add method: Uniform Risk Minimization (URM)

[kiranchari]

I am first author of "Uniformly Distributed Feature Representations for Fair and Robust Learning" (TMLR 2024) paper. Link: https://openreview.net/forum?id=PgLbS5yp8n

In this pull request I am adding code for the proposed Uniform Risk Minimization (URM) method for subpopulation robustness. The key idea is to encourage the distribution of feature representations learned by the encoder/featurizer to be uniformly distributed. The paper provides theoretical and empirical support for the proposed method in sub-population robustness and also domain generalization.

Changes include:

• added URM class in algorithms.py
• added hyper-parameters in hparams_registry.py
• modified networks.py and lib/wide_resnet.py to add an activation function to the output of the featurizer/encoder networks (before the linear classifier). This does not affect other algorithms in SubpopBench as the default activation is nn.Identity(): https://github.com/kiranchari/SubpopBench/blob/198ea9548948b5af0a084798878c880e89d248d6/subpopbench/models/networks.py#L31
• added method and link to paper in README.md

Thank you.