← Authors

Qi Lei

45 papers · 2016–2025 · 9 conferences · across top CS/AI conferences

Achievements

πŸƒ Academic Marathon (9) 🐣 Hot Topic Early Bird 🌈 Renaissance Researcher (9) πŸŒ‰ Interdisciplinary Bridge πŸ—ΊοΈ Taxonomy Completionist (15) 🧭 Keyword Pioneer 🐝 Cross-Pollinator (8) 🌍 Conference Polyglot (9) 🀝 Dynamic Duo (10) πŸ‘‘ Triple Crown πŸ”¬ Deep Specialist (12) πŸ’Ž Century Club (45) ⚑ Prolific Year (9) πŸ—ƒοΈ Keyword Collector (193) πŸ“ˆ Trend Setter πŸ”₯ Unstoppable (10)

Conferences

NIPS (14) ICML (11) AISTATS (10) EMNLP (3) ICLR (2) IJCAI (2) CVPR (1) ICCV (1) UAI (1)

Top co-authors

Jason Lee (10) Jason D. Lee (5) Baihe Huang (5) Yijun Dong (4) Inderjit S Dhillon (4) Hoang Phan (4) JIACHENG ZHUO (3) Quan Zhang (3) Alex Dimakis (3) Yining Wang (3)

Keywords

stochastic optimization (3) zeroth-order optimization (3) representation learning (3) sample efficiency (3) adversarial robustness (3) sample complexity (3) sparse optimization (2) model pruning (2) generalization bound (2) adversarial training (2) gradient descent (2) distributed learning (2) coordinate descent (2) semi-supervised learning (2) neural network optimization (2) domain adaptation (2) convex optimization (2) non-convex optimization (2) matrix factorization (2) empirical risk minimization (2)

Papers

Elastic Representation: Mitigating Spurious Correlations for Group Robustness AISTATS 2025
Beyond Invisibility: Learning Robust Visible Watermarks for Stronger Copyright Protection UAI 2025
Discrepancies are Virtue: Weak-to-Strong Generalization through Lens of Intrinsic Dimension ICML 2025
Beyond Interpretability: The Gains of Feature Monosemanticity on Model Robustness ICLR 2025
Beyond Losses Reweighting: Empowering Multi-Task Learning via the Generalization Perspective ICCV 2025
Think Twice, Generate Once: Safeguarding by Progressive Self-Reflection EMNLP 2025
Mono3DVLT: Monocular-Video-Based 3D Visual Language Tracking CVPR 2025
Data Reconstruction Attacks and Defenses: A Systematic Evaluation AISTATS 2025
Bridging Domains with Approximately Shared Features AISTATS 2025
An Information-Theoretic Analysis of In-Context Learning ICML 2024
Sketchy Moment Matching: Toward Fast and Provable Data Selection for Finetuning NIPS 2024
Stochastic Zeroth-Order Optimization under Strongly Convexity and Lipschitz Hessian: Minimax Sample Complexity NIPS 2024
Controllable Prompt Tuning For Balancing Group Distributional Robustness ICML 2024
Sample Efficiency of Data Augmentation Consistency Regularization AISTATS 2023
Reconstructing Training Data from Model Gradient, Provably AISTATS 2023
Towards Robust Pruning: An Adaptive Knowledge-Retention Pruning Strategy for Language Models EMNLP 2023
Breaking through Deterministic Barriers: Randomized Pruning Mask Generation and Selection EMNLP 2023
Optimization for Amortized Inverse Problems ICML 2023
Cluster-aware Semi-supervised Learning: Relational Knowledge Distillation Provably Learns Clustering NIPS 2023
Optimal Sample Complexity Bounds for Non-convex Optimization under Kurdyka-Lojasiewicz Condition AISTATS 2023
Provable Hierarchy-Based Meta-Reinforcement Learning AISTATS 2023
Sample Complexity for Quadratic Bandits: Hessian Dependent Bounds and Optimal Algorithms NIPS 2023
CAT: Customized Adversarial Training for Improved Robustness IJCAI 2022
Few-Shot Learning via Learning the Representation, Provably ICLR 2021
Last iterate convergence in no-regret learning: constrained min-max optimization for convex-concave landscapes AISTATS 2021
Optimal Gradient-based Algorithms for Non-concave Bandit Optimization NIPS 2021
Going Beyond Linear RL: Sample Efficient Neural Function Approximation NIPS 2021
How Fine-Tuning Allows for Effective Meta-Learning NIPS 2021
Predicting What You Already Know Helps: Provable Self-Supervised Learning NIPS 2021
A Theory of Label Propagation for Subpopulation Shift ICML 2021
Near-Optimal Linear Regression under Distribution Shift ICML 2021
Solving Inverse Problems with a Flow-based Noise Model ICML 2021
Fast Convergence of Langevin Dynamics on Manifold: Geodesics meet Log-Sobolev NIPS 2020
SGD Learns One-Layer Networks in WGANs ICML 2020
Communication-Efficient Asynchronous Stochastic Frank-Wolfe over Nuclear-norm Balls AISTATS 2020
Inverting Deep Generative models, One layer at a time NIPS 2019
Primal-Dual Block Generalized Frank-Wolfe NIPS 2019
Similarity Preserving Representation Learning for Time Series Clustering IJCAI 2019
Stabilizing Gradients for Deep Neural Networks via Efficient SVD Parameterization ICML 2018
Random Warping Series: A Random Features Method for Time-Series Embedding AISTATS 2018
Hessian-based Analysis of Large Batch Training and Robustness to Adversaries NIPS 2018
Doubly Greedy Primal-Dual Coordinate Descent for Sparse Empirical Risk Minimization ICML 2017
A Greedy Approach for Budgeted Maximum Inner Product Search NIPS 2017
Gradient Coding: Avoiding Stragglers in Distributed Learning ICML 2017
Coordinate-wise Power Method NIPS 2016