default search action
Google
Google Scholar
Semantic Scholar
Internet Archive Scholar
CiteSeerX
ORCIDKaiyi Ji
Person information
Refine list
refinements active!
zoomed in on ?? of ?? records
view refined list in
export refined list as
2020 – today
- 2025
[c29]Yifan Yang, Peiyao Xiao, Shiqian Ma, Kaiyi Ji:
First-Order Federated Bilevel Learning. AAAI 2025: 22029-22037- [i42]Jianan Nie, Peiyao Xiao, Kaiyi Ji, Peng Gao:
ReGNet: Reciprocal Space-Aware Long-Range Modeling and Multi-Property Prediction for Crystals. CoRR abs/2502.02748 (2025) - [i41]Peiyao Xiao, Chaosheng Dong, Shaofeng Zou, Kaiyi Ji:
Scalable Bilevel Loss Balancing for Multi-Task Learning. CoRR abs/2502.08585 (2025) - 2024
- [j7]Yan Zhang
, Yi Zhou, Kaiyi Ji, Yi Shen, Michael M. Zavlanos:
Boosting One-Point Derivative-Free Online Optimization via Residual Feedback. IEEE Trans. Autom. Control. 69(9): 6309-6316 (2024) - [c28]Rohan Sharma, Kaiyi Ji, Zhiqiang Xu, Changyou Chen:
AUC-CL: A Batchsize-Robust Framework for Self-Supervised Contrastive Representation Learning. ICLR 2024 - [c27]Hao Ban, Kaiyi Ji:
Fair Resource Allocation in Multi-Task Learning. ICML 2024 - [c26]Meng Ding, Kaiyi Ji, Di Wang, Jinhui Xu:
Understanding Forgetting in Continual Learning with Linear Regression. ICML 2024 - [c25]Yifan Yang, Zhaofeng Si, Siwei Lyu, Kaiyi Ji:
First-Order Minimax Bilevel Optimization. NeurIPS 2024 - [i40]Rohan Sharma, Shijie Zhou, Kaiyi Ji, Changyou Chen:
Discriminative Adversarial Unlearning. CoRR abs/2402.06864 (2024) - [i39]Hao Ban, Kaiyi Ji:
Fair Resource Allocation in Multi-Task Learning. CoRR abs/2402.15638 (2024) - [i38]Yudan Wang, Peiyao Xiao, Hao Ban, Kaiyi Ji, Shaofeng Zou:
Finite-Time Analysis for Conflict-Avoidant Multi-Task Reinforcement Learning. CoRR abs/2405.16077 (2024) - [i37]Meng Ding, Kaiyi Ji, Di Wang, Jinhui Xu:
Understanding Forgetting in Continual Learning with Linear Regression. CoRR abs/2405.17583 (2024) - [i36]Qi Zhang, Peiyao Xiao, Kaiyi Ji, Shaofeng Zou:
On the Convergence of Multi-objective Optimization under Generalized Smoothness. CoRR abs/2405.19440 (2024) - [i35]Chen Wang, Kaiyi Ji, Junyi Geng, Zhongqiang Ren, Taimeng Fu, Fan Yang, Yifan Guo, Haonan He, Xiangyu Chen, Zitong Zhan, Qiwei Du, Shaoshu Su, Bowen Li, Yuheng Qiu, Yi Du, Qihang Li, Yifan Yang, Xiao Lin, Zhipeng Zhao:
Imperative Learning: A Self-supervised Neural-Symbolic Learning Framework for Robot Autonomy. CoRR abs/2406.16087 (2024) - [i34]Meng Ding, Jinhui Xu, Kaiyi Ji:
Why Fine-Tuning Struggles with Forgetting in Machine Unlearning? Theoretical Insights and a Remedial Approach. CoRR abs/2410.03833 (2024) - [i33]Yifan Yang, Hao Ban, Minhui Huang, Shiqian Ma, Kaiyi Ji:
Tuning-Free Bilevel Optimization: New Algorithms and Convergence Analysis. CoRR abs/2410.05140 (2024) - [i32]Zhaofeng Si, Shu Hu, Kaiyi Ji, Siwei Lyu:
Meta-Learning with Heterogeneous Tasks. CoRR abs/2410.18894 (2024) - [i31]Shijie Zhou, Huaisheng Zhu, Rohan Sharma, Ruiyi Zhang, Kaiyi Ji, Changyou Chen:
Enhancing Diffusion Posterior Sampling for Inverse Problems by Integrating Crafted Measurements. CoRR abs/2411.09850 (2024) - 2023
- [j6]Kaiyi Ji, Yingbin Liang:
Lower Bounds and Accelerated Algorithms for Bilevel Optimization. J. Mach. Learn. Res. 24: 22:1-22:56 (2023) - [c24]Minhui Huang, Dewei Zhang, Kaiyi Ji:
Achieving Linear Speedup in Non-IID Federated Bilevel Learning. ICML 2023: 14039-14059 - [c23]Peiyao Xiao, Kaiyi Ji:
Communication-Efficient Federated Hypergradient Computation via Aggregated Iterative Differentiation. ICML 2023: 38059-38086 - [c22]Kaiyi Ji, Lei Ying:
Network Utility Maximization with Unknown Utility Functions: A Distributed, Data-Driven Bilevel Optimization Approach. MobiHoc 2023: 131-140 - [c21]Jie Hao, Kaiyi Ji, Mingrui Liu:
Bilevel Coreset Selection in Continual Learning: A New Formulation and Algorithm. NeurIPS 2023 - [c20]Sen Lin, Daouda Sow, Kaiyi Ji, Yingbin Liang, Ness B. Shroff:
Non-Convex Bilevel Optimization with Time-Varying Objective Functions. NeurIPS 2023 - [c19]Peiyao Xiao, Hao Ban, Kaiyi Ji:
Direction-oriented Multi-objective Learning: Simple and Provable Stochastic Algorithms. NeurIPS 2023 - [c18]Yifan Yang, Peiyao Xiao, Kaiyi Ji:
SimFBO: Towards Simple, Flexible and Communication-efficient Federated Bilevel Learning. NeurIPS 2023 - [c17]Yifan Yang, Peiyao Xiao, Kaiyi Ji:
Achieving O(ε-1.5) Complexity in Hessian/Jacobian-free Stochastic Bilevel Optimization. NeurIPS 2023 - [i30]Kaiyi Ji, Lei Ying:
Network Utility Maximization with Unknown Utility Functions: A Distributed, Data-Driven Bilevel Optimization Approach. CoRR abs/2301.01801 (2023) - [i29]Peiyao Xiao, Kaiyi Ji:
Communication-Efficient Federated Hypergradient Computation via Aggregated Iterative Differentiation. CoRR abs/2302.04969 (2023) - [i28]Minhui Huang, Dewei Zhang, Kaiyi Ji:
Achieving Linear Speedup in Non-IID Federated Bilevel Learning. CoRR abs/2302.05412 (2023) - [i27]Peiyao Xiao, Hao Ban, Kaiyi Ji:
Direction-oriented Multi-objective Learning: Simple and Provable Stochastic Algorithms. CoRR abs/2305.18409 (2023) - [i26]Yifan Yang, Peiyao Xiao, Kaiyi Ji:
SimFBO: Towards Simple, Flexible and Communication-efficient Federated Bilevel Learning. CoRR abs/2305.19442 (2023) - [i25]Sen Lin, Daouda Sow, Kaiyi Ji, Yingbin Liang, Ness B. Shroff:
Non-Convex Bilevel Optimization with Time-Varying Objective Functions. CoRR abs/2308.03811 (2023) - [i24]Yifan Yang, Peiyao Xiao, Kaiyi Ji:
Achieving O(ε-1.5) Complexity in Hessian/Jacobian-free Stochastic Bilevel Optimization. CoRR abs/2312.03807 (2023) - 2022
- [j5]Yan Zhang, Yi Zhou, Kaiyi Ji, Michael M. Zavlanos:
A new one-point residual-feedback oracle for black-box learning and control. Autom. 136: 110006 (2022) - [j4]Kaiyi Ji, Junjie Yang, Yingbin Liang:
Theoretical Convergence of Multi-Step Model-Agnostic Meta-Learning. J. Mach. Learn. Res. 23: 29:1-29:41 (2022) - [c16]Kaiyi Ji, Mingrui Liu, Yingbin Liang, Lei Ying:
Will Bilevel Optimizers Benefit from Loops. NeurIPS 2022 - [c15]Daouda Sow, Kaiyi Ji, Yingbin Liang:
On the Convergence Theory for Hessian-Free Bilevel Algorithms. NeurIPS 2022 - [c14]Shaocong Ma, Ziyi Chen, Yi Zhou, Kaiyi Ji, Yingbin Liang:
Data sampling affects the complexity of online SGD over dependent data. UAI 2022: 1296-1305 - [i23]Minhui Huang, Kaiyi Ji, Shiqian Ma, Lifeng Lai:
