mingzhang-yin/Meta-learning-without-memorization mingzhang-yin/Meta-learning-without-memorization

  • Stars
    star
    20
  • Rank 1,121,974 (Top 23 %)
  • Language
    Jupyter Notebook
  • Created almost 5 years ago
  • Updated over 1 year ago
Twitter logo Share LinkedIn logo Share Facebook logo Share
mingzhang-yin/Meta-learning-without-memorization
github

mingzhang-yin

Reviews

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Repository Details

A study on the following problems: what the memorization problem is in meta-learning; why memorization problem happens; and how we can prevent it. (ICLR 2020)

More Repositories

1

SIVI

A variational inference method with accurate uncertainty estimation. It uses a new semi-implicit variational family built on neural networks and hierarchical distribution (ICML 2018).
MATLAB
52
star
2

ARM-gradient

Low-variance, efficient and unbiased gradient estimation for optimizing models with binary latent variables. (ICLR 2019)
Python
28
star
3

CoCo

An optimization-based algorithm to accurately estimate the causal effects and robustly predict under distribution shifts. It leverages the invariance of causality over multiple environments.
Python
13
star
4

Probabilistic-Best-Subset

A probabilistic solution to the exact best subset selection problem via continuous reformulation and gradient-based optimization.
Python
6
star
5

mingzhang-yin.github.io

Personal webpage
HTML
3
star
6

Convergence-of-Gradient-EM-on-Multi-component-Mixture-of-Gaussians

Proof of local convergence region and convergence rate of gradient EM on general GMM, for both population and finite sample setting. (NeurIPS 2017)
MATLAB
2
star
7

Conformal-sensitivity-analysis

Analyzing the sensitivity of an individual treatment effect over a potential violation of unconfoundedness.
R
1
star