2025
Scalable Bilevel Loss Balancing for Multi-Task Learning.
CoRR, February, 2025
ReGNet: Reciprocal Space-Aware Long-Range Modeling and Multi-Property Prediction for Crystals.
CoRR, February, 2025
First-Order Federated Bilevel Learning.
Proceedings of the AAAI-25, Sponsored by the Association for the Advancement of Artificial Intelligence, February 25, 2025
2024
Boosting One-Point Derivative-Free Online Optimization via Residual Feedback.
IEEE Trans. Autom. Control., September, 2024
Enhancing Diffusion Posterior Sampling for Inverse Problems by Integrating Crafted Measurements.
CoRR, 2024
Meta-Learning with Heterogeneous Tasks.
CoRR, 2024
Tuning-Free Bilevel Optimization: New Algorithms and Convergence Analysis.
CoRR, 2024
Why Fine-Tuning Struggles with Forgetting in Machine Unlearning? Theoretical Insights and a Remedial Approach.
CoRR, 2024
Imperative Learning: A Self-supervised Neural-Symbolic Learning Framework for Robot Autonomy.
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
CoRR, 2024
On the Convergence of Multi-objective Optimization under Generalized Smoothness.
CoRR, 2024
Finite-Time Analysis for Conflict-Avoidant Multi-Task Reinforcement Learning.
CoRR, 2024
Discriminative Adversarial Unlearning.
CoRR, 2024
First-Order Minimax Bilevel Optimization.
Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024
Understanding Forgetting in Continual Learning with Linear Regression.
Proceedings of the Forty-first International Conference on Machine Learning, 2024
Fair Resource Allocation in Multi-Task Learning.
Proceedings of the Forty-first International Conference on Machine Learning, 2024
AUC-CL: A Batchsize-Robust Framework for Self-Supervised Contrastive Representation Learning.
Proceedings of the Twelfth International Conference on Learning Representations, 2024
2023
Lower Bounds and Accelerated Algorithms for Bilevel Optimization.
J. Mach. Learn. Res., 2023
Achieving O(ε<sup>-1.5</sup>) Complexity in Hessian/Jacobian-free Stochastic Bilevel Optimization.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023
SimFBO: Towards Simple, Flexible and Communication-efficient Federated Bilevel Learning.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023
Direction-oriented Multi-objective Learning: Simple and Provable Stochastic Algorithms.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023
Non-Convex Bilevel Optimization with Time-Varying Objective Functions.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023
Bilevel Coreset Selection in Continual Learning: A New Formulation and Algorithm.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023
Network Utility Maximization with Unknown Utility Functions: A Distributed, Data-Driven Bilevel Optimization Approach.
Proceedings of the Twenty-fourth International Symposium on Theory, 2023
Communication-Efficient Federated Hypergradient Computation via Aggregated Iterative Differentiation.
Proceedings of the International Conference on Machine Learning, 2023
Achieving Linear Speedup in Non-IID Federated Bilevel Learning.
Proceedings of the International Conference on Machine Learning, 2023
2022
Theoretical Convergence of Multi-Step Model-Agnostic Meta-Learning.
J. Mach. Learn. Res., 2022
A Constrained Optimization Approach to Bilevel Optimization with Multiple Inner Minima.
CoRR, 2022
Efficiently Escaping Saddle Points in Bilevel Optimization.
CoRR, 2022
A new one-point residual-feedback oracle for black-box learning and control.
Autom., 2022
Data sampling affects the complexity of online SGD over dependent data.
Proceedings of the Uncertainty in Artificial Intelligence, 2022
On the Convergence Theory for Hessian-Free Bilevel Algorithms.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022
Will Bilevel Optimizers Benefit from Loops.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022
2021
Understanding Estimation and Generalization Error of Generative Adversarial Networks.
IEEE Trans. Inf. Theory, 2021
ES-Based Jacobian Enables Faster Bilevel Optimization.
CoRR, 2021
Bilevel Optimization for Machine Learning: Algorithm Design and Convergence Analysis.
CoRR, 2021
Provably Faster Algorithms for Bilevel Optimization.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021
Bilevel Optimization: Convergence Analysis and Enhanced Design.
Proceedings of the 38th International Conference on Machine Learning, 2021
2020
Learning Latent Features With Pairwise Penalties in Low-Rank Matrix Completion.
IEEE Trans. Signal Process., 2020
Provably Faster Algorithms for Bilevel Optimization and Applications to Meta-Learning.
CoRR, 2020
Boosting One-Point Derivative-Free Online Optimization via Residual Feedback.
CoRR, 2020
Improving the Convergence Rate of One-Point Zeroth-Order Optimization using Residual Feedback.
CoRR, 2020
Multi-Step Model-Agnostic Meta-Learning: Convergence and Improved Algorithms.
CoRR, 2020
Convergence of Meta-Learning with Task-Specific Adaptation over Partial Parameters.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020
Proximal Gradient Algorithm with Momentum and Flexible Parameter Restart for Nonconvex Optimization.
Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence, 2020
History-Gradient Aided Batch Size Adaptation for Variance Reduced Algorithms.
Proceedings of the 37th International Conference on Machine Learning, 2020
Robust Stochastic Bandit Algorithms under Probabilistic Unbounded Adversarial Attack.
Proceedings of the Thirty-Fourth AAAI Conference on Artificial Intelligence, 2020
2019
Faster Stochastic Algorithms via History-Gradient Aided Batch Size Adaptation.
CoRR, 2019
SpiderBoost and Momentum: Faster Variance Reduction Algorithms.
Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019
Improved Zeroth-Order Variance Reduced Algorithms and Analysis for Nonconvex Optimization.
Proceedings of the 36th International Conference on Machine Learning, 2019
2018
On Resource Pooling and Separation for LRU Caching.
Proc. ACM Meas. Anal. Comput. Syst., 2018
SpiderBoost: A Class of Faster Variance-reduced Algorithms for Nonconvex Optimization.
CoRR, 2018
Convergence of SGD in Learning ReLU Models with Separable Data.
CoRR, 2018
Learning Latent Features with Pairwise Penalties in Matrix Completion.
CoRR, 2018
Minimax Estimation of Neural Net Distance.
Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018
LRU Caching with Dependent Competing Requests.
Proceedings of the 2018 IEEE Conference on Computer Communications, 2018
Asymptotic Miss Ratio of LRU Caching with Consistent Hashing.
Proceedings of the 2018 IEEE Conference on Computer Communications, 2018