Zobrazeno 1 - 10
of 3 544
pro vyhledávání: '"A. Karbasi"'
Publikováno v:
مجله اقتصاد و توسعه کشاورزی, Vol 37, Iss 2, Pp 145-156 (2023)
Export is a crucial driver of economic growth in various countries and significantly contributes to a country's entry into global markets and enhances economic success. In developing countries such as Iran, economic and social development programs pr
Externí odkaz:
https://doaj.org/article/ce2f8f3934e94f4597edc5f72d0ddaef
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 in models d
Externí odkaz:
http://arxiv.org/abs/2406.05660
In transportation networks, intersections pose significant risks of collisions due to conflicting movements of vehicles approaching from different directions. To address this issue, various tools can exert influence on traffic safety both directly an
Externí odkaz:
http://arxiv.org/abs/2405.19236
We study computational aspects of algorithmic replicability, a notion of stability introduced by Impagliazzo, Lei, Pitassi, and Sorrell [2022]. Motivated by a recent line of work that established strong statistical connections between replicability a
Externí odkaz:
http://arxiv.org/abs/2405.15599
We provide efficient replicable algorithms for the problem of learning large-margin halfspaces. Our results improve upon the algorithms provided by Impagliazzo, Lei, Pitassi, and Sorrell [STOC, 2022]. We design the first dimension-independent replica
Externí odkaz:
http://arxiv.org/abs/2402.13857
Despite the significant success of large language models (LLMs), their extensive memory requirements pose challenges for deploying them in long-context token generation. The substantial memory footprint of LLM decoders arises from the necessity to st
Externí odkaz:
http://arxiv.org/abs/2402.06082
Autor:
Mehrotra, Anay, Zampetakis, Manolis, Kassianik, Paul, Nelson, Blaine, Anderson, Hyrum, Singer, Yaron, Karbasi, Amin
While Large Language Models (LLMs) display versatile functionality, they continue to generate harmful, biased, and toxic content, as demonstrated by the prevalence of human-designed jailbreaks. In this work, we present Tree of Attacks with Pruning (T
Externí odkaz:
http://arxiv.org/abs/2312.02119
Algorithmic reproducibility measures the deviation in outputs of machine learning algorithms upon minor changes in the training process. Previous work suggests that first-order methods would need to trade-off convergence rate (gradient complexity) fo
Externí odkaz:
http://arxiv.org/abs/2310.17759
Autor:
Han, Insu, Jayaram, Rajesh, Karbasi, Amin, Mirrokni, Vahab, Woodruff, David P., Zandieh, Amir
We present an approximate attention mechanism named HyperAttention to address the computational challenges posed by the growing complexity of long contexts used in Large Language Models (LLMs). Recent work suggests that in the worst-case scenario, qu
Externí odkaz:
http://arxiv.org/abs/2310.05869
Publikováno v:
Management Research Review, 2024, Vol. 47, Issue 10, pp. 1654-1683.
Externí odkaz:
http://www.emeraldinsight.com/doi/10.1108/MRR-05-2023-0318