no code implementations • 14 Dec 2023 • Huijie Zhang, Yifu Lu, Ismail Alkhouri, Saiprasad Ravishankar, Dogyoon Song, Qing Qu
This is due to the necessity of tracking extensive forward and reverse diffusion trajectories, and employing a large model with numerous parameters across multiple timesteps (i. e., noise levels).
no code implementations • 6 Dec 2023 • Robert Malinas, Dogyoon Song, Alfred O. Hero III
Detecting communities in high-dimensional graphs can be achieved by applying random matrix theory where the adjacency matrix of the graph is modeled by a Stochastic Block Model (SBM).
1 code implementation • 8 Nov 2023 • Soo Min Kwon, Zekai Zhang, Dogyoon Song, Laura Balzano, Qing Qu
We empirically evaluate the effectiveness of our compression technique on matrix recovery problems.
1 code implementation • 27 Sep 2023 • Dennis Shen, Dogyoon Song, Peng Ding, Jasjeet S. Sekhon
Deep learning research has uncovered the phenomenon of benign overfitting for over-parameterized statistical models, which has drawn significant theoretical interest in recent years.
no code implementations • 16 May 2023 • Kyunghee Han, Dogyoon Song
Fr\'echet regression has emerged as a promising approach for regression analysis involving non-Euclidean response variables.
no code implementations • 7 Mar 2023 • Jinghan Jia, Yihua Zhang, Dogyoon Song, Sijia Liu, Alfred Hero
Most work in this learning paradigm has focused on resolving the problem of 'catastrophic forgetting,' which refers to a notorious dilemma between improving model accuracy over new data and retaining accuracy over previous data.
no code implementations • 28 Sep 2020 • Yudong Chen, Dogyoon Song, Xumei Xi, Yuqian Zhang
As the objective function is non-convex, there can be multiple local minima that are not globally optimal, even for well-separated mixture models.
no code implementations • NeurIPS 2020 • Devavrat Shah, Dogyoon Song, Zhi Xu, Yuzhe Yang
As our key contribution, we develop a simple, iterative learning algorithm that finds $\epsilon$-optimal $Q$-function with sample complexity of $\widetilde{O}(\frac{1}{\epsilon^{\max(d_1, d_2)+2}})$ when the optimal $Q$-function has low rank $r$ and the discounting factor $\gamma$ is below a certain threshold.
no code implementations • NeurIPS 2019 • Anish Agarwal, Devavrat Shah, Dennis Shen, Dogyoon Song
As an important contribution to the Synthetic Control literature, we establish that an (approximate) linear synthetic control exists in the setting of a generalized factor model; traditionally, the existence of a synthetic control needs to be assumed to exist as an axiom.
no code implementations • 31 Dec 2018 • Devavrat Shah, Dogyoon Song
Despite the success of RUMs in various domains and the versatility of mixture RUMs to capture the heterogeneity in preferences, there has been only limited progress in learning a mixture of RUMs from partial data such as pairwise comparisons.
no code implementations • NeurIPS 2016 • Dogyoon Song, Christina E. Lee, Yihua Li, Devavrat Shah
In contrast with classical regression, the features $x = (x_1(u), x_2(i))$ are not observed, making it challenging to apply standard regression methods to predict the unobserved ratings.