TrungTin Nguyen

7 papers · 2023–2024 · 4 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🗺️ Taxonomy Completionist (18) ⚡ Prolific Year · Productive

Venues

ICML (3) NeurIPS (2) AISTATS (1) EMNLP (1)

Top co-authors

nhật Hồ (4) Huy Nguyen (3) Daniel Sonntag (2) Mathias Niepert (2) Chenghao Liu (1) Khai Nguyen (1) Xin Guo (1) Jan Peters (1) Ngan Le (1) Duy Minh Ho Nguyen (1)

Research topics

Machine Learning (7) Optimization & Theory · Machine Learning (5) Core Methods (4) Deep Learning (3) Application Areas (2) Architectures (2) Learning Types (2) Optimization & Theory · Deep Learning (2) Artificial Intelligence (1) Bayesian & Probabilistic (1) Core AI (1) Techniques (1)

Keywords

parameter estimation (3) mixture of expert (3) softmax gating (2) convergence rate (2) neural network optimization (1) empirical risk minimization (1) maximum likelihood (1) maximum likelihood estimation (1) gpu implementation (1) bootstrap (1) confidence set (1) multinomial logistic (1) molecule property prediction (1) asymptotic distribution (1) model efficiency (1) maximum likelihood estimator (1) token merging (1) distance geometry (1) flops reduction (1) neural network (1)

Papers

Accelerating Transformers with Spectrum-Preserving Token Merging NeurIPS 2024 A General Theory for Softmax Gating Multinomial Logistic Mixture of Experts ICML 2024 On the Asymptotic Distribution of the Minimum Empirical Risk ICML 2024 Structure-Aware E(3)-Invariant Molecular Conformer Aggregation Networks ICML 2024 Towards Convergence Rates for Parameter Estimation in Gaussian-gated Mixture of Experts AISTATS 2024 Demystifying Softmax Gating Function in Gaussian Mixture of Experts NeurIPS 2023 HyperRouter: Towards Efficient Training and Inference of Sparse Mixture of Experts EMNLP 2023