Zobrazeno 1 - 10
of 48 567
pro vyhledávání: '"Teh, A"'
We present an empirical study investigating how specific properties of preference datasets, such as mixed-quality or noisy data, affect the performance of Preference Optimization (PO) algorithms. Our experiments, conducted in MuJoCo environments, rev
Externí odkaz:
http://arxiv.org/abs/2411.06568
Autor:
Galashov, Alexandre, Titsias, Michalis K., György, András, Lyle, Clare, Pascanu, Razvan, Teh, Yee Whye, Sahani, Maneesh
Publikováno v:
NeurIPS 2024
Neural networks are traditionally trained under the assumption that data come from a stationary distribution. However, settings which violate this assumption are becoming more popular; examples include supervised learning under distributional shifts,
Externí odkaz:
http://arxiv.org/abs/2411.04034
How to optimally persuade an agent who has a private type? When elicitation is feasible, this amounts to a fairly standard principal-agent-style mechanism design problem, where the persuader employs a mechanism to first elicit the agent's type and th
Externí odkaz:
http://arxiv.org/abs/2410.23989
We study fair allocation of indivisible chores to agents under budget constraints, where each chore has an objective size and disutility. This model captures scenarios where a set of chores need to be divided among agents with limited time, and each
Externí odkaz:
http://arxiv.org/abs/2410.23979
Supervised fine-tuning (SFT) and alignment of large language models (LLMs) are key steps in providing a good user experience. However, the concept of an appropriate alignment is inherently application-dependent, and current methods often rely on heur
Externí odkaz:
http://arxiv.org/abs/2410.21533
Autor:
Rastogi, Charvi, Teh, Tian Huey, Mishra, Pushkar, Patel, Roma, Ashwood, Zoe, Davani, Aida Mostafazadeh, Diaz, Mark, Paganini, Michela, Parrish, Alicia, Wang, Ding, Prabhakaran, Vinodkumar, Aroyo, Lora, Rieser, Verena
AI systems crucially rely on human ratings, but these ratings are often aggregated, obscuring the inherent diversity of perspectives in real-world phenomenon. This is particularly concerning when evaluating the safety of generative AI, where percepti
Externí odkaz:
http://arxiv.org/abs/2410.17032
Autor:
Mercaş, Robert, Teh, Wen Chean
The focus of this work is the study of Parikh matrices with emphasis on two concrete problems. In the first part of our presentation we show that a conjecture by Dick at al. in 2021 only stands in the case of ternary alphabets, while providing counte
Externí odkaz:
http://arxiv.org/abs/2410.15004
We study a fair division model where indivisible items arrive sequentially, and must be allocated immediately and irrevocably. Previous work on online fair division has shown impossibility results in achieving approximate envy-freeness under these co
Externí odkaz:
http://arxiv.org/abs/2410.14593
We propose SymDiff, a novel method for constructing equivariant diffusion models using the recently introduced framework of stochastic symmetrisation. SymDiff resembles a learned data augmentation that is deployed at sampling time, and is lightweight
Externí odkaz:
http://arxiv.org/abs/2410.06262
Algorithmic efficiency is essential to reducing energy use and time taken for computational problems. Optimizing efficiency is important for tasks involving multiple resources, for example in stochastic calculations where the size of the random ensem
Externí odkaz:
http://arxiv.org/abs/2410.03163