Skip to content
View Decadz's full-sized avatar
🥝
🥝
27 followers · 24 following

Achievements

Achievement: StarstruckAchievement: QuickdrawAchievement: Pull SharkAchievement: Arctic Code Vault Contributor

Achievements

Achievement: StarstruckAchievement: QuickdrawAchievement: Pull SharkAchievement: Arctic Code Vault Contributor

Highlights

  • Pro

Block or report Decadz

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. Markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Decadz/README.md

Hi, I'm Christian! 👋

I'm a senior applied scientist at Oracle, where I work on natural language processing and reinforcement learning, developing models that support and streamline healthcare. Previously, I worked at Amazon, developing a foundation model for 3D computer vision. I completed my PhD at Victoria University of Wellington (VUW) in New Zealand, where my research focused on meta-learning loss functions for deep neural networks. My current research interests include meta-learning, meta-optimization, hyperparameter optimization, few-shot learning, and continual learning.

Google Scholar LinkedIn

Pinned Loading

  1. Evolved-Model-Agnostic-Loss Evolved-Model-Agnostic-Loss Public

    [TPAMI 2023] Learning Symbolic Model-Agnostic Loss Functions via Meta-Learning. Paper Link: https://arxiv.org/abs/2209.08907

    Python 15

  2. Online-Loss-Function-Learning Online-Loss-Function-Learning Public

    [TMLR 2025] Meta-Learning Adaptive Loss Functions. Paper Link: https://arxiv.org/abs/2301.13247

    Python 1

  3. Sparse-Label-Smoothing-Regularization Sparse-Label-Smoothing-Regularization Public

    [TPAMI 2023] PyTorch code for Sparse Label Smoothing Regularization presented in "Learning Symbolic Model-Agnostic Loss Functions via Meta-Learning". Paper Link: https://arxiv.org/abs/2209.08907

    Python 2

  4. Genetic-Programming-with-Rademacher-Complexity Genetic-Programming-with-Rademacher-Complexity Public

    [CEC 2019] Genetic Programming with Rademacher Complexity. Paper Link: https://ieeexplore.ieee.org/document/8790341

    Python 16 4

  5. Meta-Learning-Literature-Overview Meta-Learning-Literature-Overview Public

    List of AI/ML papers related to my thesis on "Meta-Learning Loss Functions for Deep Neural Networks". Thesis link: https://arxiv.org/abs/2406.09713

    5