We lifted 2 functions out of this paper's own repositories and ran 1 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| ryanchankh/mcr2 | canonical | 1 of 2 |
| Function | Status | Where it lives |
|---|---|---|
| svm | Ran | ryanchankh/mcr2/evaluate.py pointer only (licence: NONE) · get_code("bac061dbcd471695") |
| load_architectures | Not yet run | ryanchankh/mcr2/train_func.py pointer only (licence: NONE) · get_code("25a77ab10668ae65") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
To learn intrinsic low-dimensional structures from high-dimensional data that most discriminate between classes, we propose the principle of Maximal Coding Rate Reduction ($\text{MCR}^2$), an information-theoretic measure that maximizes the coding rate difference between the whole dataset and the sum of each individual class. We clarify its relationships with most existing frameworks such as cross-entropy, information bottleneck, information gain, contractive and contrastive learning, and provide theoretical guarantees for learning diverse and discriminative features. The coding rate can be accurately computed from finite samples of degenerate subspace-like distributions and can learn intrinsic representations in supervised, self-supervised, and unsupervised settings in a unified manner. Empirically, the representations learned using this principle alone are significantly more robust to label corruptions in classification than those using cross-entropy, and can lead to state-of-the-art results in clustering mixed data from self-learned invariant features.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2006.08558")
get_code_for_paper("2006.08558")
have("2006.08558")
Connect an agent — have() is free.