Zobrazeno 1 - 10
of 7 919
pro vyhledávání: '"A, Argyris"'
Many alignment methods, including reinforcement learning from human feedback (RLHF), rely on the Bradley-Terry reward assumption, which is insufficient to capture the full range of general human preferences. To achieve robust alignment with general p
Externí odkaz:
http://arxiv.org/abs/2410.23223
Accurate electricity demand forecasting is essential for several reasons, especially as the integration of renewable energy sources and the transition to a decentralized network paradigm introduce greater complexity and uncertainty. The proposed meth
Externí odkaz:
http://arxiv.org/abs/2408.17366
Autor:
Mrazek, Vojtech, Kokkinis, Argyris, Papanikolaou, Panagiotis, Vasicek, Zdenek, Siozios, Kostas, Tzimpragos, Georgios, Tahoori, Mehdi, Zervakis, Georgios
Printed electronics offer ultra-low manufacturing costs and the potential for on-demand fabrication of flexible hardware. However, significant intrinsic constraints stemming from their large feature sizes and low integration density pose design chall
Externí odkaz:
http://arxiv.org/abs/2407.20589
Autor:
Serré, Gaëtan, Beja-Battais, Perceval, Chirrane, Sophia, Kalogeratos, Argyris, Vayatis, Nicolas
In this paper, we propose simple yet effective empirical improvements to the algorithms of the LIPO family, introduced in [Malherbe2017], that we call LIPO+ and AdaLIPO+. We compare our methods to the vanilla versions of the algorithms over standard
Externí odkaz:
http://arxiv.org/abs/2406.19723
Autor:
Kalavasis, Alkis, Karbasi, Amin, Oikonomou, Argyris, Sotiraki, Katerina, Velegkas, Grigoris, Zampetakis, Manolis
As ML models become increasingly complex and integral to high-stakes domains such as finance and healthcare, they also become more susceptible to sophisticated adversarial attacks. We investigate the threat posed by undetectable backdoors, as defined
Externí odkaz:
http://arxiv.org/abs/2406.05660
Autor:
Li, Yingkai, Oikonomou, Argyris
We study a single-agent contracting environment where the agent has misspecified beliefs about the outcome distributions for each chosen action. First, we show that for a myopic Bayesian learning agent with only two possible actions, the empirical fr
Externí odkaz:
http://arxiv.org/abs/2405.20423
Autor:
Agarwal, Sushant, Kamath, Gautam, Majid, Mahbod, Mouzakis, Argyris, Silver, Rose, Ullman, Jonathan
We study person-level differentially private (DP) mean estimation in the case where each person holds multiple samples. DP here requires the usual notion of distributional stability when $\textit{all}$ of a person's datapoints can be modified. Inform
Externí odkaz:
http://arxiv.org/abs/2405.20405
This paper addresses the multiple two-sample test problem in a graph-structured setting, which is a common scenario in fields such as Spatial Statistics and Neuroscience. Each node $v$ in fixed graph deals with a two-sample testing problem between tw
Externí odkaz:
http://arxiv.org/abs/2402.05715
In this paper, we present a flow-based method for global optimization of continuous Sobolev functions, called Stein Boltzmann Sampling (SBS). SBS initializes uniformly a number of particles representing candidate solutions, then uses the Stein Variat
Externí odkaz:
http://arxiv.org/abs/2402.04689
We give an example of a class of distributions that is learnable in total variation distance with a finite number of samples, but not learnable under $(\varepsilon, \delta)$-differential privacy. This refutes a conjecture of Ashtiani.
Comment: T
Comment: T
Externí odkaz:
http://arxiv.org/abs/2402.00267