9 papers
SNACK: A Sequential Notation Framework for Probabilistic Graph Generation
Hohyun Kim, Hyesung Kim, Min-hwan Oh +1
We introduce SNACK, a string representation for probabilistic graph generation that enables language models to generate graphs with discrete node and edge features. SNACK linearize…
Follow-the-Perturbed-Leader for Decoupled Bandits: Best-of-Both-Worlds and Practicality
Chaiwon Kim, Jongyeong Lee, Min-hwan Oh
We study the decoupled multi-armed bandit problem, where the learner separately selects one arm for exploration and one, possibly different, arm for exploitation at each round. In…
Revisiting Follow-the-Perturbed-Leader with Unbounded Perturbations in Bandit Problems
Jongyeong Lee, Junya Honda, Shinji Ito +1
Follow-the-Regularized-Leader (FTRL) policies have achieved Best-of-Both-Worlds (BOBW) results in various settings through hybrid regularizers, whereas analogous results for Follow…
AI Should Sense Better, Not Just Scale Bigger: Adaptive Sensing as a Paradigm Shift
Eunsu Baek, Keondo Park, Jeonggil Ko +3
Current AI advances largely rely on scaling neural models and expanding training datasets to achieve generalization and robustness. Despite notable successes, this paradigm incurs…
Symmetry-Aware GFlowNets
Hohyun Kim, Seunggeun Lee, Min-hwan Oh
Generative Flow Networks (GFlowNets) offer a powerful framework for sampling graphs in proportion to their rewards. However, existing approaches suffer from systematic biases due t…
Adversarial Policy Optimization for Offline Preference-based Reinforcement Learning
Hyungkyu Kang, Min-hwan Oh
In this paper, we study offline preference-based reinforcement learning (PbRL), where learning is based on pre-collected preference feedback over pairs of trajectories. While offli…
Supervisory Prompt Training
Jean Ghislain Billa, Min Oh, Liang Du
The performance of Large Language Models (LLMs) relies heavily on the quality of prompts, which are often manually engineered and task-specific, making them costly and non-scalable…
Follow-the-Perturbed-Leader with Fréchet-type Tail Distributions: Optimality in Adversarial Bandits and Best-of-Both-Worlds
Jongyeong Lee, Junya Honda, Shinji Ito +1
This paper studies the optimality of the Follow-the-Perturbed-Leader (FTPL) policy in both adversarial and stochastic -armed bandits. Despite the widespread use of the Follow-th…
Doubly Perturbed Task Free Continual Learning
Byung Hyun Lee, Min-hwan Oh, Se Young Chun
Task Free online continual learning (TF-CL) is a challenging problem where the model incrementally learns tasks without explicit task information. Although training with entire dat…