Zobrazeno 1 - 10
of 17
pro vyhledávání: '"Uziel, Guy"'
Following the advancement of large language models (LLMs), the development of LLM-based autonomous agents has become increasingly prevalent. As a result, the need to understand the security vulnerabilities of these agents has become a critical task.
Externí odkaz:
http://arxiv.org/abs/2410.16950
Autor:
Lazar, Koren, Vetzler, Matan, Uziel, Guy, Boaz, David, Goldbraich, Esther, Amid, David, Anaby-Tavor, Ateret
In the digital era, the widespread use of APIs is evident. However, scalable utilization of APIs poses a challenge due to structure divergence observed in online API documentation. This underscores the need for automatic tools to facilitate API consu
Externí odkaz:
http://arxiv.org/abs/2402.11625
Planning is a fundamental task in artificial intelligence that involves finding a sequence of actions that achieve a specified goal in a given environment. Large language models (LLMs) are increasingly used for applications that require planning capa
Externí odkaz:
http://arxiv.org/abs/2402.11489
Autor:
Uziel, Guy
Deep learning models are considered to be state-of-the-art in many offline machine learning tasks. However, many of the techniques developed are not suitable for online learning tasks. The problem of using deep learning models with sequential data be
Externí odkaz:
http://arxiv.org/abs/1905.10817
Autor:
Uziel, Guy
Deep neural networks are considered to be state of the art models in many offline machine learning tasks. However, their performance and generalization abilities in online learning tasks are much less understood. Therefore, we focus on online learnin
Externí odkaz:
http://arxiv.org/abs/1905.10821
We consider the problem of uncertainty estimation in the context of (non-Bayesian) deep neural classification. In this context, all known methods are based on extracting uncertainty signals from a trained network optimized to solve the classification
Externí odkaz:
http://arxiv.org/abs/1805.08206
Autor:
Uziel, Guy, El-Yaniv, Ran
Online portfolio selection research has so far focused mainly on minimizing regret defined in terms of wealth growth. Practical financial decision making, however, is deeply concerned with both wealth and risk. We consider online learning of portfoli
Externí odkaz:
http://arxiv.org/abs/1705.09800
Autor:
Uziel, Guy, El-Yaniv, Ran
Online-learning research has mainly been focusing on minimizing one objective function. In many real-world applications, however, several objective functions have to be considered simultaneously. Recently, an algorithm for dealing with several object
Externí odkaz:
http://arxiv.org/abs/1703.01680
Autor:
Uziel, Guy, El-Yaniv, Ran
We present a novel online ensemble learning strategy for portfolio selection. The new strategy controls and exploits any set of commission-oblivious portfolio selection algorithms. The strategy handles transaction costs using a novel commission avoid
Externí odkaz:
http://arxiv.org/abs/1605.00788
Autor:
Uziel, Guy, El-Yaniv, Ran
We consider online learning of ensembles of portfolio selection algorithms and aim to regularize risk by encouraging diversification with respect to a predefined risk-driven grouping of stocks. Our procedure uses online convex optimization to control
Externí odkaz:
http://arxiv.org/abs/1604.03266