Zhiyuan Li - RankMe

84 papers A* 35A 2Journal 42Unranked 4

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Recursive Models for Long-Horizon Reasoning. CoRR Chenxiao Yang, Nathan Srebro, Zhiyuan Li
2025	A*	`conf`	A Theory of Learning with Autoregressive Chain of Thought. COLT Nirmit Joshi, Gal Vardi, Adam Block, Surbhi Goel, Zhiyuan Li, Theodor Misiakiewicz, Nathan Srebro
2025	J	`jnl`	A Theory of Learning with Autoregressive Chain of Thought. CoRR Nirmit Joshi, Gal Vardi, Adam Block, Surbhi Goel, Zhiyuan Li, Theodor Misiakiewicz, Nathan Srebro
2025	A*	`conf`	Chain-of-Thought Provably Enables Learning the (Otherwise) Unlearnable. ICLR Chenxiao Yang, Zhiyuan Li, David Wipf
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	J	`jnl`	On Powerful Ways to Generate: Autoregression, Diffusion, and Beyond. CoRR Chenxiao Yang, Cai Zhou, David Wipf, Zhiyuan Li
2025	A*	`conf`	PENCIL: Long Thoughts with Short Memory. ICML Chenxiao Yang, Nathan Srebro, David McAllester, Zhiyuan Li
2025	J	`jnl`	PENCIL: Long Thoughts with Short Memory. CoRR Chenxiao Yang, Nathan Srebro, David McAllester, Zhiyuan Li
2025	A*	`conf`	Reasoning with Latent Thoughts: On the Power of Looped Transformers. ICLR Nikunj Saunshi, Nishanth Dikkala, Zhiyuan Li, Sanjiv Kumar, Sashank J. Reddi
2025	J	`jnl`	Reasoning with Latent Thoughts: On the Power of Looped Transformers. CoRR Nikunj Saunshi, Nishanth Dikkala, Zhiyuan Li, Sanjiv Kumar, Sashank J. Reddi
2025	J	`jnl`	Shift is Good: Mismatched Data Mixing Improves Test Performance. CoRR Marko Medvedev, Kaifeng Lyu, Zhiyuan Li, Nathan Srebro
2025	A*	`conf`	Structured Preconditioners in Adaptive Optimization: A Unified Analysis. ICML Shuo Xie, Tianhao Wang, Sashank J. Reddi, Sanjiv Kumar, Zhiyuan Li
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
2025	A*	`conf`	Weak-to-Strong Generalization Even in Random Feature Networks, Provably. ICML Marko Medvedev, Kaifeng Lyu, Dingli Yu, Sanjeev Arora, Zhiyuan Li, Nathan Srebro
2025	J	`jnl`	Weak-to-Strong Generalization Even in Random Feature Networks, Provably. CoRR Marko Medvedev, Kaifeng Lyu, Dingli Yu, Sanjeev Arora, Zhiyuan Li, Nathan Srebro
2024	J	`jnl`	Chain of Thought Empowers Transformers to Solve Inherently Serial Problems. CoRR Zhiyuan Li, Hong Liu, Denny Zhou, Tengyu Ma
2024	A*	`conf`	Dichotomy of Early and Late Phase Implicit Biases Can Provably Induce Grokking. ICLR Kaifeng Lyu, Jikai Jin, Zhiyuan Li, Simon Shaolei Du, Jason D. Lee, Wei Hu
2024	A*	`conf`	Simplicity Bias via Global Convergence of Sharpness Minimization. ICML Khashayar Gatmiry, Zhiyuan Li, Sashank J. Reddi, Stefanie Jegelka
2024	J	`jnl`	Simplicity Bias via Global Convergence of Sharpness Minimization. CoRR Khashayar Gatmiry, Zhiyuan Li, Sashank J. Reddi, Stefanie Jegelka
