Resultats de la cerca - Wu, Jingfeng

Fixed Design Analysis of Regularization-Based Continual Learning per Li, Haoran, Wu, Jingfeng, Braverman, Vladimir

Obtenir text complet

Memory-Statistics Tradeoff in Continual Learning with Structural Regularization per Li, Haoran, Wu, Jingfeng, Braverman, Vladimir

Obtenir text complet

Large Stepsizes Accelerate Gradient Descent for Regularized Logistic Regression per Wu, Jingfeng, Marion, Pierre, Bartlett, Peter

Obtenir text complet

In-Context Learning of a Linear Transformer Block: Benefits of the MLP Component and One-Step GD Initialization per Zhang, Ruiqi, Wu, Jingfeng, Bartlett, Peter L.

Obtenir text complet

Improved Scaling Laws in Linear Regression via Data Reuse per Lin, Licong, Wu, Jingfeng, Bartlett, Peter L.

Obtenir text complet

Context-Scaling versus Task-Scaling in In-Context Learning per Abedsoltan, Amirhesam, Radhakrishnan, Adityanarayanan, Wu, Jingfeng, Belkin, Mikhail

Obtenir text complet

Benefits of Early Stopping in Gradient Descent for Overparameterized Logistic Regression per Wu, Jingfeng, Bartlett, Peter, Telgarsky, Matus, Yu, Bin

Obtenir text complet

On the Collapse Errors Induced by the Deterministic Sampler for Diffusion Models per Zhang, Yi, Liao, Zhenyu, Wu, Jingfeng, Zou, Difan

Obtenir text complet

Large Stepsize Gradient Descent for Logistic Loss: Non-Monotonicity of the Loss Improves Optimization Efficiency per Wu, Jingfeng, Bartlett, Peter L., Telgarsky, Matus, Yu, Bin

Obtenir text complet

Minimax Optimal Convergence of Gradient Descent in Logistic Regression via Large and Adaptive Stepsizes per Zhang, Ruiqi, Wu, Jingfeng, Lin, Licong, Bartlett, Peter L.

Obtenir text complet

CloudNativeSim: a toolkit for modeling and simulation of cloud-native applications per Wu, Jingfeng, Xu, Minxian, He, Yiyuan, Ye, Kejiang, Xu, Chengzhong

Obtenir text complet

Large Stepsize Gradient Descent for Non-Homogeneous Two-Layer Networks: Margin Improvement and Fast Optimization per Cai, Yuhang, Wu, Jingfeng, Mei, Song, Lindsey, Michael, Bartlett, Peter L.

Obtenir text complet

UELLM: A Unified and Efficient Approach for LLM Inference Serving per He, Yiyuan, Xu, Minxian, Wu, Jingfeng, Zheng, Wanyi, Ye, Kejiang, Xu, Chengzhong

Obtenir text complet

Unlock the Potential of Fine-grained LLM Serving via Dynamic Module Scaling per Wu, Jingfeng, He, Yiyuan, Xu, Minxian, Gao, Xitong, Ye, Kejiang, Xu, Chengzhong

Obtenir text complet

Cloud Native System for LLM Inference Serving per Xu, Minxian, Liao, Junhan, Wu, Jingfeng, He, Yiyuan, Ye, Kejiang, Xu, Chengzhong

Obtenir text complet

How Many Pretraining Tasks Are Needed for In-Context Learning of Linear Regression? per Wu, Jingfeng, Zou, Difan, Chen, Zixiang, Braverman, Vladimir, Gu, Quanquan, Bartlett, Peter L.

Obtenir text complet

Scaling Laws in Linear Regression: Compute, Parameters, and Data per Lin, Licong, Wu, Jingfeng, Kakade, Sham M., Bartlett, Peter L., Lee, Jason D.

Obtenir text complet

Implicit Bias of Gradient Descent for Non-Homogeneous Deep Networks per Cai, Yuhang, Zhou, Kangjie, Wu, Jingfeng, Mei, Song, Lindsey, Michael, Bartlett, Peter L.

Obtenir text complet

A Simplified Analysis of SGD for Linear Regression with Weight Averaging per Meterez, Alexandru, Morwani, Depen, Oncescu, Costin-Andrei, Wu, Jingfeng, Pehlevan, Cengiz, Kakade, Sham

Obtenir text complet

Risk Comparisons in Linear Regression: Implicit Regularization Dominates Explicit Regularization per Wu, Jingfeng, Bartlett, Peter L., Lee, Jason D., Kakade, Sham M., Yu, Bin

Obtenir text complet