works on

From the 1 of 111 linked papers with an AI index.

activity
20242026
collaborators
Showing cs.LGShow all

5 papers · 1 filter

cs.LG2026

Cover meets Robbins while Betting on Bounded Data: Regret and Almost Sure Regret

Shubhada Agrawal, Aaditya Ramdas

Consider betting against a sequence of data in , where one is allowed to make any bet that is fair if the data have a conditional mean . Cover's universal por…

cs.LG2026

Eventually LIL Regret: Almost Sure Regret for a sub-Gaussian Mixture on Unbounded Data

Shubhada Agrawal, Aaditya Ramdas

We prove that a classic sub-Gaussian mixture proposed by Robbins in a stochastic setting actually satisfies a path-wise (deterministic) regret bound. For every path in a natural ``…

cs.LG2026

Gradient descent for deep equilibrium single-index models

Sanjit Dandapanthula, Aaditya Ramdas

Deep equilibrium models (DEQs) have recently emerged as a powerful paradigm for training infinitely deep weight-tied neural networks that achieve state of the art performance acros…

cs.LG2025

Optimal Transportation and Alignment Between Gaussian Measures

Sanjit Dandapanthula, Aleksandr Podkopaev, Shiva Prasad Kasiviswanathan +2

Optimal transport (OT) and Gromov-Wasserstein (GW) alignment provide interpretable geometric frameworks for comparing, transforming, and aggregating heterogeneous datasets -- tasks…

cs.LG2025

Private Evolution Converges

Tomás González, Giulia Fanti, Aaditya Ramdas

Private Evolution (PE) is a promising training-free method for differentially private (DP) synthetic data generation. While it achieves strong performance in some domains (e.g., im…