Zobrazeno 1 - 10
of 289
pro vyhledávání: '"Kong Lingkai"'
Comparing datasets is a fundamental task in machine learning, essential for various learning paradigms; from evaluating train and test datasets for model generalization to using dataset similarity for detecting data drift. While traditional notions o
Externí odkaz:
http://arxiv.org/abs/2409.06997
Transit timing variation (TTV) provides rich information about the mass and orbital properties of exoplanets, which are often obtained by solving an inverse problem via Markov Chain Monte Carlo (MCMC). In this paper, we design a new data-driven appro
Externí odkaz:
http://arxiv.org/abs/2409.04557
LLMs are increasingly used to design reward functions based on human preferences in Reinforcement Learning (RL). We focus on LLM-designed rewards for Restless Multi-Armed Bandits, a framework for allocating limited resources among agents. In applicat
Externí odkaz:
http://arxiv.org/abs/2408.12112
Multi-variate time series forecasting is an important problem with a wide range of applications. Recent works model the relations between time-series as graphs and have shown that propagating information over the relation graph can improve time serie
Externí odkaz:
http://arxiv.org/abs/2407.02641
Autor:
Wang, Haorui, Skreta, Marta, Ser, Cher-Tian, Gao, Wenhao, Kong, Lingkai, Strieth-Kalthoff, Felix, Duan, Chenru, Zhuang, Yuchen, Yu, Yue, Zhu, Yanqiao, Du, Yuanqi, Aspuru-Guzik, Alán, Neklyudov, Kirill, Zhang, Chao
Molecular discovery, when formulated as an optimization problem, presents significant computational challenges because optimization objectives can be non-differentiable. Evolutionary Algorithms (EAs), often used to optimize black-box objectives in mo
Externí odkaz:
http://arxiv.org/abs/2406.16976
Autor:
Liu, Haoxin, Kamarthi, Harshavardhan, Kong, Lingkai, Zhao, Zhiyuan, Zhang, Chao, Prakash, B. Aditya
Time-series forecasting (TSF) finds broad applications in real-world scenarios. Due to the dynamic nature of time-series data, it is crucial to equip TSF models with out-of-distribution (OOD) generalization abilities, as historical training data and
Externí odkaz:
http://arxiv.org/abs/2406.09130
Autor:
Liu, Haoxin, Xu, Shangqing, Zhao, Zhiyuan, Kong, Lingkai, Kamarthi, Harshavardhan, Sasanur, Aditya B., Sharma, Megha, Cui, Jiaming, Wen, Qingsong, Zhang, Chao, Prakash, B. Aditya
Time series data are ubiquitous across a wide range of real-world domains. While real-world time series analysis (TSA) requires human experts to integrate numerical series data with multimodal domain-specific knowledge, most existing TSA models rely
Externí odkaz:
http://arxiv.org/abs/2406.08627
Autor:
Kong, Lingkai, Wang, Haorui, Mu, Wenhao, Du, Yuanqi, Zhuang, Yuchen, Zhou, Yifei, Song, Yue, Zhang, Rongzhi, Wang, Kai, Zhang, Chao
Aligning large language models (LLMs) with human objectives is crucial for real-world applications. However, fine-tuning LLMs for alignment often suffers from unstable training and requires substantial computing resources. Test-time alignment techniq
Externí odkaz:
http://arxiv.org/abs/2406.05954
Autor:
Kong, Lingkai, Tao, Molei
Explicit, momentum-based dynamics that optimize functions defined on Lie groups can be constructed via variational optimization and momentum trivialization. Structure preserving time discretizations can then turn this dynamics into optimization algor
Externí odkaz:
http://arxiv.org/abs/2405.20390
The generative modeling of data on manifold is an important task, for which diffusion models in flat spaces typically need nontrivial adaptations. This article demonstrates how a technique called `trivialization' can transfer the effectiveness of dif
Externí odkaz:
http://arxiv.org/abs/2405.16381