Trung Trinh

trung.trinh [at] aalto [dot] fi

Research interests: Robust Machine Learning, Bayesian Deep Learning, Uncertainty Quantification, Optimization

prof_pic.jpg

Aalto University Computer Science Building

Konemiehentie 2

02150 Espoo, Finland

I’m currently a Ph.D. student in the Probablistic Machine Learning group at Aalto University under the supervision of Prof. Samuel Kaski. I’m expected to graduate in October 2025, and I’m currently looking for research visit opportunities.

My primary research interest lies in enhancing the robustness of deep learning models to distribution shifts. Distribution shifts refer to changes in data distribution between the training and deployment phases, which can lead to significant degradation in model performance. Neural networks are especially vulnerable to these shifts, reducing their reliability in practical applications. My goal is to improve the resilience of neural networks, enabling their deployment in safety-critical systems, such as autonomous vehicles and medical diagnostics. My current work focuses on enhancing generalization and uncertainty calibration of neural networks under distribution shifts through efficient Bayesian approaches and advanced optimization methods.

selected publications

  1. NeurIPS Spotlight
    Improving robustness to corruptions with multiplicative weight perturbations
    Trung Trinh, Markus Heinonen, Luigi Acerbi, and Samuel Kaski
    Advances in Neural Information Processing Systems 38, 2024
  2. ICLR Spotlight
    Input-gradient space particle inference for neural network ensembles
    Trung Trinh, Markus Heinonen, Luigi Acerbi, and Samuel Kaski
    In The Twelfth International Conference on Learning Representations , 2024
  3. ICML Oral
    Tackling covariate shift with node-based Bayesian neural networks
    Trung Trinh, Markus Heinonen, Luigi Acerbi, and Samuel Kaski
    In Proceedings of the 39th International Conference on Machine Learning , 2022
  4. Master thesis
    Scalable Bayesian neural networks
    Trung Trinh
    Jun 2021