no code implementations • 11 Apr 2024 • Tanmay Gautam, Youngsuk Park, Hao Zhou, Parameswaran Raman, Wooseok Ha
Evaluated across a range of both masked and autoregressive LMs on benchmark GLUE tasks, MeZO-SVRG outperforms MeZO with up to 20% increase in test accuracies in both full- and partial-parameter fine-tuning settings.
no code implementations • 25 May 2023 • Hilaf Hasson, Danielle C. Maddix, Yuyang Wang, Gaurav Gupta, Youngsuk Park
Ensembling is among the most popular tools in machine learning (ML) due to its effectiveness in minimizing variance and thus improving generalization.
no code implementations • 14 Mar 2023 • Arun Jambulapati, Hilaf Hasson, Youngsuk Park, Yuyang Wang
Determining causal relationship between high dimensional observations are among the most important tasks in scientific discoveries.
no code implementations • 23 Feb 2023 • Luca Masserano, Syama Sundar Rangapuram, Shubham Kapoor, Rajbir Singh Nirwan, Youngsuk Park, Michael Bohlke-Schneider
We present an adaptive sampling strategy that selects the part of the time series history that is relevant for forecasting.
1 code implementation • 15 Dec 2022 • Xiyuan Zhang, Xiaoyong Jin, Karthick Gopalswamy, Gaurav Gupta, Youngsuk Park, Xingjian Shi, Hao Wang, Danielle C. Maddix, Yuyang Wang
Transformer-based models have gained large popularity and demonstrated promising results in long-term time-series forecasting in recent years.
1 code implementation • 19 Jul 2022 • Linbo Liu, Youngsuk Park, Trong Nghia Hoang, Hilaf Hasson, Jun Huan
This work studies the threats of adversarial attack on multivariate probabilistic forecasting models and viable defense mechanisms.
1 code implementation • 24 Feb 2022 • Taeho Yoon, Youngsuk Park, Ernest K. Ryu, Yuyang Wang
Probabilistic time series forecasting has played critical role in decision-making processes due to its capability to quantify uncertainties.
no code implementations • 23 Feb 2022 • Kelvin Kan, François-Xavier Aubet, Tim Januschowski, Youngsuk Park, Konstantinos Benidis, Lars Ruthotto, Jan Gasthaus
We propose Multivariate Quantile Function Forecaster (MQF$^2$), a global probabilistic forecasting method constructed using a multivariate quantile function and investigate its application to multi-horizon forecasting.
no code implementations • 12 Nov 2021 • Youngsuk Park, Danielle Maddix, François-Xavier Aubet, Kelvin Kan, Jan Gasthaus, Yuyang Wang
Quantile regression is an effective technique to quantify uncertainty, fit challenging underlying distributions, and often provide full probabilistic predictions through joint learnings over multiple quantile levels.
no code implementations • 2 Mar 2021 • Yucheng Lu, Youngsuk Park, Lifan Chen, Yuyang Wang, Christopher De Sa, Dean Foster
In large-scale time series forecasting, one often encounters the situation where the temporal patterns of time series, while drifting over time, differ from one another in the same dataset.
1 code implementation • 13 Feb 2021 • Xiaoyong Jin, Youngsuk Park, Danielle C. Maddix, Hao Wang, Yuyang Wang
Recently, deep neural networks have gained increasing popularity in the field of time series forecasting.
no code implementations • ICML 2020 • Youngsuk Park, Ryan A. Rossi, Zheng Wen, Gang Wu, Handong Zhao
In this paper, we introduce the \textit{Structured Policy Iteration} (S-PI) for LQR, a method capable of deriving a structured linear policy.
no code implementations • 15 Oct 2019 • Youngsuk Park, Sauptik Dhar, Stephen Boyd, Mohak Shah
Under this metric selection for VM-PG, the theoretical convergence is analyzed.
1 code implementation • 6 Mar 2017 • David Hallac, Youngsuk Park, Stephen Boyd, Jure Leskovec
Many important problems can be modeled as a system of interconnected entities, where each entity is recording time-dependent observations or measurements.