Yuejie Chi

Orcid: 0000-0002-6766-5459

Affiliations:
  • Carnegie Mellon University, Pittsburgh, PA, USA


According to our database1, Yuejie Chi authored at least 175 papers between 2010 and 2024.

Collaborative distances:

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

Online presence:

On csauthors.net:

Bibliography

2024
High-Probability Sample Complexities for Policy Evaluation With Linear Function Approximation.
IEEE Trans. Inf. Theory, August, 2024

Distributionally Robust Model-Based Offline Reinforcement Learning with Near-Optimal Sample Complexity.
J. Mach. Learn. Res., 2024

Fast Policy Extragradient Methods for Competitive Games with Entropy Regularization.
J. Mach. Learn. Res., 2024

Breaking the Sample Size Barrier in Model-Based Reinforcement Learning with a Generative Model.
Oper. Res., 2024

Is Q-Learning Minimax Optimal? A Tight Sample Complexity Analysis.
Oper. Res., 2024

Can We Break the Curse of Multiagency in Robust Multi-Agent Reinforcement Learning?
CoRR, 2024

The Sample-Communication Complexity Trade-off in Federated Q-Learning.
CoRR, 2024

In-Context Learning with Representations: Contextual Generalization of Trained Transformers.
CoRR, 2024

A Sharp Convergence Theory for The Probability Flow ODEs of Diffusion Models.
CoRR, 2024

Learning Discrete Concepts in Latent Hierarchical Models.
CoRR, 2024

Value-Incentivized Preference Optimization: A Unified Approach to Online and Offline RLHF.
CoRR, 2024

Prompt-prompted Mixture of Experts for Efficient LLM Generation.
CoRR, 2024

Provably Robust Score-Based Diffusion Posterior Sampling for Plug-and-Play Image Reconstruction.
CoRR, 2024

Transformers Provably Learn Feature-Position Correlations in Masked Image Modeling.
CoRR, 2024

Beyond Expectations: Learning with Stochastic Dominance Made Practical.
CoRR, 2024

Sample Complexity of Offline Distributionally Robust Linear Markov Decision Processes.
Proceedings of the 1st Reinforcement Learning Conference, 2024

Federated Offline Reinforcement Learning: Collaborative Single-Policy Coverage Suffices.
Proceedings of the Forty-first International Conference on Machine Learning, 2024

Sample-Efficient Robust Multi-Agent Reinforcement Learning in the Face of Environmental Uncertainty.
Proceedings of the Forty-first International Conference on Machine Learning, 2024

Get More with LESS: Synthesizing Recurrence with KV Cache Compression for Efficient LLM Inference.
Proceedings of the Forty-first International Conference on Machine Learning, 2024

Accelerating Convergence of Score-Based Diffusion Models, Provably.
Proceedings of the Forty-first International Conference on Machine Learning, 2024

Towards Non-Asymptotic Convergence for Diffusion-Based Generative Models.
Proceedings of the Twelfth International Conference on Learning Representations, 2024

Communication-Efficient Federated Optimization over Semi-Decentralized Networks.
Proceedings of the IEEE International Conference on Acoustics, 2024

Communication-efficient Vertical Federated Learning via Compressed Error Feedback.
Proceedings of the 32nd European Signal Processing Conference, 2024

Escaping Saddle Points in Heterogeneous Federated Learning via Distributed SGD with Communication Compression.
Proceedings of the International Conference on Artificial Intelligence and Statistics, 2024

2023
Policy Mirror Descent for Regularized Reinforcement Learning: A Generalized Framework with Linear Convergence.
SIAM J. Optim., June, 2023

Softmax policy gradient methods can take exponential time to converge.
Math. Program., 2023

Local Geometry of Nonconvex Spike Deconvolution From Low-Pass Measurements.
IEEE J. Sel. Areas Inf. Theory, 2023

Federated Natural Policy Gradient Methods for Multi-task Reinforcement Learning.
CoRR, 2023

