Rong Ge

Orcid: 0000-0003-2807-7168

Affiliations:
  • Duke University, Durham, NC, USA
  • Princeton University, NJ, USA (former)


According to our database1, Rong Ge authored at least 110 papers between 2008 and 2024.

Collaborative distances:

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

Online presence:

On csauthors.net:

Bibliography

2024
Reassessing How to Compare and Improve the Calibration of Machine Learning Models.
CoRR, 2024

How Does Gradient Descent Learn Features - A Local Analysis for Regularized Two-Layer Neural Networks.
CoRR, 2024

For Better or For Worse? Learning Minimum Variance Features With Label Augmentation.
CoRR, 2024

On the Limitations of Temperature Scaling for Distributions with Overlaps.
Proceedings of the Twelfth International Conference on Learning Representations, 2024

2023
A Uniform Confidence Phenomenon in Deep Learning and its Implications for Calibration.
CoRR, 2023

Robust Second-Order Nonconvex Optimization and Its Application to Low Rank Matrix Sensing.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Smoothing the Landscape Boosts the Signal for SGD: Optimal Sample Complexity for Learning Single Index Models.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Connecting Pre-trained Language Model and Downstream Task via Properties of Representation.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Implicit Regularization Leads to Benign Overfitting for Sparse Linear Regression.
Proceedings of the International Conference on Machine Learning, 2023

Hiding Data Helps: On the Benefits of Masking for Sparse Coding.
Proceedings of the International Conference on Machine Learning, 2023

Provably Learning Diverse Features in Multi-View Data with Midpoint Mixup.
Proceedings of the International Conference on Machine Learning, 2023

Depth Separation with Multilayer Mean-Field Networks.
Proceedings of the Eleventh International Conference on Learning Representations, 2023

Understanding The Robustness of Self-supervised Learning Through Topic Modeling.
Proceedings of the Eleventh International Conference on Learning Representations, 2023

Plateau in Monotonic Linear Interpolation - A "Biased" View of Loss Landscape for Deep Networks.
Proceedings of the Eleventh International Conference on Learning Representations, 2023

Understanding Edge-of-Stability Training Dynamics with a Minimalist Example.
Proceedings of the Eleventh International Conference on Learning Representations, 2023

The Role of Linguistic Priors in Measuring Compositional Generalization of Vision-Language Models.
Proceedings of the Proceedings on "I Can't Believe It's Not Better: Failure Modes in the Age of Foundation Models" at NeurIPS 2023 Workshops, 2023

Do Transformers Parse while Predicting the Masked Word?
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, 2023

2022
On the optimization landscape of tensor decompositions.
Math. Program., 2022

Optimization landscape of Tucker decomposition.
Math. Program., 2022

One Objective for All Models - Self-supervised Learning for Topic Models.
CoRR, 2022

Outlier-Robust Sparse Estimation via Non-Convex Optimization.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Extracting Latent State Representations with Linear Dynamics from Rich Observations.
Proceedings of the International Conference on Machine Learning, 2022

Online Algorithms with Multiple Predictions.
Proceedings of the International Conference on Machine Learning, 2022

Towards Understanding the Data Dependency of Mixup-style Training.
Proceedings of the Tenth International Conference on Learning Representations, 2022

2021
Online Service with Delay.
ACM Trans. Algorithms, 2021

On Nonconvex Optimization for Machine Learning: Gradients, Stochasticity, and Saddle Points.
J. ACM, 2021

Understanding Deflation Process in Over-parametrized Tensor Decomposition.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

A Regression Approach to Learning-Augmented Online Algorithms.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Guarantees for Tuning the Step Size using a Learning-to-Learn Approach.
Proceedings of the 38th International Conference on Machine Learning, 2021

A Local Convergence Theory for Mildly Over-Parameterized Two-Layer Neural Network.
Proceedings of the Conference on Learning Theory, 2021

Efficient sampling from the Bingham distribution.
Proceedings of the Algorithmic Learning Theory, 2021

2020
Dissecting Hessian: Understanding Common Structure of Hessian in Neural Networks.
CoRR, 2020

Extracting Latent State Representations with Linear Dynamics from Rich Observations.
CoRR, 2020

Estimating normalizing constants for log-concave distributions: algorithms and lower bounds.
Proceedings of the 52nd Annual ACM SIGACT Symposium on Theory of Computing, 2020

Beyond Lazy Training for Over-parameterized Tensor Decomposition.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Customizing ML Predictions for Online Algorithms.
Proceedings of the 37th International Conference on Machine Learning, 2020

High-dimensional Robust Mean Estimation via Gradient Descent.
Proceedings of the 37th International Conference on Machine Learning, 2020

