collaborators

8 papers

cs.LG2026

Impatient Bandits: Optimizing for the Long-Term Without Delay

Kelly W. Zhang, Thomas Baldwin-McDonald, Kamil Ciosek +2

Increasingly, recommender systems are tasked with improving users' long-term satisfaction. In this context, we study a content exploration task, which we formalize as a bandit prob…

cs.LG2026

The Neural Tangent Kernel for Classification

Jonathan Plenk, Sergio Calvo-Ordonez, Alvaro Cartea +3

In wide neural networks, the Neural Tangent Kernel (NTK) remains approximately constant during training, providing a powerful theoretical tool for studying training dynamics, gener…

cs.LG2026

Richer Bayesian Last Layers with Subsampled NTK Features

Sergio Calvo-Ordoñez, Jonathan Plenk, Richard Bergna +4

Bayesian Last Layers (BLLs) provide a convenient and computationally efficient way to estimate uncertainty in neural networks. However, they underestimate epistemic uncertainty bec…

cs.LG2026

Fast Adversarial Attacks with Gradient Prediction

Kamil Ciosek, Aleksandr V. Petrov, Nicolò Felicioni +1

Generating adversarial examples at scale is a core primitive for robustness evaluation, adversarial training, and red-teaming, yet even "fast" attacks such as FGSM remain throughpu…

cs.LG2026

The Minimax Rate of Second-Order Calibration

Kamil Ciosek, Banafsheh Rafiee, Sina Ghiassian +1

We characterize the minimax rate of estimating the second-order calibration error for binary classification, which quantifies whether a higher-order predictor's epistemic-uncertain…

cs.LG2026

A Bayesian Information-Theoretic Approach to Data Attribution

Dharmesh Tailor, Nicolò Felicioni, Kamil Ciosek

Training Data Attribution (TDA) seeks to trace model predictions back to influential training examples, enhancing interpretability and safety. We formulate TDA as a Bayesian inform…