Search Results for author:
Found 10 papers, 4 papers with code
Balanced Data, Imbalanced Spectra: Unveiling Class Disparities with Spectral Imbalance
Classification models are expected to perform equally well for different classes, yet in practice, there are often large gaps in their performance.
Half-Hop: A graph upsampling approach for slowing down message passing
Message passing neural networks have shown a lot of success on graph-structured data.
Ranked #1 on
Node Classification
on AMZ Comp
The good, the bad and the ugly sides of data augmentation: An implicit spectral regularization perspective
Data augmentation (DA) is a powerful workhorse for bolstering performance in modern machine learning.
Provable Acceleration of Heavy Ball beyond Quadratics for a Class of Polyak-Łojasiewicz Functions when the Non-Convexity is Averaged-Out
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.
Drop, Swap, and Generate: A Self-Supervised Approach for Generating Neural Activity
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).
Escaping Saddle Points Faster with Stochastic Momentum
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.
Mine Your Own vieW: Self-Supervised Learning Through Across-Sample Prediction
State-of-the-art methods for self-supervised learning (SSL) build representations by maximizing the similarity between different transformed "views" of a sample.
Making transport more robust and interpretable by moving data through a small number of anchor points
Optimal transport (OT) is a widely used technique for distribution alignment, with applications throughout the machine learning, graphics, and vision communities.
A Modular Analysis of Provable Acceleration via Polyak's Momentum: Training a Wide ReLU Network and a Deep Linear Network
Our result shows that with the appropriate choice of parameters Polyak's momentum has a rate of $(1-\Theta(\frac{1}{\sqrt{\kappa'}}))^t$.
Bayesian optimization for modular black-box systems with switching costs
In this work, we propose a new algorithm for switch cost-aware optimization called Lazy Modular Bayesian Optimization (LaMBO).