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	A*	`conf`	The Marginal Value of Momentum for Small Learning Rate SGD. ICLR Runzhe Wang, Sadhika Malladi, Tianhao Wang, Kaifeng Lyu, Zhiyuan Li
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	J	`jnl`	Dichotomy of Early and Late Phase Implicit Biases Can Provably Induce Grokking. CoRR Kaifeng Lyu, Jikai Jin, Zhiyuan Li, Simon S. Du, Jason D. Lee, Wei Hu
2023	A*	`conf`	How Sharpness-Aware Minimization Minimizes Sharpness? ICLR Kaiyue Wen, Tengyu Ma, Zhiyuan Li
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	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`	The Marginal Value of Momentum for Small Learning Rate SGD. CoRR Runzhe Wang, Sadhika Malladi, Tianhao Wang, Kaifeng Lyu, Zhiyuan Li
2023	A*	`conf`	Understanding Incremental Learning of Gradient Descent: A Fine-grained Analysis of Matrix Sensing. ICML Jikai Jin, Zhiyuan Li, Kaifeng Lyu, Simon Shaolei Du, Jason D. Lee
2023	J	`jnl`	Understanding Incremental Learning of Gradient Descent: A Fine-grained Analysis of Matrix Sensing. CoRR Jikai Jin, Zhiyuan Li, Kaifeng Lyu, Simon S. Du, Jason D. Lee
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
2022	—	`—`	Bridging Theory and Practice in Deep Learning: Optimization and Generalization Zhiyuan Li
2022	A*	`conf`	Fast Mixing of Stochastic Gradient Descent with Normalization and Weight Decay. NeurIPS Zhiyuan Li, Tianhao Wang, Dingli Yu
2022	J	`jnl`	How Does Sharpness-Aware Minimization Minimize Sharpness? CoRR Kaiyue Wen, Tengyu Ma, Zhiyuan Li
2022	A*	`conf`	Implicit Bias of Gradient Descent on Reparametrized Models: On Equivalence to Mirror Descent. NeurIPS Zhiyuan Li, Tianhao Wang, Jason D. Lee, Sanjeev Arora
2022	J	`jnl`	Implicit Bias of Gradient Descent on Reparametrized Models: On Equivalence to Mirror Descent. CoRR Zhiyuan Li, Tianhao Wang, Jason D. Lee, Sanjeev Arora
2022	A*	`conf`	Robust Training of Neural Networks Using Scale Invariant Architectures. ICML Zhiyuan Li, Srinadh Bhojanapalli, Manzil Zaheer, Sashank J. Reddi, Sanjiv Kumar
2022	J	`jnl`	Robust Training of Neural Networks using Scale Invariant Architectures. CoRR Zhiyuan Li, Srinadh Bhojanapalli, Manzil Zaheer, Sashank J. Reddi, Sanjiv Kumar
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	J	`jnl`	Understanding Gradient Descent on Edge of Stability in Deep Learning. CoRR Sanjeev Arora, Zhiyuan Li, Abhishek Panigrahi
2022	A*	`conf`	Understanding Gradient Descent on the Edge of Stability in Deep Learning. ICML Sanjeev Arora, Zhiyuan Li, Abhishek Panigrahi
2022	A*	`conf`	Understanding the Generalization Benefit of Normalization Layers: Sharpness Reduction. NeurIPS Kaifeng Lyu, Zhiyuan Li, Sanjeev Arora
2022	J	`jnl`	Understanding the Generalization Benefit of Normalization Layers: Sharpness Reduction. CoRR Kaifeng Lyu, Zhiyuan Li, Sanjeev Arora
2022	A*	`conf`	What Happens after SGD Reaches Zero Loss? --A Mathematical Framework. ICLR Zhiyuan Li, Tianhao Wang, Sanjeev Arora
