Publications (by topics)
Click Here to view in chronological order.Click on one of the topics to jump right to it: [Reinforcement Learning, Differential Privacy,Adaptive Online Learning, Trend Filtering,Scalable Machine Learning, Subspace Clustering / Compressed Sensing, Applications]
Reinforcement Learning and other Decision making problems
- Near-Optimal Deployment Efficiency in Reward-Free Reinforcement Learning with Linear Function Approximation
Manuscript. [arxiv] - Sample-Efficient Reinforcement Learning with loglog(T) Switching Cost
ICML 2022. [arxiv] - Offline Stochastic Shortest Path: Learning, Evaluation and Towards Optimality
UAI 2022. [arxiv] - Near-optimal Offline Reinforcement Learning with Linear Representation: Leveraging Variance Information with Pessimism
ICLR 2022. [openreview] - Towards Instance-Optimal Offline Reinforcement Learning with Pessimism
NeurIPS 2021. [preprint coming soon] - Optimal Uniform OPE and Model-based Offline Reinforcement Learning in Time-Homogeneous, Reward-Free and Task-Agnostic Settings
NeurIPS 2021. [arxiv] - Near-Optimal Offline Reinforcement Learning via Double Variance Reduction
NeurIPS 2021. [arxiv] -
Near Optimal Provable Uniform Convergence in Offlin Policy Evaluation for Reinforcement Learning
AISTATS 2021. (*Plenary oral presentation) [arxiv] -
Domain Adaptation with Conditional Distribution Matching and Generalized Label Shift
NeurIPS 2020. [arxiv] -
Asymptotically Efficient Off-Policy Evaluation for Tabular Reinforcement Learning
AISTATS 2020. [arxiv] - Towards Optimal Off-Policy Evaluation for Reinforcement Learning with Marginalized Importance Sampling
NeurIPS 2019. [arxiv] - Provably Efficient Q-Learning with Low Switching Cost
NeurIPS 2019. [arxiv] - Imitation Regularized Offline Learning
AISTATS 2019. [arxiv] - Detecting and Correcting for Label Shift with Black Box Predictors
ICML'2018, Stockholm, Sweden [arxiv] - Optimal and Adaptive Off-Policy Evaluation in Contextual Bandits
ICML'17. [paper supp]
Differential Privacy
- Differentially Private Bias-Term only Fine-tuning of Foundation Models
Manuscript. [arxiv] - Differentially Private Optimization on Large Model at Small Cost
Manuscript. [arxiv] - Automatic Clipping: Differentially Private Deep Learning Made Easier and Stronger
Manuscript. [arxiv] - Offline Reinforcement Learning with Differential Privacy
Manuscript [arxiv] - Differentially Private Linear Sketches: Efficient Implementations and Applications
NeurIPS 2022. [arxiv] - SeqPATE: Differentially Private Text Generation via Knowledge Distillation
NeurIPS 2022. [available soon] - Mixed Differential Privacy in Computer Vision
CVPR 2022. [arxiv](*Oral Presentation) - Optimal Accounting of Differential Privacy via Characteristic Function
AISTATS 2022. [arxiv] - Adaptive Private-K-Selection with Adaptive K and Application to Multi-label PATE
AISTATS 2022. [arxiv] - Privately Publishable Per-instance Privacy
NeurIPS 2021. [arxiv] - Voting-based Approaches For Differentially Private Federated Learning
Manuscript. [arxiv] -
Revisiting Model-Agnostic Private Learning: Faster Rates and Active Learning
Journal of Machine Learning Research. Shorter version appeared in AISTATS 2021. [arxiv] - Improving Sparse Vector Technique with Renyi Differential Privacy
NeurIPS 2020. [paper,supplement ] -
An end-to-end Differentially Private Latent Dirichlet Allocation Using a Spectral Algorithm
ICML 2020. [pdf, code] -
Private-kNN: Practical Differential Privacy for Computer Vision
CVPR 2020. [paper] - Poisson Subsampled Rényi Differential Privacy
ICML 2019. [paper,code] - Subsampled Rényi Differential Privacy and Analytical Moments Accountant
AISTATS 2019. [arxiv] (*Notable Paper Award, *Plenary oral presentation) - Revisiting differentially private linear regression: optimal and adaptive prediction and estimation in unbounded domain
UAI'18. [arxiv] (*Plenary oral presentation) - Improving Gaussian Mechanism for Differential Privacy: Analytical Calibration and Optimal Denoising
ICML'2018, Stockholm, Sweden. [arxiv] - Per-instance Differential Privacy
Journal of Confidentiality and Privacy. [pdf] - On-Average KL-Privacy and its equivalence to Generalization for Max-Entropy Mechanisms
Privacy in Statistical Databases. PSD'2016, Dubrovnik. [springer, arxiv] - Differentially Private Subspace Clustering
NIPS 2015, Montreal, Canada. [pdf] - Fast Differential Private Matrix Factorization
RecSys'15, Vienna, Austria. [arxiv, code] - Privacy for Free: Posterior Sampling and Stochastic Gradient Monte Carlo
ICML 2015, Lille, France. [arxiv] - Learning with Differential Privacy: Stability, Learnability and the Sufficiency and Necessity of ERM Principle
Journal of Machine Learning Research (JMLR), 2016. [arxiv]
Nonstationary and Adaptive Online Learning
- Optimal Dynamic Regret in LQR Control
NeurIPS 2022. [arxiv] - Second Order Path Variationals in Non-Stationary Online Learning
Manuscript. [arxiv] - Optimal Dynamic Regret in Proper Online Learning with Strongly Convex Losses and Beyond
AISTATS 2022. [arxiv] - Non-stationary Online Learning with Memory and Non-stochastic Control
AISTATS 2022. [arxiv] - Optimal Dynamic Regret in Exp-Concave Online Learning
COLT 2021. [arxiv] (*Best Student Paper Award) - An Optimal Reduction of TV-Denoising to Adaptive Online Learning
AISTATS 2021. [arxiv] - Adaptive Online Estimation of Piecewise Polynomial Trends
NeurIPS 2020. [arxiv] - Online Forecasting of Total Variation-Bounded Sequences
NeurIPS 2019. [arxiv]
A short version appeared at ICML'19 Time Series Workshop. (*Best Paper Honorable Mention) - Non-stationary Stochastic Optimization under Lp,q-Variation Measures
Operations Research. [informs_online, arxiv]
Trend filtering and Local adaptivity
- Deep Learning meets Nonparametric Regression: Are Weight-Decayed DNNs Locally Adaptive?