Provably Accelerating Ill-Conditioned Low-rank Estimation via Scaled Gradient Descent, Even with Overparameterization.
CoRR, 2023

Global Convergence of Policy Gradient Methods in Reinforcement Learning, Games and Control.
CoRR, 2023

A Multi-Token Coordinate Descent Method for Semi-Decentralized Vertical Federated Learning.
CoRR, 2023

A Lightweight Transformer for Faster and Robust EBSD Data Collection.
CoRR, 2023

Towards Faster Non-Asymptotic Convergence for Diffusion-Based Generative Models.
CoRR, 2023

Sharp high-probability sample complexities for policy evaluation with linear function approximation.
CoRR, 2023

Convergence and Privacy of Decentralized Nonconvex Optimization with Gradient Clipping and Communication Compression.
CoRR, 2023

Fast Computation of Optimal Transport via Entropy-Regularized Extragradient Methods.
CoRR, 2023

A trajectory is worth three sentences: multimodal transformer for offline reinforcement learning.
Proceedings of the Uncertainty in Artificial Intelligence, 2023

Offline Reinforcement Learning with On-Policy Q-Function Regularization.
Proceedings of the Machine Learning and Knowledge Discovery in Databases: Research Track, 2023

Counterfactual Generation with Identifiability Guarantees.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

The Curious Price of Distributional Robustness in Reinforcement Learning with a Generative Model.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Identification of Nonlinear Latent Hierarchical Models.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Seeing is not Believing: Robust Reinforcement Learning against Spurious Correlation.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Reward-agnostic Fine-tuning: Provable Statistical Benefits of Hybrid Reinforcement Learning.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

The Blessing of Heterogeneity in Federated Q-Learning: Linear Speedup and Beyond.
Proceedings of the International Conference on Machine Learning, 2023

The Power of Preconditioning in Overparameterized Low-Rank Matrix Sensing.
Proceedings of the International Conference on Machine Learning, 2023

Faster Last-iterate Convergence of Policy Optimization in Zero-Sum Markov Games.
Proceedings of the Eleventh International Conference on Learning Representations, 2023

Asynchronous Gradient Play in Zero-Sum Multi-agent Games.
Proceedings of the Eleventh International Conference on Learning Representations, 2023

Deep Unfolded Tensor Robust PCA With Self-Supervised Learning.
Proceedings of the IEEE International Conference on Acoustics, 2023

Understanding Masked Autoencoders via Hierarchical Latent Variable Models.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

2022
Sample Complexity of Asynchronous Q-Learning: Sharper Analysis and Variance Reduction.
IEEE Trans. Inf. Theory, 2022

DESTRESS: Computation-Optimal and Communication-Efficient Decentralized Nonconvex Finite-Sum Optimization.
SIAM J. Math. Data Sci., 2022

Scaling and Scalability: Provable Nonconvex Low-Rank Tensor Estimation from Incomplete Measurements.
J. Mach. Learn. Res., 2022

Fast Global Convergence of Natural Policy Gradient Methods with Entropy Regularization.
Oper. Res., 2022

Minimax-Optimal Multi-Agent RL in Zero-Sum Markov Games With a Generative Model.
CoRR, 2022

Fast and Provable Tensor Robust Principal Component Analysis via Scaled Gradient Descent.
CoRR, 2022

Settling the Sample Complexity of Model-Based Offline Reinforcement Learning.
CoRR, 2022

BEER: Fast $O(1/T)$ Rate for Decentralized Nonconvex Optimization with Communication Compression.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

SoteriaFL: A Unified Framework for Private Federated Learning with Communication Compression.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Minimax-Optimal Multi-Agent RL in Markov Games With a Generative Model.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Pessimistic Q-Learning for Offline Reinforcement Learning: Towards Optimal Sample Complexity.
Proceedings of the International Conference on Machine Learning, 2022

Active Heterogeneous Graph Neural Networks with Per-step Meta-Q-Learning.
Proceedings of the IEEE International Conference on Data Mining, 2022