2021	A*	`conf`	Gradient Descent on Two-layer Nets: Margin Maximization and Simplicity Bias. NeurIPS Kaifeng Lyu, Zhiyuan Li, Runzhe Wang, Sanjeev Arora
2021	J	`jnl`	Gradient Descent on Two-layer Nets: Margin Maximization and Simplicity Bias. CoRR Kaifeng Lyu, Zhiyuan Li, Runzhe Wang, Sanjeev Arora
2021	A*	`conf`	On the Validity of Modeling SGD with Stochastic Differential Equations (SDEs). NeurIPS Zhiyuan Li, Sadhika Malladi, Sanjeev Arora
2021	J	`jnl`	On the Validity of Modeling SGD with Stochastic Differential Equations (SDEs). CoRR Zhiyuan Li, Sadhika Malladi, Sanjeev Arora
2021	A*	`conf`	Towards Resolving the Implicit Bias of Gradient Descent for Matrix Factorization: Greedy Low-Rank Learning. ICLR Zhiyuan Li, Yuping Luo, Kaifeng Lyu
2021	J	`jnl`	What Happens after SGD Reaches Zero Loss? -A Mathematical Framework. CoRR Zhiyuan Li, Tianhao Wang, Sanjeev Arora
2021	A	`conf`	When is particle filtering efficient for planning in partially observed linear dynamical systems? UAI Simon S. Du, Wei Hu, Zhiyuan Li, Ruoqi Shen, Zhao Song, Jiajun Wu
2021	A*	`conf`	Why Are Convolutional Nets More Sample-Efficient than Fully-Connected Nets? ICLR Zhiyuan Li, Yi Zhang, Sanjeev Arora
2020	A*	`conf`	An Exponential Learning Rate Schedule for Deep Learning. ICLR Zhiyuan Li, Sanjeev Arora
2020	A*	`conf`	Harnessing the Power of Infinitely Wide Deep Nets on Small-data Tasks. ICLR Sanjeev Arora, Simon S. Du, Zhiyuan Li, Ruslan Salakhutdinov, Ruosong Wang, Dingli Yu
2020	A*	`conf`	Reconciling Modern Deep Learning with Traditional Optimization Analyses: The Intrinsic Learning Rate. NeurIPS Zhiyuan Li, Kaifeng Lyu, Sanjeev Arora
2020	J	`jnl`	Reconciling Modern Deep Learning with Traditional Optimization Analyses: The Intrinsic Learning Rate. CoRR Zhiyuan Li, Kaifeng Lyu, Sanjeev Arora
2020	A*	`conf`	Simple and Effective Regularization Methods for Training on Noisily Labeled Data with Generalization Guarantee. ICLR Wei Hu, Zhiyuan Li, Dingli Yu
2020	J	`jnl`	Towards Resolving the Implicit Bias of Gradient Descent for Matrix Factorization: Greedy Low-Rank Learning. CoRR Zhiyuan Li, Yuping Luo, Kaifeng Lyu
2020	J	`jnl`	When is Particle Filtering Efficient for POMDP Sequential Planning? CoRR Simon S. Du, Wei Hu, Zhiyuan Li, Ruoqi Shen, Zhao Song, Jiajun Wu
2020	J	`jnl`	Why Are Convolutional Nets More Sample-Efficient than Fully-Connected Nets? CoRR Zhiyuan Li, Yi Zhang, Sanjeev Arora
2019	J	`jnl`	An Exponential Learning Rate Schedule for Deep Learning. CoRR Zhiyuan Li, Sanjeev Arora
2019	J	`jnl`	Enhanced Convolutional Neural Tangent Kernels. CoRR Zhiyuan Li, Ruosong Wang, Dingli Yu, Simon S. Du, Wei Hu, Ruslan Salakhutdinov, Sanjeev Arora
2019	A*	`conf`	Explaining Landscape Connectivity of Low-cost Solutions for Multilayer Nets. NeurIPS Rohith Kuditipudi, Xiang Wang, Holden Lee, Yi Zhang, Zhiyuan Li, Wei Hu, Rong Ge, Sanjeev Arora