Topic Models and Nonnegative Matrix Factorization.
Proceedings of the Beyond the Worst-Case Analysis of Algorithms, 2020

2019
Spectral Learning on Matrices and Tensors.
Found. Trends Mach. Learn., 2019

Mildly Overparametrized Neural Nets can Memorize Training Data Efficiently.
CoRR, 2019

The Step Decay Schedule: A Near Optimal, Geometrically Decaying Learning Rate Procedure.
CoRR, 2019

Stochastic Gradient Descent Escapes Saddle Points Efficiently.
CoRR, 2019

A Short Note on Concentration Inequalities for Random Vectors with SubGaussian Norm.
CoRR, 2019

High-Dimensional Robust Mean Estimation in Nearly-Linear Time.
Proceedings of the Thirtieth Annual ACM-SIAM Symposium on Discrete Algorithms, 2019

Explaining Landscape Connectivity of Low-cost Solutions for Multilayer Nets.
Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

The Step Decay Schedule: A Near Optimal, Geometrically Decaying Learning Rate Procedure For Least Squares.
Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Learning Two-layer Neural Networks with Symmetric Inputs.
Proceedings of the 7th International Conference on Learning Representations, 2019

Understanding Composition of Word Embeddings via Tensor Decomposition.
Proceedings of the 7th International Conference on Learning Representations, 2019

Stabilized SVRG: Simple Variance Reduction for Nonconvex Optimization.
Proceedings of the Conference on Learning Theory, 2019

Faster Algorithms for High-Dimensional Robust Covariance Estimation.
Proceedings of the Conference on Learning Theory, 2019

Open Problem: Do Good Algorithms Necessarily Query Bad Points?
Proceedings of the Conference on Learning Theory, 2019

2018
Simulated Tempering Langevin Monte Carlo II: An Improved Proof using Soft Markov Chain Decomposition.
CoRR, 2018

Minimizing Nonconvex Population Risk from Rough Empirical Risk.
CoRR, 2018

Global Convergence of Policy Gradient Methods for Linearized Control Problems.
CoRR, 2018

Learning topic models - provably and efficiently.
Commun. ACM, 2018

Beyond Log-concavity: Provable Guarantees for Sampling Multi-modal Distributions using Simulated Tempering Langevin Monte Carlo.
Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018

On the Local Minima of the Empirical Risk.
Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018

Global Convergence of Policy Gradient Methods for the Linear Quadratic Regulator.
Proceedings of the 35th International Conference on Machine Learning, 2018

Stronger Generalization Bounds for Deep Nets via a Compression Approach.
Proceedings of the 35th International Conference on Machine Learning, 2018

Learning One-hidden-layer Neural Networks with Landscape Design.
Proceedings of the 6th International Conference on Learning Representations, 2018

Non-Convex Matrix Completion Against a Semi-Random Adversary.
Proceedings of the Conference On Learning Theory, 2018

2017
Analyzing Tensor Power Method Dynamics in Overcomplete Regime.
J. Mach. Learn. Res., 2017

Provable learning of noisy-OR networks.
Proceedings of the 49th Annual ACM SIGACT Symposium on Theory of Computing, 2017

How to Escape Saddle Points Efficiently.
Proceedings of the 34th International Conference on Machine Learning, 2017

Generalization and Equilibrium in Generative Adversarial Nets (GANs).
Proceedings of the 34th International Conference on Machine Learning, 2017

No Spurious Local Minima in Nonconvex Low Rank Problems: A Unified Geometric Analysis.
Proceedings of the 34th International Conference on Machine Learning, 2017

On the Ability of Neural Nets to Express Distributions.
Proceedings of the 30th Conference on Learning Theory, 2017

Homotopy Analysis for Tensor PCA.
Proceedings of the 30th Conference on Learning Theory, 2017

2016
Minimal Realization Problems for Hidden Markov Models.
IEEE Trans. Signal Process., 2016

Computing a Nonnegative Matrix Factorization - Provably.
SIAM J. Comput., 2016

Homotopy Method for Tensor Principal Component Analysis.
CoRR, 2016

Matrix Completion has No Spurious Local Minimum.
Proceedings of the Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems 2016, 2016

Rich Component Analysis.
Proceedings of the 33nd International Conference on Machine Learning, 2016

Efficient Algorithms for Large-scale Generalized Eigenvector Computation and Canonical Correlation Analysis.
Proceedings of the 33nd International Conference on Machine Learning, 2016

Provable Algorithms for Inference in Topic Models.
Proceedings of the 33nd International Conference on Machine Learning, 2016

Efficient approaches for escaping higher order saddle points in non-convex optimization.
Proceedings of the 29th Conference on Learning Theory, 2016

2015
Provable ICA with Unknown Gaussian Noise, and Implications for Gaussian Mixtures and Autoencoders.
Algorithmica, 2015

Learning Mixtures of Gaussians in High Dimensions.
Proceedings of the Forty-Seventh Annual ACM on Symposium on Theory of Computing, 2015

Intersecting Faces: Non-negative Matrix Factorization With New Guarantees.
Proceedings of the 32nd International Conference on Machine Learning, 2015

Un-regularizing: approximate proximal point and faster stochastic algorithms for empirical risk minimization.
Proceedings of the 32nd International Conference on Machine Learning, 2015

Escaping From Saddle Points - Online Stochastic Gradient for Tensor Decomposition.
Proceedings of The 28th Conference on Learning Theory, 2015

Competing with the Empirical Risk Minimizer in a Single Pass.
Proceedings of The 28th Conference on Learning Theory, 2015

Simple, Efficient, and Neural Algorithms for Sparse Coding.
Proceedings of The 28th Conference on Learning Theory, 2015

Learning Overcomplete Latent Variable Models through Tensor Methods.
Proceedings of The 28th Conference on Learning Theory, 2015

Decomposing Overcomplete 3rd Order Tensors using Sum-of-Squares Algorithms.
Proceedings of the Approximation, 2015

Tensor Decompositions for Learning Latent Variable Models (A Survey for ALT).
Proceedings of the Algorithmic Learning Theory - 26th International Conference, 2015

2014
Tensor decompositions for learning latent variable models.
J. Mach. Learn. Res., 2014

A tensor approach to learning mixed membership community models.
J. Mach. Learn. Res., 2014

More Algorithms for Provable Dictionary Learning.
CoRR, 2014

Analyzing Tensor Power Method Dynamics: Applications to Learning Overcomplete Latent Variable Models.
CoRR, 2014

Provable Learning of Overcomplete Latent Variable Models: Semi-supervised and Unsupervised Settings.
CoRR, 2014

Guaranteed Non-Orthogonal Tensor Decomposition via Alternating Rank-1 Updates.
CoRR, 2014

Provable Bounds for Learning Some Deep Representations.
Proceedings of the 31th International Conference on Machine Learning, 2014

New Algorithms for Learning Incoherent and Overcomplete Dictionaries.
Proceedings of The 27th Conference on Learning Theory, 2014

Minimal realization problem for Hidden Markov Models.
Proceedings of the 52nd Annual Allerton Conference on Communication, 2014

2013
Provable Algorithms for Machine Learning Problems
PhD thesis, 2013

A Practical Algorithm for Topic Modeling with Provable Guarantees.
Proceedings of the 30th International Conference on Machine Learning, 2013

Towards a Better Approximation for Sparsest Cut?
Proceedings of the 54th Annual IEEE Symposium on Foundations of Computer Science, 2013

A Tensor Spectral Approach to Learning Mixed Membership Community Models.
Proceedings of the COLT 2013, 2013

2012
Finding overlapping communities in social networks: toward a rigorous approach.
Proceedings of the 13th ACM Conference on Electronic Commerce, 2012

"Provable ICA with Unknown Gaussian Noise, with Implications for Gaussian Mixtures and Autoencoders".
Proceedings of the Advances in Neural Information Processing Systems 25: 26th Annual Conference on Neural Information Processing Systems 2012. Proceedings of a meeting held December 3-6, 2012

Learning Topic Models - Going beyond SVD.
Proceedings of the 53rd Annual IEEE Symposium on Foundations of Computer Science, 2012

2011
Computational complexity and information asymmetry in financial products.
Commun. ACM, 2011

Another Sub-exponential Algorithm for the Simple Stochastic Game.
Algorithmica, 2011

New Algorithms for Learning in Presence of Errors.
Proceedings of the Automata, Languages and Programming - 38th International Colloquium, 2011

New Tools for Graph Coloring.
Proceedings of the Approximation, Randomization, and Combinatorial Optimization. Algorithms and Techniques, 2011

2010
Learning Parities with Structured Noise.
Electron. Colloquium Comput. Complex., 2010

Computational Complexity and Information Asymmetry in Financial Products (Extended Abstract).
Proceedings of the Innovations in Computer Science, 2010

2009
New Results on Simple Stochastic Games.
Proceedings of the Algorithms and Computation, 20th International Symposium, 2009

2008
THU QUANTA at TAC 2008 QA and RTE Track.
Proceedings of the First Text Analysis Conference, 2008


  Loading...