6 papers
BA-DPO: Bias-Adjusted Direct Preference Optimization for Language Model Alignment
Antonio Ferrara, Alberto Rumi, Francesco Bonchi
Preference-based alignment methods such as Direct Preference Optimization (DPO) use pairwise preferences labeled by human annotators to fine-tune language models. However, annotato…
Surviving Eratosthenes sieve I: quadratic density and Legendre's conjecture
Fred B. Holt
We have been studying Eratosthenes sieve as a discrete dynamic system, obtaining exact models for the relative populations for small gaps (currently gaps ) in the cycle o…
Stochastic Shortest Path with Sparse Adversarial Costs
Emmeran Johnson, Alberto Rumi, Ciara Pike-Burke +1
We study the adversarial Stochastic Shortest Path (SSP) problem with sparse costs under full-information feedback. In the known transition setting, existing bounds based on Online…
Bandits with Abstention under Expert Advice
Stephen Pasteris, Alberto Rumi, Maximilian Thiessen +4
We study the classic problem of prediction with expert advice under bandit feedback. Our model assumes that one action, corresponding to the learner's abstention from play, has no…
Best-of-Both-Worlds Algorithms for Linear Contextual Bandits
Yuko Kuroki, Alberto Rumi, Taira Tsuchiya +2
We study best-of-both-worlds algorithms for -armed linear contextual bandits. Our algorithms deliver near-optimal regret bounds in both the adversarial and stochastic regimes, w…
Sum-max Submodular Bandits
Stephen Pasteris, Alberto Rumi, Fabio Vitale +1
Many online decision-making problems correspond to maximizing a sequence of submodular functions. In this work, we introduce sum-max functions, a subclass of monotone submodular fu…