2019	J	`jnl`	Explaining Landscape Connectivity of Low-cost Solutions for Multilayer Nets. CoRR Rohith Kuditipudi, Xiang Wang, Holden Lee, Yi Zhang, Zhiyuan Li, Wei Hu, Sanjeev Arora, Rong Ge
2019	A*	`conf`	Fine-Grained Analysis of Optimization and Generalization for Overparameterized Two-Layer Neural Networks. ICML Sanjeev Arora, Simon S. Du, Wei Hu, Zhiyuan Li, Ruosong Wang
2019	J	`jnl`	Fine-Grained Analysis of Optimization and Generalization for Overparameterized Two-Layer Neural Networks. CoRR Sanjeev Arora, Simon S. Du, Wei Hu, Zhiyuan Li, Ruosong Wang
2019	J	`jnl`	Harnessing the Power of Infinitely Wide Deep Nets on Small-data Tasks. CoRR Sanjeev Arora, Simon S. Du, Zhiyuan Li, Ruslan Salakhutdinov, Ruosong Wang, Dingli Yu
2019	A*	`conf`	On Exact Computation with an Infinitely Wide Neural Net. NeurIPS Sanjeev Arora, Simon S. Du, Wei Hu, Zhiyuan Li, Ruslan Salakhutdinov, Ruosong Wang
2019	J	`jnl`	On Exact Computation with an Infinitely Wide Neural Net. CoRR Sanjeev Arora, Simon S. Du, Wei Hu, Zhiyuan Li, Ruslan Salakhutdinov, Ruosong Wang
2019	—	`conf`	The role of over-parametrization in generalization of neural networks. ICLR (Poster) Behnam Neyshabur, Zhiyuan Li, Srinadh Bhojanapalli, Yann LeCun, Nathan Srebro
2019	—	`conf`	Theoretical Analysis of Auto Rate-Tuning by Batch Normalization. ICLR (Poster) Sanjeev Arora, Zhiyuan Li, Kaifeng Lyu
2019	J	`jnl`	Understanding Generalization of Deep Neural Networks Trained with Noisy Labels. CoRR Wei Hu, Zhiyuan Li, Dingli Yu
2018	A*	`conf`	Online Improper Learning with an Approximation Oracle. NeurIPS Elad Hazan, Wei Hu, Yuanzhi Li, Zhiyuan Li
2018	J	`jnl`	Online Improper Learning with an Approximation Oracle. CoRR Elad Hazan, Wei Hu, Yuanzhi Li, Zhiyuan Li
2018	J	`jnl`	Theoretical Analysis of Auto Rate-Tuning by Batch Normalization. CoRR Sanjeev Arora, Zhiyuan Li, Kaifeng Lyu
2018	J	`jnl`	Towards Understanding the Role of Over-Parametrization in Generalization of Neural Networks. CoRR Behnam Neyshabur, Zhiyuan Li, Srinadh Bhojanapalli, Yann LeCun, Nathan Srebro
2017	A	`conf`	Stability of Generalized Two-sided Markets with Transaction Thresholds. AAMAS Zhiyuan Li, Yicheng Liu, Pingzhong Tang, Tingting Xu, Wei Zhan
2016	J	`jnl`	Fast Convergence of Common Learning Algorithms in Games. CoRR Dylan J. Foster, Zhiyuan Li, Thodoris Lykouris, Karthik Sridharan, Éva Tardos
2016	—	`conf`	Learning in Games: Robustness of Fast Convergence. NIPS Dylan J. Foster, Zhiyuan Li, Thodoris Lykouris, Karthik Sridharan, Éva Tardos
2016	—	`conf`	Solving Marginal MAP Problems with NP Oracles and Parity Constraints. NIPS Yexiang Xue, Zhiyuan Li, Stefano Ermon, Carla P. Gomes, Bart Selman
2016	J	`jnl`	Solving Marginal MAP Problems with NP Oracles and Parity Constraints. CoRR Yexiang Xue, Zhiyuan Li, Stefano Ermon, Carla P. Gomes, Bart Selman