Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Generalization Guarantees on Data-Driven Tuning of Gradient Descent with Langevin Updates
Saumya Goyal, Rohith Rongali, Ritabrata Ray +1
We study learning to learn through the lens of hyperparameter tuning. We propose the Langevin Gradient Descent Algorithm (LGD), which approximates the mean of the posterior distrib…
cs.LG2025
Eigenfunction Extraction for Ordered Representation Learning
Burak Varıcı, Che-Ping Tsai, Ritabrata Ray +2
Recent advances in representation learning reveal that widely used objectives, such as contrastive and non-contrastive, implicitly perform spectral decomposition of a contextual ke…