Efficiently Escaping Saddle Points in Bilevel Optimization. CoRR abs/2202.03684 (2022) - [i22]Daouda Sow, Kaiyi Ji, Ziwei Guan, Yingbin Liang:
A Constrained Optimization Approach to Bilevel Optimization with Multiple Inner Minima. CoRR abs/2203.01123 (2022) - [i21]Shaocong Ma, Ziyi Chen, Yi Zhou, Kaiyi Ji, Yingbin Liang:
Data Sampling Affects the Complexity of Online SGD over Dependent Data. CoRR abs/2204.00006 (2022) - [i20]Kaiyi Ji, Mingrui Liu, Yingbin Liang, Lei Ying:
Will Bilevel Optimizers Benefit from Loops. CoRR abs/2205.14224 (2022) - 2021
- [j3]Kaiyi Ji, Yi Zhou, Yingbin Liang:
Understanding Estimation and Generalization Error of Generative Adversarial Networks. IEEE Trans. Inf. Theory 67(5): 3114-3129 (2021) - [c13]Kaiyi Ji, Junjie Yang, Yingbin Liang:
Bilevel Optimization: Convergence Analysis and Enhanced Design. ICML 2021: 4882-4892 - [c12]Junjie Yang, Kaiyi Ji, Yingbin Liang:
Provably Faster Algorithms for Bilevel Optimization. NeurIPS 2021: 13670-13682 - [i19]Kaiyi Ji, Yingbin Liang:
Lower Bounds and Accelerated Algorithms for Bilevel Optimization. CoRR abs/2102.03926 (2021) - [i18]Junjie Yang, Kaiyi Ji, Yingbin Liang:
Provably Faster Algorithms for Bilevel Optimization. CoRR abs/2106.04692 (2021) - [i17]Kaiyi Ji:
Bilevel Optimization for Machine Learning: Algorithm Design and Convergence Analysis. CoRR abs/2108.00330 (2021) - [i16]Daouda Sow, Kaiyi Ji, Yingbin Liang:
ES-Based Jacobian Enables Faster Bilevel Optimization. CoRR abs/2110.07004 (2021) - 2020
- [j2]Kaiyi Ji, Jian Tan, Jinfeng Xu, Yuejie Chi:
Learning Latent Features With Pairwise Penalties in Low-Rank Matrix Completion. IEEE Trans. Signal Process. 68: 4210-4225 (2020) - [c11]Ziwei Guan, Kaiyi Ji, Donald J. Bucci Jr., Timothy Y. Hu, Joseph Palombo, Michael Liston, Yingbin Liang:
Robust Stochastic Bandit Algorithms under Probabilistic Unbounded Adversarial Attack. AAAI 2020: 4036-4043 - [c10]Kaiyi Ji, Zhe Wang, Bowen Weng, Yi Zhou, Wei Zhang, Yingbin Liang:
History-Gradient Aided Batch Size Adaptation for Variance Reduced Algorithms. ICML 2020: 4762-4772 - [c9]Kaiyi Ji, Jian Tan, Jinfeng Xu, Yuejie Chi:
Learning Latent Features with Pairwise Penalties in Low-Rank Matrix Completion. SAM 2020: 1-5 - [c8]Yi Zhou, Zhe Wang, Kaiyi Ji, Yingbin Liang, Vahid Tarokh:
Proximal Gradient Algorithm with Momentum and Flexible Parameter Restart for Nonconvex Optimization. IJCAI 2020: 1445-1451 - [c7]Kaiyi Ji, Jason D. Lee, Yingbin Liang, H. Vincent Poor:
Convergence of Meta-Learning with Task-Specific Adaptation over Partial Parameters. NeurIPS 2020 - [i15]Ziwei Guan, Kaiyi Ji, Donald J. Bucci Jr., Timothy Y. Hu, Joseph Palombo, Michael Liston, Yingbin Liang:
Robust Stochastic Bandit Algorithms under Probabilistic Unbounded Adversarial Attack. CoRR abs/2002.07214 (2020) - [i14]Kaiyi Ji, Junjie Yang, Yingbin Liang:
Multi-Step Model-Agnostic Meta-Learning: Convergence and Improved Algorithms. CoRR abs/2002.07836 (2020) - [i13]Yi Zhou, Zhe Wang, Kaiyi Ji, Yingbin Liang, Vahid Tarokh:
Proximal Gradient Algorithm with Momentum and Flexible Parameter Restart for Nonconvex Optimization. CoRR abs/2002.11582 (2020) - [i12]Kaiyi Ji, Jason D. Lee, Yingbin Liang, H. Vincent Poor:
Convergence of Meta-Learning with Task-Specific Adaptation over Partial Parameters. CoRR abs/2006.09486 (2020) - [i11]Yan Zhang, Yi Zhou, Kaiyi Ji, Michael M. Zavlanos:
Improving the Convergence Rate of One-Point Zeroth-Order Optimization using Residual Feedback. CoRR abs/2006.10820 (2020) - [i10]Yan Zhang, Yi Zhou, Kaiyi Ji, Michael M. Zavlanos:
Boosting One-Point Derivative-Free Online Optimization via Residual Feedback. CoRR abs/2010.07378 (2020) - [i9]Kaiyi Ji, Junjie Yang, Yingbin Liang:
Provably Faster Algorithms for Bilevel Optimization and Applications to Meta-Learning. CoRR abs/2010.07962 (2020)
2010 – 2019
- 2019
- [c6]Kaiyi Ji, Zhe Wang, Yi Zhou, Yingbin Liang:
Improved Zeroth-Order Variance Reduced Algorithms and Analysis for Nonconvex Optimization. ICML 2019: 3100-3109 - [c5]Zhe Wang, Kaiyi Ji, Yi Zhou, Yingbin Liang, Vahid Tarokh:
SpiderBoost and Momentum: Faster Variance Reduction Algorithms. NeurIPS 2019: 2403-2413 - [i8]Kaiyi Ji, Zhe Wang, Yi Zhou, Yingbin Liang:
Faster Stochastic Algorithms via History-Gradient Aided Batch Size Adaptation. CoRR abs/1910.09670 (2019) - [i7]Kaiyi Ji, Zhe Wang, Yi Zhou, Yingbin Liang:
Improved Zeroth-Order Variance Reduced Algorithms and Analysis for Nonconvex Optimization. CoRR abs/1910.12166 (2019) - 2018
- [j1]Jian Tan, Guocong Quan, Kaiyi Ji, Ness B. Shroff:
On Resource Pooling and Separation for LRU Caching. Proc. ACM Meas. Anal. Comput. Syst. 2(1): 5:1-5:31 (2018) - [c4]Kaiyi Ji, Guocong Quan, Jian Tan:
Asymptotic Miss Ratio of LRU Caching with Consistent Hashing. INFOCOM 2018: 450-458 - [c3]Guocong Quan, Kaiyi Ji, Jian Tan:
LRU Caching with Dependent Competing Requests. INFOCOM 2018: 459-467 - [c2]Kaiyi Ji, Yingbin Liang:
Minimax Estimation of Neural Net Distance. NeurIPS 2018: 3849-3858 - [c1]Jian Tan, Guocong Quan, Kaiyi Ji, Ness B. Shroff:
On Resource Pooling and Separation for LRU Caching. SIGMETRICS (Abstracts) 2018: 27 - [i6]Kaiyi Ji, Guocong Quan, Jian Tan:
Asymptotic Miss Ratio of LRU Caching with Consistent Hashing. CoRR abs/1801.02436 (2018) - [i5]Kaiyi Ji, Jian Tan, Yuejie Chi, Jinfeng Xu:
Learning Latent Features with Pairwise Penalties in Matrix Completion. CoRR abs/1802.05821 (2018) - [i4]Tengyu Xu, Yi Zhou, Kaiyi Ji, Yingbin Liang:
Convergence of SGD in Learning ReLU Models with Separable Data. CoRR abs/1806.04339 (2018) - [i3]Zhe Wang, Kaiyi Ji, Yi Zhou, Yingbin Liang, Vahid Tarokh:
SpiderBoost: A Class of Faster Variance-reduced Algorithms for Nonconvex Optimization. CoRR abs/1810.10690 (2018) - [i2]Kaiyi Ji, Yingbin Liang:
Minimax Estimation of Neural Net Distance. CoRR abs/1811.01054 (2018) - 2017
- [i1]Jian Tan, Guocong Quan, Kaiyi Ji, Ness B. Shroff:
On Resource Pooling and Separation for LRU Caching. CoRR abs/1708.01673 (2017)
Coauthor Index
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 2025-04-20 23:51 CEST by the dblp team
all metadata released as open data under CC0 1.0 license
see also: Terms of Use | Privacy Policy | Imprint
dblp was originally created in 1993 at:
since 2018, dblp has been operated and maintained by:
the dblp computer science bibliography is funded and supported by:
