Rong Ge

Task Descriptors Help Transformers Learn Linear Models In-Context ICLR 2025 Reassessing How to Compare and Improve the Calibration of Machine Learning Models ICLR 2025 For Better or For Worse? Learning Minimum Variance Features With Label Augmentation ICLR 2025 Linear Transformers are Versatile In-Context Learners NIPS 2024 ReCaLL: Membership Inference via Relative Conditional Log-Likelihoods EMNLP 2024 On the Limitations of Temperature Scaling for Distributions with Overlaps ICLR 2024 Mean-Field Analysis for Learning Subspace-Sparse Polynomials with Gaussian Input NIPS 2024 How does Gradient Descent Learn Features --- A Local Analysis for Regularized Two-Layer Neural Networks NIPS 2024 Connecting Pre-trained Language Model and Downstream Task via Properties of Representation NIPS 2023 Robust Second-Order Nonconvex Optimization and Its Application to Low Rank Matrix Sensing NIPS 2023 Plateau in Monotonic Linear Interpolation --- A "Biased" View of Loss Landscape for Deep Networks ICLR 2023 Provably Learning Diverse Features in Multi-View Data with Midpoint Mixup ICML 2023 Depth Separation with Multilayer Mean-Field Networks ICLR 2023 Hiding Data Helps: On the Benefits of Masking for Sparse Coding ICML 2023 Understanding The Robustness of Self-supervised Learning Through Topic Modeling ICLR 2023 Do Transformers Parse while Predicting the Masked Word? EMNLP 2023 Implicit Regularization Leads to Benign Overfitting for Sparse Linear Regression ICML 2023 Understanding Edge-of-Stability Training Dynamics with a Minimalist Example ICLR 2023 Smoothing the Landscape Boosts the Signal for SGD: Optimal Sample Complexity for Learning Single Index Models NIPS 2023 Towards Understanding the Data Dependency of Mixup-style Training ICLR 2022 Outlier-Robust Sparse Estimation via Non-Convex Optimization NIPS 2022 Extracting Latent State Representations with Linear Dynamics from Rich Observations ICML 2022 Online Algorithms with Multiple Predictions ICML 2022 A Local Convergence Theory for Mildly Over-Parameterized Two-Layer Neural Network COLT 2021 Understanding Deflation Process in Over-parametrized Tensor Decomposition NIPS 2021 A Regression Approach to Learning-Augmented Online Algorithms NIPS 2021 Guarantees for Tuning the Step Size using a Learning-to-Learn Approach ICML 2021 Efficient sampling from the Bingham distribution ALT 2021 Beyond Lazy Training for Over-parameterized Tensor Decomposition NIPS 2020 Customizing ML Predictions for Online Algorithms ICML 2020 High-dimensional Robust Mean Estimation via Gradient Descent ICML 2020 The Step Decay Schedule: A Near Optimal, Geometrically Decaying Learning Rate Procedure For Least Squares NIPS 2019 Faster Algorithms for High-Dimensional Robust Covariance Estimation COLT 2019 Stabilized SVRG: Simple Variance Reduction for Nonconvex Optimization COLT 2019 Open Problem: Do Good Algorithms Necessarily Query Bad Points? COLT 2019 Explaining Landscape Connectivity of Low-cost Solutions for Multilayer Nets NIPS 2019 Learning Two-layer Neural Networks with Symmetric Inputs ICLR 2019 Understanding Composition of Word Embeddings via Tensor Decomposition ICLR 2019 Learning One-hidden-layer Neural Networks with Landscape Design ICLR 2018 Beyond Log-concavity: Provable Guarantees for Sampling Multi-modal Distributions using Simulated Tempering Langevin Monte Carlo NIPS 2018 On the Local Minima of the Empirical Risk NIPS 2018 Non-Convex Matrix Completion Against a Semi-Random Adversary COLT 2018 Stronger Generalization Bounds for Deep Nets via a Compression Approach ICML 2018 Global Convergence of Policy Gradient Methods for the Linear Quadratic Regulator ICML 2018 Homotopy Analysis for Tensor PCA COLT 2017 Generalization and Equilibrium in Generative Adversarial Nets (GANs) ICML 2017 No Spurious Local Minima in Nonconvex Low Rank Problems: A Unified Geometric Analysis ICML 2017 How to Escape Saddle Points Efficiently ICML 2017 Analyzing Tensor Power Method Dynamics in Overcomplete Regime JMLR 2017 On the Optimization Landscape of Tensor Decompositions NIPS 2017 On the Ability of Neural Nets to Express Distributions COLT 2017 Efficient Algorithms for Large-scale Generalized Eigenvector Computation and Canonical Correlation Analysis ICML 2016 Provable Algorithms for Inference in Topic Models ICML 2016 Matrix Completion has No Spurious Local Minimum NIPS 2016 Efficient approaches for escaping higher order saddle points in non-convex optimization COLT 2016 Rich Component Analysis ICML 2016 Escaping From Saddle Points — Online Stochastic Gradient for Tensor Decomposition COLT 2015 Un-regularizing: approximate proximal point and faster stochastic algorithms for empirical risk minimization ICML 2015 Intersecting Faces: Non-negative Matrix Factorization With New Guarantees ICML 2015 Competing with the Empirical Risk Minimizer in a Single Pass COLT 2015 Simple, Efficient, and Neural Algorithms for Sparse Coding COLT 2015 Learning Overcomplete Latent Variable Models through Tensor Methods COLT 2015 New Algorithms for Learning Incoherent and Overcomplete Dictionaries COLT 2014 A Tensor Approach to Learning Mixed Membership Community Models JMLR 2014 Tensor Decompositions for Learning Latent Variable Models JMLR 2014 Provable Bounds for Learning Some Deep Representations ICML 2014 A Tensor Spectral Approach to Learning Mixed Membership Community Models COLT 2013 A Practical Algorithm for Topic Modeling with Provable Guarantees ICML 2013 Provable ICA with Unknown Gaussian Noise, with Implications for Gaussian Mixtures and Autoencoders NIPS 2012