![](https://dblp.dagstuhl.de/img/logo.ua.320x120.png)
![](https://dblp.dagstuhl.de/img/dropdown.dark.16x16.png)
![](https://dblp.dagstuhl.de/img/peace.dark.16x16.png)
Остановите войну!
for scientists:
![search dblp search dblp](https://dblp.dagstuhl.de/img/search.dark.16x16.png)
![search dblp](https://dblp.dagstuhl.de/img/search.dark.16x16.png)
default search action
Yuanzhi Li
Person information
Refine list
![note](https://dblp.dagstuhl.de/img/note-mark.dark.12x12.png)
refinements active!
zoomed in on ?? of ?? records
view refined list in
export refined list as
Journal Articles
- 2023
- [j7]Shuyu Zhang
, Shangran Xie
, Yuanzhi Li, Mengqi Yuan, Xinming Qian:
Detection of Gas Pipeline Leakage Using Distributed Optical Fiber Sensors: Multi-Physics Analysis of Leakage-Fiber Coupling Mechanism in Soil Environment. Sensors 23(12): 5430 (2023) - [j6]Qinsheng Hou
, Wenrui Diao
, Yanhao Wang
, Chenglin Mao
, Lingyun Ying
, Song Liu
, Xiaofeng Liu
, Yuanzhi Li
, Shanqing Guo
, Meining Nie
, Haixin Duan
:
Can We Trust the Phone Vendors? Comprehensive Security Measurements on the Android Firmware Ecosystem. IEEE Trans. Software Eng. 49(7): 3901-3921 (2023) - 2021
- [j5]Zeyuan Allen-Zhu, Yuanzhi Li, Aarti Singh, Yining Wang
:
Near-optimal discrete optimization for experimental design: a regret minimization approach. Math. Program. 186(1): 439-478 (2021) - 2018
- [j4]Yuanzhi Li, Lingsheng Shi:
Geodesic cycles in random graphs. Discret. Math. 341(5): 1275-1281 (2018) - [j3]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) - 2017
- [j2]Kose John, Yuanzhi Li, Jiaren Pang:
Does Corporate Governance Matter More for High Financial Slack Firms? Manag. Sci. 63(6): 1872-1891 (2017) - 2016
- [j1]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)
Conference and Workshop Papers
- 2024
- [c83]Ruiqian Nai, Zixin Wen, Ji Li, Yuanzhi Li, Yang Gao:
Revisiting Disentanglement in Downstream Tasks: A Study on Its Necessity for Abstract Visual Reasoning. AAAI 2024: 14405-14413 - [c82]Zixiang Chen, Yihe Deng, Yuanzhi Li, Quanquan Gu:
Understanding Transferable Representation Learning and Zero-shot Transfer in CLIP. ICLR 2024 - [c81]Aakash Lahoti, Stefani Karp, Ezra Winston, Aarti Singh, Yuanzhi Li:
Role of Locality and Weight Sharing in Image-Based Tasks: A Sample Complexity Separation between CNNs, LCNs, and FCNs. ICLR 2024 - [c80]Yue Wu, Xuan Tang, Tom M. Mitchell, Yuanzhi Li:
SmartPlay : A Benchmark for LLMs as Intelligent Agents. ICLR 2024 - 2023
- [c79]Zeyuan Allen-Zhu, Yuanzhi Li:
Backward Feature Correction: How Deep Learning Performs Deep (Hierarchical) Learning. COLT 2023: 4598 - [c78]Yuan Cao, Difan Zou, Yuanzhi Li, Quanquan Gu:
The Implicit Bias of Batch Normalization in Linear Models and Two-layer Linear Convolutional Neural Networks. COLT 2023: 5699-5753 - [c77]Zeyuan Allen-Zhu, Yuanzhi Li:
Towards Understanding Ensemble, Knowledge Distillation and Self-Distillation in Deep Learning. ICLR 2023 - [c76]Zeyuan Allen-Zhu, Yuanzhi Li:
Forward Super-Resolution: How Can GANs Learn Hierarchical Generative Models for Real-World Distributions. ICLR 2023 - [c75]Sitan Chen, Sinho Chewi, Jerry Li, Yuanzhi Li, Adil Salim, Anru Zhang:
Sampling is as easy as learning the score: theory for diffusion models with minimal data assumptions. ICLR 2023 - [c74]Difan Zou, Yuan Cao, Yuanzhi Li, Quanquan Gu:
Understanding the Generalization of Adam in Learning Neural Networks with Proper Regularization. ICLR 2023 - [c73]Yuchen Li, Yuanzhi Li, Andrej Risteski:
How Do Transformers Learn Topic Structure: Towards a Mechanistic Understanding. ICML 2023: 19689-19729 - [c72]Dhruv Malik, Conor Igoe, Yuanzhi Li, Aarti Singh:
Weighted Tallying Bandits: Overcoming Intractability via Repeated Exposure Optimality. ICML 2023: 23590-23609 - [c71]Difan Zou, Yuan Cao, Yuanzhi Li, Quanquan Gu:
The Benefits of Mixup for Feature Learning. ICML 2023: 43423-43479 - [c70]Sitan Chen, Sinho Chewi, Holden Lee, Yuanzhi Li, Jianfeng Lu, Adil Salim:
The probability flow ODE is provably fast. NeurIPS 2023 - [c69]Kaiqi Jiang, Dhruv Malik, Yuanzhi Li:
How Does Adaptive Optimization Impact Local Neural Network Geometry? NeurIPS 2023 - [c68]Yue Wu, Yewen Fan, Paul Pu Liang, Amos Azaria, Yuanzhi Li, Tom M. Mitchell:
Read and Reap the Rewards: Learning to Play Atari with the Help of Instruction Manuals. NeurIPS 2023 - [c67]Yue Wu, So Yeon Min, Shrimai Prabhumoye, Yonatan Bisk, Russ Salakhutdinov, Amos Azaria, Tom M. Mitchell, Yuanzhi Li:
SPRING: Studying Papers and Reasoning to play Games. NeurIPS 2023 - [c66]Sitan Chen, Jerry Li, Yuanzhi Li, Anru R. Zhang:
Learning Polynomial Transformations via Generalized Tensor Decompositions. STOC 2023: 1671-1684 - 2022
- [c65]Dhruv Malik, Yuanzhi Li, Aarti Singh:
Complete Policy Regret Bounds for Tallying Bandits. COLT 2022: 5146-5174 - [c64]Sitan Chen, Jerry Li, Yuanzhi Li, Raghu Meka:
Minimax Optimality (Probably) Doesn't Imply Distribution Learning for GANs. ICLR 2022 - [c63]Edward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, Weizhu Chen:
LoRA: Low-Rank Adaptation of Large Language Models. ICLR 2022 - [c62]Samy Jelassi, Yuanzhi Li:
Towards understanding how momentum improves generalization in deep learning. ICML 2022: 9965-10040 - [c61]Qinsheng Hou, Wenrui Diao
, Yanhao Wang, Xiaofeng Liu, Song Liu, Lingyun Ying, Shanqing Guo, Yuanzhi Li, Meining Nie, Haixin Duan:
Large-scale Security Measurements on the Android Firmware Ecosystem. ICSE 2022: 1257-1268 - [c60]Sitan Chen, Jerry Li, Yuanzhi Li:
Learning (Very) Simple Generative Models Is Hard. NeurIPS 2022 - [c59]Zixiang Chen, Yihe Deng, Yue Wu, Quanquan Gu, Yuanzhi Li:
Towards Understanding the Mixture-of-Experts Layer in Deep Learning. NeurIPS 2022 - [c58]Samy Jelassi, Michael E. Sander, Yuanzhi Li:
Vision Transformers provably learn spatial structure. NeurIPS 2022 - [c57]Zixin Wen, Yuanzhi Li:
The Mechanism of Prediction Head in Non-contrastive Self-supervised Learning. NeurIPS 2022 - 2021
- [c56]Sébastien Bubeck, Yuanzhi Li, Dheeraj M. Nagaraj:
A Law of Robustness for Two-Layers Neural Networks. COLT 2021: 804-820 - [c55]Yuanzhi Li, Ruosong Wang, Lin F. Yang
:
Settling the Horizon-Dependence of Sample Complexity in Reinforcement Learning. FOCS 2021: 965-976 - [c54]Zeyuan Allen-Zhu, Yuanzhi Li:
Feature Purification: How Adversarial Training Performs Robust Deep Learning. FOCS 2021: 977-988 - [c53]Yuanzhi Li, Shanshan Xu, Yuling Luo, Sheng Qin, Shunsheng Zhang, Min Su:
A Highly Efficient Profiled Power Analysis Attack Based on Power Leakage Fitting. HPCC/DSS/SmartCity/DependSys 2021: 791-796 - [c52]Lei Li, Lei Wang, Yuanzhi Li, Jie Sheng:
Mixed Deep Reinforcement Learning-behavior Tree for Intelligent Agents Design. ICAART (1) 2021: 113-124 - [c51]Jeremy Cohen, Simran Kaur, Yuanzhi Li, J. Zico Kolter, Ameet Talwalkar:
Gradient Descent on Neural Networks Typically Occurs at the Edge of Stability. ICLR 2021 - [c50]Dhruv Malik, Aldo Pacchiano, Vishwak Srinivasan, Yuanzhi Li:
Sample Efficient Reinforcement Learning In Continuous State Spaces: A Perspective Beyond Linearity. ICML 2021: 7412-7422 - [c49]Zixin Wen, Yuanzhi Li:
Toward Understanding the Feature Learning Process of Self-supervised Contrastive Learning. ICML 2021: 11112-11122 - [c48]Dhruv Malik, Yuanzhi Li, Pradeep Ravikumar:
When Is Generalizable Reinforcement Learning Tractable? NeurIPS 2021: 8032-8045 - [c47]Stefani Karp, Ezra Winston, Yuanzhi Li, Aarti Singh:
Local Signal Adaptivity: Provable Feature Learning in Neural Networks Beyond Kernels. NeurIPS 2021: 24883-24897 - [c46]Haojie Wang, Jidong Zhai, Mingyu Gao, Zixuan Ma, Shizhi Tang
, Liyan Zheng, Yuanzhi Li, Kaiyuan Rong, Yuanyong Chen, Zhihao Jia:
PET: Optimizing Tensor Programs with Partially Equivalent Transformations and Automated Corrections. OSDI 2021: 37-54 - [c45]Komal Dhull, Jingyan Wang, Nihar B. Shah, Yuanzhi Li, R. Ravi:
A heuristic for statistical seriation. UAI 2021: 621-631 - 2020
- [c44]Sébastien Bubeck, Yuanzhi Li, Yuval Peres, Mark Sellke:
Non-Stochastic Multi-Player Multi-Armed Bandits: Optimal Rate With Collision Information, Sublinear Without. COLT 2020: 961-987 - [c43]Yuanzhi Li, Tengyu Ma, Hongyang R. Zhang:
Learning Over-Parametrized Two-Layer Neural Networks beyond NTK. COLT 2020: 2613-2682 - [c42]Sébastien Bubeck, Bo'az Klartag, Yin Tat Lee, Yuanzhi Li, Mark Sellke:
Chasing Nested Convex Bodies Nearly Optimally. SODA 2020: 1496-1508 - 2019
- [c41]Sébastien Bubeck, Qijia Jiang, Yin Tat Lee, Yuanzhi Li, Aaron Sidford:
Near-optimal method for highly smooth convex optimization. COLT 2019: 492-507 - [c40]Sébastien Bubeck, Yuanzhi Li, Haipeng Luo, Chen-Yu Wei:
Improved Path-length Regret Bounds for Bandits. COLT 2019: 508-528 - [c39]Alexander V. Gasnikov, Pavel E. Dvurechensky, Eduard Gorbunov, Evgeniya A. Vorontsova, Daniil Selikhanovych, César A. Uribe, Bo Jiang, Haoyue Wang, Shuzhong Zhang, Sébastien Bubeck, Qijia Jiang, Yin Tat Lee, Yuanzhi Li, Aaron Sidford:
Near Optimal Methods for Minimizing Convex Functions with Lipschitz $p$-th Derivatives. COLT 2019: 1392-1393 - [c38]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 - [c37]Zeyuan Allen-Zhu, Yuanzhi Li, Zhao Song:
A Convergence Theory for Deep Learning via Over-Parameterization. ICML 2019: 242-252 - [c36]Zeyuan Allen-Zhu, Yuanzhi Li, Yingyu Liang:
Learning and Generalization in Overparameterized Neural Networks, Going Beyond Two Layers. NeurIPS 2019: 6155-6166 - [c35]Zeyuan Allen-Zhu, Yuanzhi Li, Zhao Song:
On the Convergence Rate of Training Recurrent Neural Networks. NeurIPS 2019: 6673-6685 - [c34]Zeyuan Allen-Zhu, Yuanzhi Li:
What Can ResNet Learn Efficiently, Going Beyond Kernels? NeurIPS 2019: 9015-9025 - [c33]Zeyuan Allen-Zhu, Yuanzhi Li:
Can SGD Learn Recurrent Neural Networks with Provable Generalization? NeurIPS 2019: 10331-10341 - [c32]Yuanzhi Li, Colin Wei, Tengyu Ma:
Towards Explaining the Regularization Effect of Initial Large Learning Rate in Training Neural Networks. NeurIPS 2019: 11669-11680 - [c31]Sébastien Bubeck, Qijia Jiang, Yin Tat Lee, Yuanzhi Li, Aaron Sidford:
Complexity of Highly Parallel Non-Smooth Convex Optimization. NeurIPS 2019: 13900-13909 - [c30]Sébastien Bubeck, Yin Tat Lee, Yuanzhi Li, Mark Sellke
:
Competitively chasing convex bodies. STOC 2019: 861-868 - 2018
- [c29]Sébastien Bubeck, Michael B. Cohen, Yuanzhi Li:
Sparsity, variance and curvature in multi-armed bandits. ALT 2018: 111-127 - [c28]Yuanzhi Li, Tengyu Ma, Hongyang Zhang:
Algorithmic Regularization in Over-parameterized Matrix Sensing and Neural Networks with Quadratic Activations. COLT 2018: 2-47 - [c27]Yuanzhi Li, Yingyu Liang:
Learning Mixtures of Linear Regressions with Nearly Optimal Complexity. COLT 2018: 1125-1144 - [c26]Zeyuan Allen-Zhu, Sébastien Bubeck, Yuanzhi Li:
Make the Minority Great Again: First-Order Regret Bound for Contextual Bandits. ICML 2018: 186-194 - [c25]Robert Kleinberg, Yuanzhi Li, Yang Yuan:
An Alternative View: When Does SGD Escape Local Minima? ICML 2018: 2703-2712 - [c24]Yuanzhi Li, Yoram Singer:
The Well-Tempered Lasso. ICML 2018: 3030-3038 - [c23]Zeyuan Allen-Zhu, Yuanzhi Li:
NEON2: Finding Local Minima via First-Order Oracles. NeurIPS 2018: 3720-3730 - [c22]Elad Hazan, Wei Hu, Yuanzhi Li, Zhiyuan Li:
Online Improper Learning with an Approximation Oracle. NeurIPS 2018: 5657-5665 - [c21]Yuanzhi Li, Yingyu Liang:
Learning Overparameterized Neural Networks via Stochastic Gradient Descent on Structured Data. NeurIPS 2018: 8168-8177 - [c20]Xi Chen, Yuanzhi Li, Jieming Mao:
A Nearly Instance Optimal Algorithm for Top-k Ranking under the Multinomial Logit Model. SODA 2018: 2504-2522 - [c19]Zeyuan Allen-Zhu, Ankit Garg, Yuanzhi Li, Rafael Mendes de Oliveira, Avi Wigderson:
Operator scaling via geodesically convex optimization, invariant theory and polynomial identity testing. STOC 2018: 172-181 - [c18]Sébastien Bubeck, Michael B. Cohen, Yin Tat Lee, Yuanzhi Li:
An homotopy method for lp regression provably beyond self-concordance and in input-sparsity time. STOC 2018: 1130-1137 - 2017
- [c17]Zeyuan Allen-Zhu, Yuanzhi Li:
