ML: Contrastive learning

Machine-learning ideas tagged Contrastive learning in the ML taxonomy of the Math2NN corpus.

2 ideas found

Status: Unverified ML: Contrastive learning Clear all

Unverified 2026

Quantile-Calibrated Multi-Scale Spectral Regularizer

Build several Gaussian similarity matrices on minibatch embeddings, using empirical distance quantiles as their bandwidths, then combine them before degree normalization and spectral embedding. Add a regularizer that encourages the resulting row-normalized spectral coordinates to form compact pseudo-clusters, making the representation robust to multiple geometric scales rather than one manually tuned temperature.

Useful6/10

Difficulty5/10

Novelty5/10

Regularization Accuracy Generalization Sample efficiency

Paper: Multi-kernel spectral clustering: Entrywise eigenvector perturbation bounds and exact recovery arXiv:2608.08704

Unverified 2026

Spherical Hemisphere Balance Regularizer

Add a coordinate-free regularizer that prevents a batch of unit-normalized embeddings from concentrating almost entirely on one side of a hyperplane passing through their spherical centroid. Sample random directions tangent to the estimated centroid, measure the soft fraction of embeddings in each corresponding hemisphere, and penalize fractions below the spherical Grünbaum constant. This targets directional mode collapse while preserving rotational invariance.

Useful5/10

Difficulty3/10

Novelty7/10

Regularization Generalization Stability Embedding

Paper: The Spherical Grünbaum Inequality arXiv:2607.16924