Zobrazeno 1 - 10
of 28
pro vyhledávání: '"Li, Shuai"'
Web-based applications such as chatbots, search engines and news recommendations continue to grow in scale and complexity with the recent surge in the adoption of LLMs. Online model selection has thus garnered increasing attention due to the need to
Externí odkaz:
http://arxiv.org/abs/2403.07213
In this work, we study the low-rank MDPs with adversarially changed losses in the full-information feedback setting. In particular, the unknown transition probability kernel admits a low-rank matrix decomposition \citep{REPUCB22}, and the loss functi
Externí odkaz:
http://arxiv.org/abs/2311.07876
Autor:
Wu, Junda, Yu, Tong, Wang, Rui, Song, Zhao, Zhang, Ruiyi, Zhao, Handong, Lu, Chaochao, Li, Shuai, Henao, Ricardo
Soft prompt tuning achieves superior performances across a wide range of few-shot tasks. However, the performances of prompt tuning can be highly sensitive to the initialization of the prompts. We also empirically observe that conventional prompt tun
Externí odkaz:
http://arxiv.org/abs/2306.04933
The linear bandit problem has been studied for many years in both stochastic and adversarial settings. Designing an algorithm that can optimize the environment without knowing the loss type attracts lots of interest. \citet{LeeLWZ021} propose an algo
Externí odkaz:
http://arxiv.org/abs/2303.06825
Conversational contextual bandits elicit user preferences by occasionally querying for explicit feedback on key-terms to accelerate learning. However, there are aspects of existing approaches which limit their performance. First, information gained f
Externí odkaz:
http://arxiv.org/abs/2303.00315
Density peaks clustering has become a nova of clustering algorithm because of its simplicity and practicality. However, there is one main drawback: it is time-consuming due to its high computational complexity. Herein, a density peaks clustering algo
Externí odkaz:
http://arxiv.org/abs/2203.00973
Thompson sampling (TS) has attracted a lot of interest in the bandit area. It was introduced in the 1930s but has not been theoretically proven until recent years. All of its analysis in the combinatorial multi-armed bandit (CMAB) setting requires an
Externí odkaz:
http://arxiv.org/abs/2111.04295
The bandit problem with graph feedback, proposed in [Mannor and Shamir, NeurIPS 2011], is modeled by a directed graph $G=(V,E)$ where $V$ is the collection of bandit arms, and once an arm is triggered, all its incident arms are observed. A fundamenta
Externí odkaz:
http://arxiv.org/abs/2105.14260
Conservative mechanism is a desirable property in decision-making problems which balance the tradeoff between the exploration and exploitation. We propose the novel \emph{conservative contextual combinatorial cascading bandit ($C^4$-bandit)}, a casca
Externí odkaz:
http://arxiv.org/abs/2104.08615
The problem of adversarial examples has shown that modern Neural Network (NN) models could be rather fragile. Among the more established techniques to solve the problem, one is to require the model to be {\it $\epsilon$-adversarially robust} (AR); th
Externí odkaz:
http://arxiv.org/abs/2011.07478