Accelerating ILL-Conditioned Robust Low-Rank Tensor Regression.
Proceedings of the IEEE International Conference on Acoustics, 2022

Privacy-Preserving Federated Multi-Task Linear Regression: A One-Shot Linear Mixing Approach Inspired By Graph Regularization.
Proceedings of the IEEE International Conference on Acoustics, 2022

Independent Natural Policy Gradient Methods for Potential Games: Finite-time Global Convergence with Entropy Regularization.
Proceedings of the 61st IEEE Conference on Decision and Control, 2022

Scaling and Scalability: Provable Nonconvex Low-Rank Tensor Completion.
Proceedings of the International Conference on Artificial Intelligence and Statistics, 2022

Harvesting Curvatures for Communication-Efficient Distributed Optimization.
Proceedings of the 56th Asilomar Conference on Signals, Systems, and Computers, ACSSC 2022, Pacific Grove, CA, USA, October 31, 2022

Batch Active Learning with Graph Neural Networks via Multi-Agent Deep Reinforcement Learning.
Proceedings of the Thirty-Sixth AAAI Conference on Artificial Intelligence, 2022

2021
Low-Rank Matrix Recovery With Scaled Subgradient Methods: Fast and Robust Convergence Without the Condition Number.
IEEE Trans. Signal Process., 2021

Beyond Procrustes: Balancing-Free Gradient Descent for Asymmetric Low-Rank Matrix Sensing.
IEEE Trans. Signal Process., 2021

Manifold Gradient Descent Solves Multi-Channel Sparse Blind Deconvolution Provably and Efficiently.
IEEE Trans. Inf. Theory, 2021

Nonconvex Matrix Factorization From Rank-One Measurements.
IEEE Trans. Inf. Theory, 2021

Compressed Super-Resolution of Positive Sources.
IEEE Signal Process. Lett., 2021

Accelerating Ill-Conditioned Low-Rank Matrix Estimation via Scaled Gradient Descent.
J. Mach. Learn. Res., 2021

Spectral Methods for Data Science: A Statistical Perspective.
Found. Trends Mach. Learn., 2021

Breaking the Sample Complexity Barrier to Regret-Optimal Model-Free Reinforcement Learning.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Sample-Efficient Reinforcement Learning Is Feasible for Linearly Realizable MDPs with Limited Revisiting.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Tightening the Dependence on Horizon in the Sample Complexity of Q-Learning.
Proceedings of the 38th International Conference on Machine Learning, 2021

Plug-And-Play Image Reconstruction Meets Stochastic Variance-Reduced Gradient Methods.
Proceedings of the 2021 IEEE International Conference on Image Processing, 2021

Softmax Policy Gradient Methods Can Take Exponential Time to Converge.
Proceedings of the Conference on Learning Theory, 2021

2020
Learning Latent Features With Pairwise Penalties in Low-Rank Matrix Completion.
IEEE Trans. Signal Process., 2020

Guaranteed Recovery of One-Hidden-Layer Neural Networks via Cross Entropy.
IEEE Trans. Signal Process., 2020

Convergence of Distributed Stochastic Variance Reduced Methods Without Sampling Extra Data.
IEEE Trans. Signal Process., 2020

Vector-Valued Graph Trend Filtering With Non-Convex Penalties.
IEEE Trans. Signal Inf. Process. over Networks, 2020

On the Stable Resolution Limit of Total Variation Regularization for Spike Deconvolution.
IEEE Trans. Inf. Theory, 2020

Harnessing Sparsity Over the Continuum: Atomic norm minimization for superresolution.
IEEE Signal Process. Mag., 2020

Noisy Matrix Completion: Understanding Statistical Guarantees for Convex Relaxation via Nonconvex Optimization.
SIAM J. Optim., 2020

Communication-Efficient Distributed Optimization in Networks with Gradient Tracking and Variance Reduction.
J. Mach. Learn. Res., 2020

