, Huacheng Yu:
On a Conjecture of Butler and Graham. CoRR abs/1107.2027 (2011)
Coauthor Index
![](https://dblp1.uni-trier.de/img/cog.dark.24x24.png)
manage site settings
To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.
Unpaywalled article links
Add open access links from to the list of external document links (if available).
Privacy notice: By enabling the option above, your browser will contact the API of unpaywall.org to load hyperlinks to open access articles. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Unpaywall privacy policy.
Archived links via Wayback Machine
For web page which are no longer available, try to retrieve content from the of the Internet Archive (if available).
Privacy notice: By enabling the option above, your browser will contact the API of archive.org to check for archived content of web pages that are no longer available. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Internet Archive privacy policy.
Reference lists
Add a list of references from ,
, and
to record detail pages.
load references from crossref.org and opencitations.net
Privacy notice: By enabling the option above, your browser will contact the APIs of crossref.org, opencitations.net, and semanticscholar.org to load article reference information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Crossref privacy policy and the OpenCitations privacy policy, as well as the AI2 Privacy Policy covering Semantic Scholar.
Citation data
Add a list of citing articles from and
to record detail pages.
load citations from opencitations.net
Privacy notice: By enabling the option above, your browser will contact the API of opencitations.net and semanticscholar.org to load citation information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the OpenCitations privacy policy as well as the AI2 Privacy Policy covering Semantic Scholar.
OpenAlex data
Load additional information about publications from .
Privacy notice: By enabling the option above, your browser will contact the API of openalex.org to load additional information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the information given by OpenAlex.
last updated on 2024-08-08 20:11 CEST by the dblp team
all metadata released as open data under CC0 1.0 license
see also: Terms of Use | Privacy Policy | Imprint