First Efficient Convergence for Streaming k-PCA: A Global, Gap-Free, and Near-Optimal Rate. FOCS 2017: 487-492 - [c16]Zeyuan Allen-Zhu, Yuanzhi Li, Rafael Mendes de Oliveira, Avi Wigderson:
Much Faster Algorithms for Matrix Scaling. FOCS 2017: 890-901 - [c15]Zeyuan Allen-Zhu, Yuanzhi Li:
Doubly Accelerated Methods for Faster CCA and Generalized Eigendecomposition. ICML 2017: 98-106 - [c14]Zeyuan Allen-Zhu, Yuanzhi Li:
Faster Principal Component Regression and Stable Matrix Chebyshev Approximation. ICML 2017: 107-115 - [c13]Zeyuan Allen-Zhu, Yuanzhi Li:
Follow the Compressed Leader: Faster Online Learning of Eigenvectors and Faster MMWU. ICML 2017: 116-125 - [c12]Zeyuan Allen-Zhu, Yuanzhi Li, Aarti Singh, Yining Wang:
Near-Optimal Design of Experiments via Regret Minimization. ICML 2017: 126-135 - [c11]Yuanzhi Li, Yingyu Liang:
Provable Alternating Gradient Descent for Non-negative Matrix Factorization with Strong Correlations. ICML 2017: 2062-2070 - [c10]Yuanzhi Li, Yang Yuan:
Convergence Analysis of Two-layer Neural Networks with ReLU Activation. NIPS 2017: 597-607 - [c9]Zeyuan Allen-Zhu, Elad Hazan, Wei Hu, Yuanzhi Li:
Linear Convergence of a Frank-Wolfe Type Algorithm over Trace-Norm Balls. NIPS 2017: 6191-6200 - 2016
- [c8]Yuanzhi Li, Yingyu Liang, Andrej Risteski:
Recovery guarantee of weighted low-rank approximation via alternating minimization. ICML 2016: 2358-2367 - [c7]Zeyuan Allen Zhu, Yuanzhi Li:
Even Faster SVD Decomposition Yet Without Agonizing Pain. NIPS 2016: 974-982 - [c6]Andrej Risteski, Yuanzhi Li:
Approximate maximum entropy principles via Goemans-Williamson with applications to provable variational methods. NIPS 2016: 4628-4636 - [c5]Andrej Risteski, Yuanzhi Li:
Algorithms and matching lower bounds for approximately-convex optimization. NIPS 2016: 4745-4753 - [c4]Yuanzhi Li, Yingyu Liang, Andrej Risteski:
Recovery Guarantee of Non-negative Matrix Factorization via Alternating Updates. NIPS 2016: 4988-4996 - 2014
- [c3]Hongyu Mao, Keqin Wang, Rui Ma, Yifan Gao, Yuanzhi Li, Kun Chen
, Dejun Xie, Wei Zhu, Ting Wang, Huaiqing Wang:
An Automatic News Analysis and Opinion Sharing System for Exchange Rate Analysis. ICEBE 2014: 303-307 - 2013
- [c2]Yining Wang, Liwei Wang, Yuanzhi Li, Di He, Tie-Yan Liu:
A Theoretical Analysis of NDCG Type Ranking Measures. COLT 2013: 25-54 - 2007
- [c1]Hui Chen, Yuanzhi Li:
An Empirical Research of Factors Influencing the Decision-Making of Chinese Online Shoppers. I3E (1) 2007: 202-210
Informal and Other Publications
- 2024
- [i103]Sitan Chen, Yuanzhi Li:
Provably learning a multi-head attention layer. CoRR abs/2402.04084 (2024) - [i102]Ruiqian Nai, Zixin Wen, Ji Li, Yuanzhi Li, Yang Gao:
Revisiting Disentanglement in Downstream Tasks: A Study on Its Necessity for Abstract Visual Reasoning. CoRR abs/2403.00352 (2024) - [i101]Aakash Lahoti, Stefani Karp, Ezra Winston, Aarti Singh, Yuanzhi Li:
Role of Locality and Weight Sharing in Image-Based Tasks: A Sample Complexity Separation between CNNs, LCNs, and FCNs. CoRR abs/2403.15707 (2024) - [i100]Zeyuan Allen-Zhu, Yuanzhi Li:
Physics of Language Models: Part 3.3, Knowledge Capacity Scaling Laws. CoRR abs/2404.05405 (2024) - [i99]Junpeng Liu, Yifan Song, Bill Yuchen Lin, Wai Lam, Graham Neubig, Yuanzhi Li, Xiang Yue:
VisualWebBench: How Far Have Multimodal LLMs Evolved in Web Page Understanding and Grounding? CoRR abs/2404.05955 (2024) - [i98]Yue Wu, Yewen Fan, So Yeon Min, Shrimai Prabhumoye, Stephen McAleer, Yonatan Bisk, Ruslan Salakhutdinov, Yuanzhi Li, Tom M. Mitchell:
AgentKit: Flow Engineering with Graphs, not Coding. CoRR abs/2404.11483 (2024) - [i97]Marah I Abdin, Sam Ade Jacobs, Ammar Ahmad Awan, Jyoti Aneja, Ahmed Awadallah, Hany Awadalla, Nguyen Bach, Amit Bahree, Arash Bakhtiari, Harkirat S. Behl, Alon Benhaim, Misha Bilenko, Johan Bjorck, Sébastien Bubeck, Martin Cai, Caio César Teodoro Mendes, Weizhu Chen, Vishrav Chaudhary, Parul Chopra, Allie Del Giorno, Gustavo de Rosa, Matthew Dixon, Ronen Eldan, Dan Iter, Amit Garg, Abhishek Goswami, Suriya Gunasekar, Emman Haider, Junheng Hao, Russell J. Hewett, Jamie Huynh, Mojan Javaheripi, Xin Jin, Piero Kauffmann, Nikos Karampatziakis, Dongwoo Kim, Mahoud Khademi, Lev Kurilenko, James R. Lee, Yin Tat Lee, Yuanzhi Li, Chen Liang, Weishung Liu, Eric Lin, Zeqi Lin, Piyush Madan, Arindam Mitra, Hardik Modi, Anh Nguyen, Brandon Norick, Barun Patra, Daniel Perez-Becker, Thomas Portet, Reid Pryzant, Heyang Qin, Marko Radmilac, Corby Rosset, Sambudha Roy, Olatunji Ruwase, Olli Saarikivi, Amin Saied, Adil Salim, Michael Santacroce, Shital Shah, Ning Shang, Hiteshi Sharma, Xia Song, Masahiro Tanaka, Xin Wang, Rachel Ward, Guanhua Wang, Philipp Witte, Michael Wyatt, Can Xu, Jiahang Xu, Sonali Yadav, Fan Yang, Ziyi Yang, Donghan Yu, Chengruidong Zhang, Cyril Zhang, Jianwen Zhang, Li Lyna Zhang, Yi Zhang, Yue Zhang, Yunan Zhang, Xiren Zhou:
Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone. CoRR abs/2404.14219 (2024) - [i96]Ahmet Cagri Duzgun, Samy Jelassi, Yuanzhi Li:
How Does Overparameterization Affect Features? CoRR abs/2407.00968 (2024) - 2023
- [i95]Michael Santacroce, Zixin Wen, Yelong Shen, Yuanzhi Li:
What Matters In The Structured Pruning of Generative Language Models? CoRR abs/2302.03773 (2023) - [i94]Yue Wu, Yewen Fan, Paul Pu Liang, Amos Azaria, Yuanzhi Li, Tom M. Mitchell:
Read and Reap the Rewards: Learning to Play Atari with the Help of Instruction Manuals. CoRR abs/2302.04449 (2023) - [i93]Yuchen Li, Yuanzhi Li, Andrej Risteski:
How Do Transformers Learn Topic Structure: Towards a Mechanistic Understanding. CoRR abs/2303.04245 (2023) - [i92]Difan Zou, Yuan Cao, Yuanzhi Li, Quanquan Gu:
The Benefits of Mixup for Feature Learning. CoRR abs/2303.08433 (2023) - [i91]Sébastien Bubeck, Varun Chandrasekaran, Ronen Eldan, Johannes Gehrke, Eric Horvitz, Ece Kamar, Peter Lee, Yin Tat Lee, Yuanzhi Li, Scott M. Lundberg, Harsha Nori, Hamid Palangi, Marco Túlio Ribeiro, Yi Zhang:
Sparks of Artificial General Intelligence: Early experiments with GPT-4. CoRR abs/2303.12712 (2023) - [i90]Yunwei Ren, Yuanzhi Li:
On the Importance of Contrastive Loss in Multimodal Learning. CoRR abs/2304.03717 (2023) - [i89]Yue Wu, So Yeon Min, Yonatan Bisk, Ruslan Salakhutdinov, Amos Azaria, Yuanzhi Li, Tom M. Mitchell, Shrimai Prabhumoye:
Plan, Eliminate, and Track - Language Models are Good Teachers for Embodied Agents. CoRR abs/2305.02412 (2023) - [i88]Dhruv Malik, Conor Igoe, Yuanzhi Li, Aarti Singh:
Weighted Tallying Bandits: Overcoming Intractability via Repeated Exposure Optimality. CoRR abs/2305.02955 (2023) - [i87]Ronen Eldan, Yuanzhi Li:
TinyStories: How Small Can Language Models Be and Still Speak Coherent English? CoRR abs/2305.07759 (2023) - [i86]Sitan Chen, Sinho Chewi, Holden Lee, Yuanzhi Li, Jianfeng Lu, Adil Salim:
The probability flow ODE is provably fast. CoRR abs/2305.11798 (2023) - [i85]Zeyuan Allen-Zhu, Yuanzhi Li:
Physics of Language Models: Part 1, Context-Free Grammar. CoRR abs/2305.13673 (2023) - [i84]Yue Wu, Shrimai Prabhumoye, So Yeon Min, Yonatan Bisk, Ruslan Salakhutdinov, Amos Azaria, Tom M. Mitchell, Yuanzhi Li:
SPRING: GPT-4 Out-performs RL Algorithms by Studying Papers and Reasoning. CoRR abs/2305.15486 (2023) - [i83]Yan Pan, Yuanzhi Li:
Toward Understanding Why Adam Converges Faster Than SGD for Transformers. CoRR abs/2306.00204 (2023) - [i82]Binghui Li, Yuanzhi Li:
Why Clean Generalization and Robust Overfitting Both Happen in Adversarial Training. CoRR abs/2306.01271 (2023) - [i81]Eric Luxenberg, Dhruv Malik, Yuanzhi Li, Aarti Singh, Stephen P. Boyd:
Specifying and Solving Robust Empirical Risk Minimization Problems Using CVXPY. CoRR abs/2306.05649 (2023) - [i80]Suriya Gunasekar, Yi Zhang, Jyoti Aneja, Caio César Teodoro Mendes, Allie Del Giorno, Sivakanth Gopi, Mojan Javaheripi, Piero Kauffmann, Gustavo de Rosa, Olli Saarikivi, Adil Salim, Shital Shah, Harkirat Singh Behl, Xin Wang, Sébastien Bubeck, Ronen Eldan, Adam Tauman Kalai, Yin Tat Lee, Yuanzhi Li:
Textbooks Are All You Need. CoRR abs/2306.11644 (2023) - [i79]Yuan Cao, Difan Zou, Yuanzhi Li, Quanquan Gu:
