no code implementations • 18 Feb 2024 • Chiraag Kaushik, Ran Liu, Chi-Heng Lin, Amrit Khera, Matthew Y Jin, Wenrui Ma, Vidya Muthukumar, Eva L Dyer
Classification models are expected to perform equally well for different classes, yet in practice, there are often large gaps in their performance.
1 code implementation • 17 Aug 2023 • Mehdi Azabou, Venkataramana Ganesh, Shantanu Thakoor, Chi-Heng Lin, Lakshmi Sathidevi, Ran Liu, Michal Valko, Petar Veličković, Eva L. Dyer
Message passing neural networks have shown a lot of success on graph-structured data.
Ranked #1 on Node Classification on AMZ Comp
no code implementations • 10 Oct 2022 • Chi-Heng Lin, Chiraag Kaushik, Eva L. Dyer, Vidya Muthukumar
Data augmentation (DA) is a powerful workhorse for bolstering performance in modern machine learning.
no code implementations • 22 Jun 2022 • Jun-Kun Wang, Chi-Heng Lin, Andre Wibisono, Bin Hu
An additional condition needs to be satisfied for the acceleration result of HB beyond quadratics in this work, which naturally holds when the dimension is one or, more broadly, when the Hessian is diagonal.
1 code implementation • NeurIPS 2021 • Ran Liu, Mehdi Azabou, Max Dabagia, Chi-Heng Lin, Mohammad Gheshlaghi Azar, Keith B. Hengen, Michal Valko, Eva L. Dyer
Our approach combines a generative modeling framework with an instance-specific alignment loss that tries to maximize the representational similarity between transformed views of the input (brain state).
no code implementations • ICLR 2020 • Jun-Kun Wang, Chi-Heng Lin, Jacob Abernethy
At the same time, a widely-observed empirical phenomenon is that in training deep networks stochastic momentum appears to significantly improve convergence time, variants of it have flourished in the development of other popular update methods, e. g. ADAM [KB15], AMSGrad [RKK18], etc.
1 code implementation • 19 Feb 2021 • Mehdi Azabou, Mohammad Gheshlaghi Azar, Ran Liu, Chi-Heng Lin, Erik C. Johnson, Kiran Bhaskaran-Nair, Max Dabagia, Bernardo Avila-Pires, Lindsey Kitchell, Keith B. Hengen, William Gray-Roncal, Michal Valko, Eva L. Dyer
State-of-the-art methods for self-supervised learning (SSL) build representations by maximizing the similarity between different transformed "views" of a sample.
1 code implementation • 21 Dec 2020 • Chi-Heng Lin, Mehdi Azabou, Eva L. Dyer
Optimal transport (OT) is a widely used technique for distribution alignment, with applications throughout the machine learning, graphics, and vision communities.
no code implementations • 4 Oct 2020 • Jun-Kun Wang, Chi-Heng Lin, Jacob Abernethy
Our result shows that with the appropriate choice of parameters Polyak's momentum has a rate of $(1-\Theta(\frac{1}{\sqrt{\kappa'}}))^t$.
no code implementations • 4 Jun 2020 • Chi-Heng Lin, Joseph D. Miano, Eva L. Dyer
In this work, we propose a new algorithm for switch cost-aware optimization called Lazy Modular Bayesian Optimization (LaMBO).