Manuscript. [arxiv] - Multivariate Trend Filtering for Lattice Data
Manuscript. [arxiv] - A Higher-Order Kolmogorov-Smirnov Test
AISTATS 2019. [arxiv] (*Plenary oral presentation) - Higher-Order Total Variation Classes on Grids:
Minimax Theory and Trend Filtering Methods
NIPS'2017. [paper,supp] - Attributing Hacks with Survival Trend Filtering
Electronic Journal of Statistics[ paper]
"Attributing Hacks" in AISTATS'17 (*Plenary oral presentation) - Total Variation Classes Beyond 1d: Minimax Rates, and the
Limitations of Linear Smoothers
NIPS 2016, Barcelona. [arxiv] - Trend Filtering on Graphs
Journal of Machine Learning Research (JMLR), 2016. [jmlr]
AISTATS 2015, San Diego. [conf] - The Falling Factorial Basis and Its Statistical Applications
ICML 2014, Beijing. [paper, Supplementary, code]
Subspace clustering, matrix factorization
- Graph Connectivity in Noisy Sparse Subspace Clustering
AISTATS 2016, Cadiz, Spain. [arxiv] - A Theoretical Analysis of Noisy Sparse Subspace Clustering for Dimensionality-reduced Data
IEEE Transaction on Information Theory[ieee,arxiv]
ICML 2015, Lille, France. [conf] - Provable Subspace Clustering: When LRR meets SSC
IEEE Transaction on Information Theory, to appear.[fullpaper,arxiv]
NIPS 2013. Selected for spotlight presentation. [conf, demo code] - Noisy Sparse Subspace Clustering
Journal of Machine Learning Research (2016). [pdf]
ICML 2013, Atlanta [paper, Supplementary, code, Video] - Practical Matrix Completion and Corruption Recovery using Proximal Alternating Robust Subspace Minimization
International Journal of Computer Vision (IJCV), 2014. [Springerlink,DemoCode] - Block-Sparse RPCA for Salient Motion Detection
Pattern Analysis and Machine Intelligence (PAMI), 2014. [IEEEXplore] - Stability of Matrix Factorization for Collaborative Filtering
ICML 2012, Edinburgh. [paper, Supplementary, Slides , Video]
Scalability and Large-scale optimization (for Deep Learning)
- Enhancing the Locality and Breaking the Memory Bottleneck of Transformer on Time Series Forecasting
NeurIPS 2019. [arxiv] - ProxQuant: Quantized Neural Networks via Proximal Operators.
ICLR 2019 [arxiv] - signSGD: compressed optimisation for non-convex problems
ICML 2018, Stockholm, Sweden. [arxiv] - Parallel and Distributed Block-Coordinate Frank-Wolfe Algorithms
ICML 2016, New York City. [pdf][supplement] - DiFacto --- Distributed Factorization Machines (*Best Paper Honorable Mention)
WSDM 2016, San Francisco. [pdf] - Graph Sparsification Approaches for Large-Scale Laplacian Smoothing
AISTATS 2016, Cadiz, Spain. [pdf, supplementary]
Other applications
- Non-stationary Contextual Pricing with Safety Constraints
Transaction of Machine Learning Research (to appear) [openreview] - Doubly Fair Dynamic Pricing
AISTATS 2023 [arxiv] - Towards Agnostic Feature-based Dynamic Pricing: Linear Policies vs Linear Valuation with Unknown Noise
AISTATS 2022. [arxiv] (*Plenary Oral Presentation) - Logarithmic Regret in Feature-Based Dynamic Pricing
NeurIPS 2021. [arxiv] (*Spotlight Presentation) -
Bullseye Polytope: A Scalable Clean-Label Poisoning Attack with Improved Transferability.
IEEE EuroS&P 2021. [arxiv] - Inter-Series Attention Model for COVID-19 Forecasting
SDM 2021. [arxiv] - Distillation-Resistant Watermarking for Model Protection in NLP
Findings of EMNLP 2022. [arxiv] (*Oral Presentation) - Provably Confidential Language Modelling
NAACL 2022. [arxiv] - Doubly Robust Crowdsourcing
Journal of Artificial Intelligence Research [pdf] - A Minimax Theory for Adaptive Data Analysis
In preparation. [arxiv] - Understanding the 2016 US Presidential Election using ecological inference and distribution regression with census microdata
In preparation. [arxiv] - Who supported Obama in 2012? Ecological inference through distribution regression (*Best Student Paper)
KDD 2015, Sydney, Australia. [pdf] - An efficient algorithm for UAV indoor pose
estimation using vanishing geometry
MVA 2011, Nara, Japan [paper, Poster]