Implicit Regularization in Nonconvex Statistical Estimation: Gradient Descent Converges Linearly for Phase Retrieval, Matrix Completion, and Blind Deconvolution.
Found. Comput. Math., 2020

Analytical convergence regions of accelerated gradient descent in nonconvex optimization under Regularity Condition.
Autom., 2020

Data Quality-Informed Multiple Occupant Localization using Floor Vibration Sensing.
Proceedings of the HotMobile '20: The 21st International Workshop on Mobile Computing Systems and Applications, 2020

Breaking the Sample Size Barrier in Model-Based Reinforcement Learning with a Generative Model.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Support Stability of Spike Deconvolution via Total Variation Minimization.
Proceedings of the 54th Annual Conference on Information Sciences and Systems, 2020

2019
Nonconvex Optimization Meets Low-Rank Matrix Factorization: An Overview.
IEEE Trans. Signal Process., 2019

Low-Rank Structured Covariance Matrix Estimation.
IEEE Signal Process. Lett., 2019

Gradient descent with random initialization: fast global convergence for nonconvex phase retrieval.
Math. Program., 2019

Subspace Estimation from Unbalanced and Incomplete Data Matrices: 𝓁<sub>2, ∞</sub> Statistical Guarantees.
CoRR, 2019

Communication-Efficient Distributed Optimization in Networks with Gradient Tracking.
CoRR, 2019

Harnessing Sparsity over the Continuum: Atomic Norm Minimization for Super Resolution.
CoRR, 2019

Device-free Multiple People Localization through Floor Vibration.
Proceedings of the 1st ACM International Workshop on Device-Free Human Sensing, 2019

Local Geometry of Cross Entropy Loss in Learning One-Hidden-Layer Neural Networks.
Proceedings of the IEEE International Symposium on Information Theory, 2019

Improving Graph Trend Filtering with Non-convex Penalties.
Proceedings of the IEEE International Conference on Acoustics, 2019

Solving Quadratic Equations via Amplitude-based Nonconvex Optimization.
Proceedings of the IEEE International Conference on Acoustics, 2019

On the Sensitivity of Spectral Initialization for Noisy Phase Retrieval.
Proceedings of the IEEE International Conference on Acoustics, 2019

Shift-invariant Subspace Tracking with Missing Data.
Proceedings of the IEEE International Conference on Acoustics, 2019

Self-Calibrated Super Resolution.
Proceedings of the 53rd Asilomar Conference on Signals, Systems, and Computers, 2019

2018
Stochastic Approximation and Memory-Limited Subspace Tracking for Poisson Streaming Data.
IEEE Trans. Signal Process., 2018

Quantized Spectral Compressed Sensing: Cramer-Rao Bounds and Recovery Algorithms.
IEEE Trans. Signal Process., 2018

Median-Truncated Nonconvex Approach for Phase Retrieval With Outliers.
IEEE Trans. Inf. Theory, 2018

Low-Rank Matrix Completion [Lecture Notes].
IEEE Signal Process. Mag., 2018

Harnessing Structures in Big Data via Guaranteed Low-Rank Matrix Estimation: Recent Theory and Fast Algorithms via Convex and Nonconvex Optimization.
IEEE Signal Process. Mag., 2018

Rethinking PCA for Modern Data Sets: Theory, Algorithms, and Applications.
Proc. IEEE, 2018

Streaming PCA and Subspace Tracking: The Missing Data Case.
Proc. IEEE, 2018

Harnessing Structures in Big Data via Guaranteed Low-Rank Matrix Estimation.
CoRR, 2018

Local Geometry of One-Hidden-Layer Neural Networks for Logistic Regression.
CoRR, 2018

Learning Latent Features with Pairwise Penalties in Matrix Completion.
CoRR, 2018

A Non-Convex Approach To Joint Sensor Calibration And Spectrum Estimation.
Proceedings of the 2018 IEEE Statistical Signal Processing Workshop, 2018