The Implicit Bias of Batch Normalization in Linear Models and Two-layer Linear Convolutional Neural Networks. CoRR abs/2306.11680 (2023) - [i78]Samy Jelassi, Stéphane d'Ascoli, Carles Domingo-Enrich, Yuhuai Wu, Yuanzhi Li, François Charton:
Length Generalization in Arithmetic Transformers. CoRR abs/2306.15400 (2023) - [i77]Michael Santacroce, Yadong Lu, Han Yu, Yuanzhi Li, Yelong Shen:
Efficient RLHF: Reducing the Memory Usage of PPO. CoRR abs/2309.00754 (2023) - [i76]Yuanzhi Li, Sébastien Bubeck, Ronen Eldan, Allie Del Giorno, Suriya Gunasekar, Yin Tat Lee:
Textbooks Are All You Need II: phi-1.5 technical report. CoRR abs/2309.05463 (2023) - [i75]Zeyuan Allen Zhu, Yuanzhi Li:
Physics of Language Models: Part 3.1, Knowledge Storage and Extraction. CoRR abs/2309.14316 (2023) - [i74]Zeyuan Allen-Zhu, Yuanzhi Li:
Physics of Language Models: Part 3.2, Knowledge Manipulation. CoRR abs/2309.14402 (2023) - [i73]Zixiang Chen, Yihe Deng, Yuanzhi Li, Quanquan Gu:
Understanding Transferable Representation Learning and Zero-shot Transfer in CLIP. CoRR abs/2310.00927 (2023) - [i72]Yue Wu, Xuan Tang, Tom M. Mitchell, Yuanzhi Li:
SmartPlay : A Benchmark for LLMs as Intelligent Agents. CoRR abs/2310.01557 (2023) - [i71]Yuanzhi Li, Raghu Meka, Rina Panigrahy, Kulin Shah:
Simple Mechanisms for Representing, Indexing and Manipulating Concepts. CoRR abs/2310.12143 (2023) - [i70]Ruoqi Shen, Sébastien Bubeck, Ronen Eldan, Yin Tat Lee, Yuanzhi Li, Yi Zhang:
Positional Description Matters for Transformers Arithmetic. CoRR abs/2311.14737 (2023) - [i69]Harsha Nori, Yin Tat Lee, Sheng Zhang, Dean Carignan, Richard Edgar, Nicolò Fusi, Nicholas King, Jonathan Larson, Yuanzhi Li, Weishung Liu, Renqian Luo, Scott Mayer McKinney, Robert Osazuwa Ness, Hoifung Poon, Tao Qin, Naoto Usuyama, Chris White, Eric Horvitz:
Can Generalist Foundation Models Outcompete Special-Purpose Tuning? Case Study in Medicine. CoRR abs/2311.16452 (2023) - [i68]Bingbin Liu, Sébastien Bubeck, Ronen Eldan, Janardhan Kulkarni, Yuanzhi Li, Anh Nguyen, Rachel Ward, Yi Zhang:
TinyGSM: achieving >80% on GSM8k with small language models. CoRR abs/2312.09241 (2023) - 2022
- [i67]Sitan Chen, Jerry Li, Yuanzhi Li, Raghu Meka:
Minimax Optimality (Probably) Doesn't Imply Distribution Learning for GANs. CoRR abs/2201.07206 (2022) - [i66]Sitan Chen, Jerry Li, Yuanzhi Li, Anru R. Zhang:
Learning Polynomial Transformations. CoRR abs/2204.04209 (2022) - [i65]Dhruv Malik, Yuanzhi Li, Aarti Singh:
Complete Policy Regret Bounds for Tallying Bandits. CoRR abs/2204.11174 (2022) - [i64]Zixin Wen, Yuanzhi Li:
The Mechanism of Prediction Head in Non-contrastive Self-supervised Learning. CoRR abs/2205.06226 (2022) - [i63]Sitan Chen, Jerry Li, Yuanzhi Li:
Learning (Very) Simple Generative Models Is Hard. CoRR abs/2205.16003 (2022) - [i62]Samy Jelassi, Yuanzhi Li:
Towards understanding how momentum improves generalization in deep learning. CoRR abs/2207.05931 (2022) - [i61]Zixiang Chen, Yihe Deng, Yue Wu, Quanquan Gu, Yuanzhi Li:
Towards Understanding Mixture of Experts in Deep Learning. CoRR abs/2208.02813 (2022) - [i60]Sitan Chen, Sinho Chewi, Jerry Li, Yuanzhi Li, Adil Salim, Anru R. Zhang:
Sampling is as easy as learning the score: theory for diffusion models with minimal data assumptions. CoRR abs/2209.11215 (2022) - [i59]Samy Jelassi, David Dobre, Arthur Mensch, Yuanzhi Li, Gauthier Gidel:
Dissecting adaptive methods in GANs. CoRR abs/2210.04319 (2022) - [i58]Samy Jelassi, Michael E. Sander, Yuanzhi Li:
Vision Transformers provably learn spatial structure. CoRR abs/2210.09221 (2022) - [i57]Kaiqi Jiang, Dhruv Malik, Yuanzhi Li:
How Does Adaptive Optimization Impact Local Neural Network Geometry? CoRR abs/2211.02254 (2022) - 2021
- [i56]Dhruv Malik, Yuanzhi Li, Pradeep Ravikumar:
When Is Generalizable Reinforcement Learning Tractable? CoRR abs/2101.00300 (2021) - [i55]Jeremy Cohen, Simran Kaur, Yuanzhi Li, J. Zico Kolter, Ameet Talwalkar:
Gradient Descent on Neural Networks Typically Occurs at the Edge of Stability. CoRR abs/2103.00065 (2021) - [i54]Zixin Wen, Yuanzhi Li:
Toward Understanding the Feature Learning Process of Self-supervised Contrastive Learning. CoRR abs/2105.15134 (2021) - [i53]Zeyuan Allen-Zhu, Yuanzhi Li:
Forward Super-Resolution: How Can GANs Learn Hierarchical Generative Models for Real-World Distributions. CoRR abs/2106.02619 (2021) - [i52]Dhruv Malik, Aldo Pacchiano, Vishwak Srinivasan, Yuanzhi Li:
Sample Efficient Reinforcement Learning In Continuous State Spaces: A Perspective Beyond Linearity. CoRR abs/2106.07814 (2021) - [i51]Edward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Weizhu Chen:
LoRA: Low-Rank Adaptation of Large Language Models. CoRR abs/2106.09685 (2021) - [i50]Difan Zou, Yuan Cao, Yuanzhi Li, Quanquan Gu:
Understanding the Generalization of Adam in Learning Neural Networks with Proper Regularization. CoRR abs/2108.11371 (2021) - [i49]Zehao Dou, Yuanzhi Li:
On the One-sided Convergence of Adam-type Algorithms in Non-convex Non-concave Min-max Optimization. CoRR abs/2109.14213 (2021) - [i48]Yuanzhi Li, Ruosong Wang, Lin F. Yang:
Settling the Horizon-Dependence of Sample Complexity in Reinforcement Learning. CoRR abs/2111.00633 (2021) - 2020
- [i47]Zeyuan Allen-Zhu, Yuanzhi Li:
Backward Feature Correction: How Deep Learning Performs Deep Learning. CoRR abs/2001.04413 (2020) - [i46]Yuanzhi Li, Zehao Dou:
When can Wasserstein GANs minimize Wasserstein Distance? CoRR abs/2003.04033 (2020) - [i45]Zeyuan Allen-Zhu, Yuanzhi Li:
Feature Purification: How Adversarial Training Performs Robust Deep Learning. CoRR abs/2005.10190 (2020) - [i44]Yuanzhi Li, Tengyu Ma, Hongyang R. Zhang:
Learning Over-Parametrized Two-Layer ReLU Neural Networks beyond NTK. CoRR abs/2007.04596 (2020) - [i43]Sébastien Bubeck, Yuanzhi Li, Dheeraj Nagaraj:
A law of robustness for two-layers neural networks. CoRR abs/2009.14444 (2020) - [i42]Zeyuan Allen-Zhu, Yuanzhi Li:
Towards Understanding Ensemble, Knowledge Distillation and Self-Distillation in Deep Learning. CoRR abs/2012.09816 (2020) - 2019
- [i41]Sébastien Bubeck, Yuanzhi Li, Haipeng Luo, Chen-Yu Wei:
Improved Path-length Regret Bounds for Bandits. CoRR abs/1901.10604 (2019) - [i40]Zeyuan Allen-Zhu, Yuanzhi Li:
Can SGD Learn Recurrent Neural Networks with Provable Generalization? CoRR abs/1902.01028 (2019) - [i39]Sébastien Bubeck, Yuanzhi Li, Yuval Peres, Mark Sellke:
Non-Stochastic Multi-Player Multi-Armed Bandits: Optimal Rate With Collision Information, Sublinear Without. CoRR abs/1904.12233 (2019) - [i38]Zeyuan Allen-Zhu, Yuanzhi Li:
What Can ResNet Learn Efficiently, Going Beyond Kernels? CoRR abs/1905.10337 (2019) - [i37]Sébastien Bubeck, Qijia Jiang, Yin Tat Lee, Yuanzhi Li, Aaron Sidford:
Complexity of Highly Parallel Non-Smooth Convex Optimization. CoRR abs/1906.10655 (2019) - [i36]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) - 2018
- [i35]Zeyuan Allen-Zhu, Sébastien Bubeck, Yuanzhi Li:
Make the Minority Great Again: First-Order Regret Bound for Contextual Bandits. CoRR abs/1802.03386 (2018) - [i34]Robert Kleinberg, Yuanzhi Li, Yang Yuan:
An Alternative View: When Does SGD Escape Local Minima? CoRR abs/1802.06175 (2018) - [i33]Yuanzhi Li, Yingyu Liang:
Learning Mixtures of Linear Regressions with Nearly Optimal Complexity. CoRR abs/1802.07895 (2018) - [i32]Zeyuan Allen-Zhu, Ankit Garg, Yuanzhi Li, Rafael Mendes de Oliveira, Avi Wigderson:
Operator Scaling via Geodesically Convex Optimization, Invariant Theory and Polynomial Identity Testing. CoRR abs/1804.01076 (2018) - [i31]Elad Hazan, Wei Hu, Yuanzhi Li, Zhiyuan Li:
Online Improper Learning with an Approximation Oracle. CoRR abs/1804.07837 (2018) - [i30]Yuanzhi Li, Yoram Singer:
The Well Tempered Lasso. CoRR abs/1806.03190 (2018) - [i29]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) - [i28]Yuanzhi Li, Yingyu Liang:
Learning Overparameterized Neural Networks via Stochastic Gradient Descent on Structured Data. CoRR abs/1808.01204 (2018) - [i27]Zeyuan Allen-Zhu, Yuanzhi Li, Zhao Song:
On the Convergence Rate of Training Recurrent Neural Networks. CoRR abs/1810.12065 (2018) - [i26]Sébastien Bubeck, Yin Tat Lee, Yuanzhi Li, Mark Sellke:
Competitively Chasing Convex Bodies. CoRR abs/1811.00887 (2018) - [i25]Sébastien Bubeck, Yin Tat Lee, Yuanzhi Li, Mark Sellke:
Chasing Nested Convex Bodies Nearly Optimally. CoRR abs/1811.00999 (2018) - [i24]Zeyuan Allen-Zhu, Yuanzhi Li, Zhao Song:
A Convergence Theory for Deep Learning via Over-Parameterization. CoRR abs/1811.03962 (2018) - [i23]Zeyuan Allen-Zhu, Yuanzhi Li, Yingyu Liang:
Learning and Generalization in Overparameterized Neural Networks, Going Beyond Two Layers. CoRR abs/1811.04918 (2018) - 2017
- [i22]Zeyuan Allen Zhu, Yuanzhi Li:
Follow the Compressed Leader: Faster Algorithms for Matrix Multiplicative Weight Updates. CoRR abs/1701.01722 (2017) - [i21]Zeyuan Allen Zhu, Yuanzhi Li, Rafael Mendes de Oliveira, Avi Wigderson:
Much Faster Algorithms for Matrix Scaling. CoRR abs/1704.02315 (2017) - [i20]Yuanzhi Li, Yang Yuan:
Convergence Analysis of Two-layer Neural Networks with ReLU Activation. CoRR abs/1705.09886 (2017) - [i19]Yuanzhi Li, Yingyu Liang:
Provable Alternating Gradient Descent for Non-negative Matrix Factorization with Strong Correlations. CoRR abs/1706.04097 (2017) - [i18]Xi Chen, Yuanzhi Li, Jieming Mao:
A Nearly Instance Optimal Algorithm for Top-k Ranking under the Multinomial Logit Model. CoRR abs/1707.08238 (2017) - [i17]Zeyuan Allen-Zhu, Elad Hazan, Wei Hu, Yuanzhi Li:
Linear Convergence of a Frank-Wolfe Type Algorithm over Trace-Norm Balls. CoRR abs/1708.02105 (2017) - [i16]Sébastien Bubeck, Michael B. Cohen, Yuanzhi Li:
Sparsity, variance and curvature in multi-armed bandits. CoRR abs/1711.01037 (2017) - [i15]Sébastien Bubeck, Michael B. Cohen, Yin Tat Lee, Yuanzhi Li:
An homotopy method for 𝓵p regression provably beyond self-concordance and in input-sparsity time. CoRR abs/1711.01328 (2017) - [i14]Zeyuan Allen-Zhu, Yuanzhi Li, Aarti Singh, Yining Wang:
Near-Optimal Discrete Optimization for Experimental Design: A Regret Minimization Approach. CoRR abs/1711.05174 (2017) - [i13]Zeyuan Allen-Zhu, Yuanzhi Li:
Neon2: Finding Local Minima via First-Order Oracles. CoRR abs/1711.06673 (2017) - [i12]Yuanzhi Li, Tengyu Ma, Hongyang Zhang:
Algorithmic Regularization in Over-parameterized Matrix Recovery. CoRR abs/1712.09203 (2017) - 2016
- [i11]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) - [i10]Yuanzhi Li, Yingyu Liang, Andrej Risteski:
Recovery guarantee of weighted low-rank approximation via alternating minimization. CoRR abs/1602.02262 (2016) - [i9]Elad Hazan, Yuanzhi Li:
An optimal algorithm for bandit convex optimization. CoRR abs/1603.04350 (2016) - [i8]Yuanzhi Li, Andrej Risteski:
Approximate maximum entropy principles via Goemans-Williamson with applications to provable variational methods. CoRR abs/1607.03360 (2016) - [i7]Zeyuan Allen Zhu, Yuanzhi Li:
Even Faster SVD Decomposition Yet Without Agonizing Pain. CoRR abs/1607.03463 (2016) - [i6]Zeyuan Allen Zhu, Yuanzhi Li:
Doubly Accelerated Methods for Faster CCA and Generalized Eigendecomposition. CoRR abs/1607.06017 (2016) - [i5]Zeyuan Allen Zhu, Yuanzhi Li:
Fast Global Convergence of Online PCA. CoRR abs/1607.07837 (2016) - [i4]Zeyuan Allen Zhu, Yuanzhi Li:
Faster Principal Component Regression via Optimal Polynomial Approximation to sgn(x). CoRR abs/1608.04773 (2016) - [i3]Yuanzhi Li, Yingyu Liang, Andrej Risteski:
Recovery Guarantee of Non-negative Matrix Factorization via Alternating Updates. CoRR abs/1611.03819 (2016) - 2015
- [i2]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) - 2013
- [i1]Yining Wang, Liwei Wang, Yuanzhi Li, Di He, Tie-Yan Liu, Wei Chen:
A Theoretical Analysis of NDCG Type Ranking Measures. CoRR abs/1304.6480 (2013)
Coauthor Index
![](https://dblp.dagstuhl.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 2024-08-16 18:29 CEST by the dblp team
all metadata released as open data under CC0 1.0 license
see also: Terms of Use | Privacy Policy | Imprint