Zobrazeno 1 - 10
of 7 979
pro vyhledávání: '"Oh, In‐Hwan"'
Autor:
Kim, Seok-Jin, Oh, Min-hwan
We study the performance guarantees of exploration-free greedy algorithms for the linear contextual bandit problem. We introduce a novel condition, named the \textit{Local Anti-Concentration} (LAC) condition, which enables a greedy bandit algorithm t
Externí odkaz:
http://arxiv.org/abs/2411.12878
Autor:
Lee, Harin, Oh, Min-hwan
In this work, we close the fundamental gap of theory and practice by providing an improved regret bound for linear ensemble sampling. We prove that with an ensemble size logarithmic in $T$, linear ensemble sampling can achieve a frequentist regret bo
Externí odkaz:
http://arxiv.org/abs/2411.03932
Autor:
Lee, Joongkyu, Oh, Min-hwan
In this work, we prove that, in linear MDPs, the feature dimension $d$ is lower bounded by $S/U$ in order to aptly represent transition probabilities, where $S$ is the size of the state space and $U$ is the maximum size of directly reachable states.
Externí odkaz:
http://arxiv.org/abs/2410.24089
Speech Emotion Recognition (SER) analyzes human emotions expressed through speech. Self-supervised learning (SSL) offers a promising approach to SER by learning meaningful representations from a large amount of unlabeled audio data. However, existing
Externí odkaz:
http://arxiv.org/abs/2410.12416
Autor:
Kim, Jung-hun, Oh, Min-hwan
In this study, we consider multi-class multi-server asymmetric queueing systems consisting of $N$ queues on one side and $K$ servers on the other side, where jobs randomly arrive in queues at each time. The service rate of each job-server assignment
Externí odkaz:
http://arxiv.org/abs/2410.10098
Autor:
Kim, Sang Min, Kim, Byeongchan, Sehanobish, Arijit, Choromanski, Krzysztof, Shim, Dongseok, Dubey, Avinava, Oh, Min-hwan
Improving the efficiency and performance of implicit neural representations in 3D, particularly Neural Radiance Fields (NeRF) and Signed Distance Fields (SDF) is crucial for enabling their use in real-time applications. These models, while capable of
Externí odkaz:
http://arxiv.org/abs/2410.09771
Autor:
Nam, Jaehyun, Song, Woomin, Park, Seong Hyeon, Tack, Jihoon, Yun, Sukmin, Kim, Jaehyung, Oh, Kyu Hwan, Shin, Jinwoo
Learning with a limited number of labeled data is a central problem in real-world applications of machine learning, as it is often expensive to obtain annotations. To deal with the scarcity of labeled data, transfer learning is a conventional approac
Externí odkaz:
http://arxiv.org/abs/2408.11063
We consider a stochastic sparse linear bandit problem where only a sparse subset of context features affects the expected reward function, i.e., the unknown reward parameter has sparse structure. In the existing Lasso bandit literature, the compatibi
Externí odkaz:
http://arxiv.org/abs/2406.00823
We study reinforcement learning with multinomial logistic (MNL) function approximation where the underlying transition probability kernel of the Markov decision processes (MDPs) is parametrized by an unknown transition core with features of state and
Externí odkaz:
http://arxiv.org/abs/2405.20165
Autor:
Lee, Joongkyu, Oh, Min-hwan
In this paper, we study the contextual multinomial logit (MNL) bandit problem in which a learning agent sequentially selects an assortment based on contextual information, and user feedback follows an MNL choice model. There has been a significant di
Externí odkaz:
http://arxiv.org/abs/2405.09831