Implicit Regularization in Nonconvex Statistical Estimation: Gradient Descent Converges Linearly for Phase Retrieval and Matrix Completion.
Proceedings of the 35th International Conference on Machine Learning, 2018

Terahertz Imaging of Binary Reflectance with Variational Bayesian Inference.
Proceedings of the 2018 IEEE International Conference on Acoustics, 2018

2017
Low-Rank Positive Semidefinite Matrix Recovery From Corrupted Rank-One Measurements.
IEEE Trans. Signal Process., 2017

Subspace Learning From Bits.
IEEE Trans. Signal Process., 2017

Super-Resolution Image Reconstruction for High-Density Three-Dimensional Single-Molecule Microscopy.
IEEE Trans. Computational Imaging, 2017

A Nonconvex Approach for Phase Retrieval: Reshaped Wirtinger Flow and Incremental Algorithms.
J. Mach. Learn. Res., 2017

Nonconvex Low-Rank Matrix Recovery with Arbitrary Outliers via Median-Truncated Gradient Descent.
CoRR, 2017

Memory-Limited stochastic approximation for poisson subspace tracking.
Proceedings of the 2017 IEEE 7th International Workshop on Computational Advances in Multi-Sensor Adaptive Processing, 2017

Compressive spectrum estimation using quantized measurements.
Proceedings of the 51st Asilomar Conference on Signals, Systems, and Computers, 2017

2016
Off-the-Grid Line Spectrum Denoising and Estimation With Multiple Measurement Vectors.
IEEE Trans. Signal Process., 2016

Blind Deconvolution From Multiple Sparse Inputs.
IEEE Signal Process. Lett., 2016

Kaczmarz Method for Solving Quadratic Equations.
IEEE Signal Process. Lett., 2016

Guaranteed Blind Sparse Spikes Deconvolution via Lifting and Convex Optimization.
IEEE J. Sel. Top. Signal Process., 2016

Low-Rank Positive Semidefinite Matrix Recovery from Quadratic Measurements with Outliers.
CoRR, 2016

Super-resolution image reconstruction for high-density 3D single-molecule microscopy.
Proceedings of the 13th IEEE International Symposium on Biomedical Imaging, 2016

Provable Non-convex Phase Retrieval with Outliers: Median TruncatedWirtinger Flow.
Proceedings of the 33nd International Conference on Machine Learning, 2016

Outlier-robust recovery of low-rank positive semidefinite matrices from magnitude measurements.
Proceedings of the 2016 IEEE International Conference on Acoustics, 2016

Robust blind spikes deconvolution.
Proceedings of the 2016 IEEE International Conference on Acoustics, 2016

Kronecker covariance sketching for spatial-temporal data.
Proceedings of the 24th European Signal Processing Conference, 2016

Principal subspace estimation for low-rank Toeplitz covariance matrices with binary sensing.
Proceedings of the 50th Asilomar Conference on Signals, Systems and Computers, 2016

2015
Compressive Two-Dimensional Harmonic Retrieval via Atomic Norm Minimization.
IEEE Trans. Signal Process., 2015

Exact and Stable Covariance Estimation From Quadratic Sampling via Convex Programming.
IEEE Trans. Inf. Theory, 2015

Orthogonal Matching Pursuit on Faulty Circuits.
IEEE Trans. Commun., 2015

Stable Separation and Super-Resolution of Mixture Models.
CoRR, 2015

Super-resolution of mutually interfering signals.
Proceedings of the IEEE International Symposium on Information Theory, 2015

Covariance tracking from sketches of rapid data streams.
Proceedings of the 2015 IEEE International Conference on Acoustics, 2015

Compressive graph clustering from random sketches.
Proceedings of the 2015 IEEE International Conference on Acoustics, 2015

Blind calibration of multi-channel samplers using sparse recovery.
Proceedings of the 6th IEEE International Workshop on Computational Advances in Multi-Sensor Adaptive Processing, 2015

Change-point estimation of high-dimensional streaming data via sketching.
Proceedings of the 49th Asilomar Conference on Signals, Systems and Computers, 2015

