Huy Nguyen

Understanding Expert Structures on Minimax Parameter Estimation in Contaminated Mixture of Experts AISTATS 2025 Statistical Advantages of Perturbing Cosine Router in Mixture of Experts ICLR 2025 Revisiting Prefix-tuning: Statistical Benefits of Reparameterization among Prompts ICLR 2025 AG-VPReID: A Challenging Large-Scale Benchmark for Aerial-Ground Video-based Person Re-Identification CVPR 2025 Maximum Coverage in Turnstile Streams with Applications to Fingerprinting Measures ICML 2025 Online and Streaming Algorithms for Constrained k-Submodular Maximization AAAI 2025 On Zero-Initialized Attention: Optimal Prompt and Gating Factor Estimation ICML 2025 RepLoRA: Reparameterizing Low-rank Adaptation via the Perspective of Mixture of Experts ICML 2025 Lean and Mean Adaptive Optimization via Subset-Norm and Subspace-Momentum with Convergence Guarantees ICML 2025 Private Vector Mean Estimation in the Shuffle Model: Optimal Rates Require Many Messages ICML 2024 Is Temperature Sample Efficient for Softmax Gaussian Mixture of Experts? ICML 2024 On Parameter Estimation in Deviated Gaussian Mixture of Experts AISTATS 2024 Towards Convergence Rates for Parameter Estimation in Gaussian-gated Mixture of Experts AISTATS 2024 FuseMoE: Mixture-of-Experts Transformers for Fleximodal Fusion NIPS 2024 Sigmoid Gating is More Sample Efficient than Softmax Gating in Mixture of Experts NIPS 2024 Statistical Perspective of Top-K Sparse Softmax Gating Mixture of Experts ICLR 2024 Mixture of Experts Meets Prompt-Based Continual Learning NIPS 2024 On Least Square Estimation in Softmax Gating Mixture of Experts ICML 2024 A General Theory for Softmax Gating Multinomial Logistic Mixture of Experts ICML 2024 PP4AV: A Benchmarking Dataset for Privacy-Preserving Autonomous Driving WACV 2023 Demystifying Softmax Gating Function in Gaussian Mixture of Experts NIPS 2023 Improved Frequency Estimation Algorithms with and without Predictions NIPS 2023 Fast Optimal Locally Private Mean Estimation via Random Projections NIPS 2023 Improved Convergence in High Probability of Clipped Gradient Methods with Heavy Tailed Noise NIPS 2023 Minimax Optimal Rate for Parameter Estimation in Multivariate Deviated Models NIPS 2023 On the Generalization Error of Stochastic Mirror Descent for Quadratically-Bounded Losses: an Improved Analysis NIPS 2023 An Efficient Algorithm for Fair Multi-Agent Multi-Armed Bandit with Low Regret AAAI 2023 A Spectral Viewpoint on Continual Relation Extraction EMNLP 2023 Transitioning Representations between Languages for Cross-lingual Event Detection via Langevin Dynamics EMNLP 2023 On the Convergence of AdaGrad(Norm) on $\mathbb{R}^d$: Beyond Convexity, Non-Asymptotic Rate and Acceleration ICLR 2023 Improved Learning-augmented Algorithms for k-means and k-medians Clustering ICLR 2023 Hierarchical Sliced Wasserstein Distance ICLR 2023 Streaming Submodular Maximization with Differential Privacy ICML 2023 High Probability Convergence of Stochastic Gradient Methods ICML 2023 Adaptive Accelerated (Extra-)Gradient Methods with Variance Reduction ICML 2022 Robust Product Classification with Instance-Dependent Noise ACL 2022 On Multimarginal Partial Optimal Transport: Equivalent Forms and Computational Complexity AISTATS 2022 Automatic Mean Opinion Score Estimation with Temporal Modulation Features on Gammatone Filterbank for Speech Assessment INTERSPEECH 2022 Streaming Algorithm for Monotone k-Submodular Maximization with Cardinality Constraints ICML 2022 Private frequency estimation via projective geometry ICML 2022 Entropic Gromov-Wasserstein between Gaussian Distributions ICML 2022 On Robust Optimal Transport: Computational Complexity and Barycenter Computation NIPS 2021 Fair k-Centers via Maximum Matching ICML 2020 Parallel Algorithm for Non-Monotone DR-Submodular Maximization ICML 2020 Automated Essay Scoring with Discourse-Aware Neural Models ACL 2019 Improved Algorithms for Collaborative PAC Learning NIPS 2018 Liulishuo's System for the Spoken CALL Shared Task 2018 INTERSPEECH 2018 Decomposable Submodular Function Minimization: Discrete and Continuous NIPS 2017 Context-aware Argumentative Relation Mining ACL 2016 Instant Feedback for Increasing the Presence of Solutions in Peer Reviews NAACL 2016 Random Coordinate Descent Methods for Minimizing Decomposable Submodular Functions ICML 2015 The Power of Randomization: Distributed Submodular Maximization on Massive Datasets ICML 2015 Subspace Embeddings for the Polynomial Kernel NIPS 2014 On Communication Cost of Distributed Statistical Estimation and Dimensionality NIPS 2014 Named Entity Recognition with Character-Level Models CONLL 2003 Automatic Semantic Grouping in a Spoken Language User Interface Toolkit COLING 2002