Cong Fang

Orcid: 0000-0002-5076-7897

Affiliations:
  • Shenzhen Research Institute of Big Data, China
  • Peking University, Department of Machine Intelligence, Beijing, China


According to our database1, Cong Fang authored at least 52 papers between 2015 and 2025.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

Online presence:

On csauthors.net:

Bibliography

2025
Hessian-Aware Zeroth-Order Optimization.
IEEE Trans. Pattern Anal. Mach. Intell., June, 2025

Learning Curves of Stochastic Gradient Descent in Kernel Regression.
CoRR, May, 2025

Scaling Law for Stochastic Gradient Descent in Quadratically Parameterized Linear Regression.
CoRR, February, 2025

Optimal Algorithms in Linear Regression under Covariate Shift: On the Importance of Precondition.
CoRR, February, 2025

Fundamental Computational Limits in Pursuing Invariant Causal Prediction and Invariance-Guided Regularization.
CoRR, January, 2025

SEPARATE: A Simple Low-rank Projection for Gradient Compression in Modern Large-scale Model Training Process.
Proceedings of the Thirteenth International Conference on Learning Representations, 2025

2024
Designing Universally-Approximating Deep Neural Networks: A First-Order Optimization Approach.
IEEE Trans. Pattern Anal. Mach. Intell., September, 2024

The Optimality of (Accelerated) SGD for High-Dimensional Quadratic Optimization.
CoRR, 2024

On the Algorithmic Bias of Aligning Large Language Models with RLHF: Preference Collapse and Matching Regularization.
CoRR, 2024

Causality Pursuit from Heterogeneous Environments via Neural Adversarial Invariance Learning.
CoRR, 2024

INSIGHT: End-to-End Neuro-Symbolic Visual Reinforcement Learning with Language Explanations.
CoRR, 2024

The Implicit Bias of Heterogeneity towards Invariance and Causality.
CoRR, 2024

The Implicit Bias of Heterogeneity towards Invariance: A Study of Multi-Environment Matrix Sensing.
Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024

Separation and Bias of Deep Equilibrium Models on Expressivity and Learning Dynamics.
Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024

Optimizing over Multiple Distributions under Generalized Quasar-Convexity Condition.
Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024

Quantum Algorithms and Lower Bounds for Finite-Sum Optimization.
Proceedings of the Forty-first International Conference on Machine Learning, 2024

End-to-End Neuro-Symbolic Reinforcement Learning with Textual Explanations.
Proceedings of the Forty-first International Conference on Machine Learning, 2024

Relational Learning in Pre-Trained Models: A Theory from Hypergraph Recovery Perspective.
Proceedings of the Forty-first International Conference on Machine Learning, 2024

2023
Accelerated Gradient Algorithms with Adaptive Subspace Search for Instance-Faster Optimization.
CoRR, 2023

CORE: Common Random Reconstruction for Distributed Optimization with Provable Low Communication Complexity.
CoRR, 2023

Task-Robust Pre-Training for Worst-Case Downstream Adaptation.
CoRR, 2023

Policy Representation via Diffusion Probability Model for Reinforcement Learning.
CoRR, 2023

Environment Invariant Linear Least Squares.
CoRR, 2023

Provable Particle-based Primal-Dual Algorithm for Mixed Nash Equilibrium.
CoRR, 2023

Task-Robust Pre-Training for Worst-Case Downstream Adaptation.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Double Randomized Underdamped Langevin with Dimension-Independent Convergence Guarantee.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Zeroth-order Optimization with Weak Dimension Dependency.
Proceedings of the Thirty Sixth Annual Conference on Learning Theory, 2023

On the Lower Bound of Minimizing Polyak-Łojasiewicz functions.
Proceedings of the Thirty Sixth Annual Conference on Learning Theory, 2023

2022
Convex Formulation of Overparameterized Deep Neural Networks.
IEEE Trans. Inf. Theory, 2022

Training Neural Networks by Lifted Proximal Operator Machines.
IEEE Trans. Pattern Anal. Mach. Intell., 2022

Alternating Direction Method of Multipliers for Machine Learning
Springer, ISBN: 978-981-16-9839-2, 2022

2021
Mathematical Models of Overparameterized Neural Networks.
Proc. IEEE, 2021

Layer-Peeled Model: Toward Understanding Well-Trained Deep Neural Networks.
CoRR, 2021

Modeling from Features: a Mean-field Framework for Over-parameterized Deep Neural Networks.
Proceedings of the Conference on Learning Theory, 2021

2020
Decentralized Accelerated Gradient Methods With Increasing Penalty Parameters.
IEEE Trans. Signal Process., 2020

Accelerated First-Order Optimization Algorithms for Machine Learning.
Proc. IEEE, 2020

Improved Analysis of Clipping Algorithms for Non-convex Optimization.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

How to Characterize The Landscape of Overparameterized Convolutional Neural Networks.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Accelerated Optimization for Machine Learning - First-Order Algorithms
Springer, ISBN: 978-981-15-2909-2, 2020

2019
Over Parameterized Two-level Neural Networks Can Learn Near Optimal Feature Representations.
CoRR, 2019

Learning Compact Partial Differential Equations for Color Images with Efficiency.
Proceedings of the IEEE International Conference on Acoustics, 2019

Sharp Analysis for Nonconvex SGD Escaping from Saddle Points.
Proceedings of the Conference on Learning Theory, 2019

Complexities in Projection-Free Stochastic Non-convex Minimization.
Proceedings of the 22nd International Conference on Artificial Intelligence and Statistics, 2019

Lifted Proximal Operator Machines.
Proceedings of the Thirty-Third AAAI Conference on Artificial Intelligence, 2019

2018
Dictionary learning with structured noise.
Neurocomputing, 2018

Hessian-Aware Zeroth-Order Optimization for Black-Box Adversarial Attack.
CoRR, 2018

Accelerating Asynchronous Algorithms for Convex Optimization by Momentum Compensation.
CoRR, 2018

SPIDER: Near-Optimal Non-Convex Optimization via Stochastic Path-Integrated Differential Estimator.
Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018

2017
Feature learning via partial differential equation with applications to face recognition.
Pattern Recognit., 2017

Faster and Non-ergodic O(1/K) Stochastic Alternating Direction Method of Multipliers.
Proceedings of the Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, 2017

Parallel Asynchronous Stochastic Variance Reduction for Nonconvex Optimization.
Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence, 2017

2015
A robust hybrid method for text detection in natural scenes by learning-based partial differential equations.
Neurocomputing, 2015


  Loading...