Zobrazeno 1 - 10
of 2 055
pro vyhledávání: '"Calinescu, A"'
A key challenge in interpretability is to decompose model activations into meaningful features. Sparse autoencoders (SAEs) have emerged as a promising tool for this task. However, a central problem in evaluating the quality of SAEs is the absence of
Externí odkaz:
http://arxiv.org/abs/2410.07456
Autor:
Wiese, Samuel, Kaszowska-Mojsa, Jagoda, Dyer, Joel, Moran, Jose, Pangallo, Marco, Lafond, Francois, Muellbauer, John, Calinescu, Anisoara, Farmer, J. Doyne
In the last few years, economic agent-based models have made the transition from qualitative models calibrated to match stylised facts to quantitative models for time series forecasting, and in some cases, their predictions have performed as well or
Externí odkaz:
http://arxiv.org/abs/2409.18760
Publikováno v:
In proceedings of The European Simulation and Modelling Conference 2023: ESM'2023, Toulouse, France October 24-26, 2023
In agent-based simulations, synthetic populations of agents are commonly used to represent the structure, behaviour, and interactions of individuals. However, generating a synthetic population that accurately reflects real population statistics is a
Externí odkaz:
http://arxiv.org/abs/2407.03180
Autor:
Herman, Lawrence, Barbarie, Christopher, Agrawal, Mohan, Calinescu, Vlad, Chen, Simon, Chiang, H. Cynthia, Day, Cherie K., Egan, Eamon, Fay, Stephen, Gerodias, Kit, Goss, Maya, Hétu, Michael, Jacobs, Daniel C., Lalonde, Marc-Olivier R., McGee, Francis, Miara, Loïc, Orlowski-Scherer, John, Sievers, Jonathan
The development of low-frequency radio astronomy experiments for detecting 21-cm line emission from hydrogen presents new opportunities for creative solutions to the challenge of characterizing an antenna beam pattern. The Array of Long Baseline Ante
Externí odkaz:
http://arxiv.org/abs/2407.00856
Empowering safe exploration of reinforcement learning (RL) agents during training is a critical impediment towards deploying RL agents in many real-world scenarios. Training RL agents in unknown, black-box environments poses an even greater safety ri
Externí odkaz:
http://arxiv.org/abs/2405.18180
Autor:
Zennaro, Fabio Massimo, Bishop, Nicholas, Dyer, Joel, Felekis, Yorgos, Calinescu, Anisoara, Wooldridge, Michael, Damoulas, Theodoros
Multi-armed bandits (MAB) and causal MABs (CMAB) are established frameworks for decision-making problems. The majority of prior work typically studies and solves individual MAB and CMAB in isolation for a given problem and associated data. However, d
Externí odkaz:
http://arxiv.org/abs/2404.17493
Autor:
Feng, Nick, Marsso, Lina, Yaman, S. Getir, Standen, Isobel, Baatartogtokh, Yesugen, Ayad, Reem, de Mello, Victória Oldemburgo, Townsend, Bev, Bartels, Hanne, Cavalcanti, Ana, Calinescu, Radu, Chechik, Marsha
Normative non-functional requirements specify constraints that a system must observe in order to avoid violations of social, legal, ethical, empathetic, and cultural norms. As these requirements are typically defined by non-technical system stakehold
Externí odkaz:
http://arxiv.org/abs/2404.12335
We study the online busy time scheduling model on heterogeneous machines. In our setting, unit-length jobs arrive online with a deadline that is known to the algorithm at the job's arrival time. An algorithm has access to machines, each with differen
Externí odkaz:
http://arxiv.org/abs/2402.11109
Autor:
Carwehl, Marc, Imrie, Calum, Vogel, Thomas, Rodrigues, Genaína, Calinescu, Radu, Grunske, Lars
In its quest for approaches to taming uncertainty in self-adaptive systems (SAS), the research community has largely focused on solutions that adapt the SAS architecture or behaviour in response to uncertainty. By comparison, solutions that reduce th
Externí odkaz:
http://arxiv.org/abs/2401.17187
Autor:
Feng, Nick, Marsso, Lina, Yaman, Sinem Getir, Baatartogtokh, Yesugen, Ayad, Reem, de Mello, Victória Oldemburgo, Townsend, Beverley, Standen, Isobel, Stefanakos, Ioannis, Imrie, Calum, Rodrigues, Genaína Nunes, Cavalcanti, Ana, Calinescu, Radu, Chechik, Marsha
As software systems increasingly interact with humans in application domains such as transportation and healthcare, they raise concerns related to the social, legal, ethical, empathetic, and cultural (SLEEC) norms and values of their stakeholders. No
Externí odkaz:
http://arxiv.org/abs/2401.05673