Blind super-resolution of sparse spike signals.
Proceedings of the 49th Asilomar Conference on Signals, Systems and Computers, 2015

2014
Robust Spectral Compressed Sensing via Structured Matrix Completion.
IEEE Trans. Inf. Theory, 2014

Classification and Boosting with Multiple Collaborative Representations.
IEEE Trans. Pattern Anal. Mach. Intell., 2014

Subspace Learning From Bits.
CoRR, 2014

Compressive parameter estimation with multiple measurement vectors via structured low-rank covariance estimation.
Proceedings of the IEEE Workshop on Statistical Signal Processing, 2014

Robust and universal covariance estimation from quadratic measurements via convex programming.
Proceedings of the 2014 IEEE International Symposium on Information Theory, Honolulu, HI, USA, June 29, 2014

Joint sparsity recovery for spectral compressed sensing.
Proceedings of the IEEE International Conference on Acoustics, 2014

Estimation of simultaneously structured covariance matrices from quadratic measurements.
Proceedings of the IEEE International Conference on Acoustics, 2014

One-bit principal subspace estimation.
Proceedings of the 2014 IEEE Global Conference on Signal and Information Processing, 2014

2013
PETRELS: Parallel Subspace Estimation and Tracking by Recursive Least Squares From Partial Observations.
IEEE Trans. Signal Process., 2013

Compressive Demodulation of Mutually Interfering Signals
CoRR, 2013

Spectral Compressed Sensing via Structured Matrix Completion.
Proceedings of the 30th International Conference on Machine Learning, 2013

Analysis of fisher information and the Cramer-Rao bound for nonlinear parameter estimation after compressed sensing.
Proceedings of the IEEE International Conference on Acoustics, 2013

Knowledge-enhanced Matching Pursuit.
Proceedings of the IEEE International Conference on Acoustics, 2013

Low-rank matrix recovery with poison noise.
Proceedings of the IEEE Global Conference on Signal and Information Processing, 2013

Sparse MIMO radar via structured matrix completion.
Proceedings of the IEEE Global Conference on Signal and Information Processing, 2013

Compressive recovery of 2-D off-grid frequencies.
Proceedings of the 2013 Asilomar Conference on Signals, 2013

Nearest subspace classification with missing data.
Proceedings of the 2013 Asilomar Conference on Signals, 2013

2012
PETRELS: Parallel Estimation and Tracking of Subspace by Recursive Least Squares from Partial Observations
CoRR, 2012

Compressive demodulation of mutually interfering signals.
Proceedings of the IEEE Statistical Signal Processing Workshop, 2012

PETRELS: Subspace estimation and tracking from partial observations.
Proceedings of the 2012 IEEE International Conference on Acoustics, 2012

Connecting the dots in multi-class classification: From nearest subspace to collaborative representation.
Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition, 2012

Coherence-based performance guarantees of Orthogonal Matching Pursuit.
Proceedings of the 50th Annual Allerton Conference on Communication, 2012

2011
Training Signal Design and Tradeoffs for Spectrally-Efficient Multi-User MIMO-OFDM Systems.
IEEE Trans. Wirel. Commun., 2011

Sensitivity to Basis Mismatch in Compressed Sensing.
IEEE Trans. Signal Process., 2011

On Training Signal Design for Multi-User MIMO-OFDM: Performance Analysis and Tradeoffs.
Proceedings of the 74th IEEE Vehicular Technology Conference, 2011

MMSE-optimal training sequences for spectrally-efficient Multi-User MIMO-OFDM systems.
Proceedings of the 19th European Signal Processing Conference, 2011

Diagnostic grade wireless ECG monitoring.
Proceedings of the 33rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 2011

2010
Regularized blind detection for MIMO communications.
Proceedings of the IEEE International Symposium on Information Theory, 2010

Compressive blind source separation.
Proceedings of the International Conference on Image Processing, 2010


  Loading...