44 citations · 199 across the 22 of their papers we have counts for
23 papers
LatentDR: Improving Model Generalization Through Sample-Aware Latent Degradation and Restoration
Ran Liu, Sahil Khose, Jingyun Xiao +4
Despite significant advances in deep learning, models often struggle to generalize well to new, unseen domains, especially when training data is limited. To address this challenge,…
Half-Hop: A graph upsampling approach for slowing down message passing
Mehdi Azabou, Venkataramana Ganesh, Shantanu Thakoor +6
Message passing neural networks have shown a lot of success on graph-structured data. However, there are many instances where message passing can lead to over-smoothing or fail whe…
Relax, it doesn't matter how you get there: A new self-supervised approach for multi-timescale behavior analysis
Mehdi Azabou, Michael Mendelson, Nauman Ahad +4
Natural behavior consists of dynamics that are complex and unpredictable, especially when trying to predict many steps into the future. While some success has been found in buildin…
MTNeuro: A Benchmark for Evaluating Representations of Brain Structure Across Multiple Levels of Abstraction
Jorge Quesada, Lakshmi Sathidevi, Ran Liu +10
There are multiple scales of abstraction from which we can describe the same image, depending on whether we are focusing on fine-grained details or a more global attribute of the i…
The good, the bad and the ugly sides of data augmentation: An implicit spectral regularization perspective
Chi-Heng Lin, Chiraag Kaushik, Eva L. Dyer +1
Data augmentation (DA) is a powerful workhorse for bolstering performance in modern machine learning. Specific augmentations like translations and scaling in computer vision are tr…
Learning Behavior Representations Through Multi-Timescale Bootstrapping
Mehdi Azabou, Michael Mendelson, Maks Sorokin +4
Natural behavior consists of dynamics that are both unpredictable, can switch suddenly, and unfold over many different timescales. While some success has been found in building rep…
Seeing the forest and the tree: Building representations of both individual and collective dynamics with transformers
Ran Liu, Mehdi Azabou, Max Dabagia +2
Complex time-varying systems are often studied by abstracting away from the dynamics of individual components to build a model of the population-level dynamics from the start. Howe…
Comparing high-dimensional neural recordings by aligning their low-dimensional latent representations
Max Dabagia, Konrad P Kording, Eva L Dyer
Many questions in neuroscience involve understanding of the responses of large populations of neurons. However, when dealing with large-scale neural activity, interpretation become…
Learning Sinkhorn divergences for supervised change point detection
Nauman Ahad, Eva L. Dyer, Keith B. Hengen +2
Many modern applications require detecting change points in complex sequential data. Most existing methods for change point detection are unsupervised and, as a consequence, lack a…
Drop, Swap, and Generate: A Self-Supervised Approach for Generating Neural Activity
Ran Liu, Mehdi Azabou, Max Dabagia +5
Meaningful and simplified representations of neural activity can yield insights into how and what information is being processed within a neural circuit. However, without labels, f…
Neural Latents Benchmark '21: Evaluating latent variable models of neural population activity
Felix Pei, Joel Ye, David Zoltowski +13
Advances in neural recording present increasing opportunities to study neural activity in unprecedented detail. Latent variable models (LVMs) are promising tools for analyzing this…
Mine Your Own vieW: Self-Supervised Learning Through Across-Sample Prediction
Mehdi Azabou, Mohammad Gheshlaghi Azar, Ran Liu +10
State-of-the-art methods for self-supervised learning (SSL) build representations by maximizing the similarity between different transformed "views" of a sample. Without sufficient…
Large-Scale Representation Learning on Graphs via Bootstrapping
Shantanu Thakoor, Corentin Tallec, Mohammad Gheshlaghi Azar +5
Self-supervised learning provides a promising path towards eliminating the need for costly label information in representation learning on graphs. However, to achieve state-of-the-…
Making transport more robust and interpretable by moving data through a small number of anchor points
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. Without any addit…
Bayesian optimization for modular black-box systems with switching costs
Chi-Heng Lin, Joseph D. Miano, Eva L. Dyer
Most existing black-box optimization methods assume that all variables in the system being optimized have equal cost and can change freely at each iteration. However, in many real…
Hierarchical Optimal Transport for Multimodal Distribution Alignment
John Lee, Max Dabagia, Eva L. Dyer +1
In many machine learning applications, it is necessary to meaningfully aggregate, through alignment, different but related datasets. Optimal transport (OT)-based approaches pose al…
Quantifying mesoscale neuroanatomy using X-ray microtomography
Eva L. Dyer, William Gray Roncal, Hugo L. Fernandes +9
Methods for resolving the 3D microstructure of the brain typically start by thinly slicing and staining the brain, and then imaging each individual section with visible light photo…
From sample to knowledge: Towards an integrated approach for neuroscience discovery
William Gray Roncal, Eva L Dyer, Doga Gürsoy +2
Imaging methods used in modern neuroscience experiments are quickly producing large amounts of data capable of providing increasing amounts of knowledge about neuroanatomy and func…
Convex Relaxation Regression: Black-Box Optimization of Smooth Functions by Learning Their Convex Envelopes
Mohammad Gheshlaghi Azar, Eva Dyer, Konrad Kording
Finding efficient and provable methods to solve non-convex optimization problems is an outstanding challenge in machine learning and optimization theory. A popular approach used to…
oASIS: Adaptive Column Sampling for Kernel Matrix Approximation
Raajen Patel, Thomas A. Goldstein, Eva L. Dyer +2
Kernel matrices (e.g. Gram or similarity matrices) are essential for many state-of-the-art approaches to classification, clustering, and dimensionality reduction. For large dataset…
Self-Expressive Decompositions for Matrix Approximation and Clustering
Eva L. Dyer, Tom A. Goldstein, Raajen Patel +2
Data-aware methods for dimensionality reduction and matrix decomposition aim to find low-dimensional structure in a collection of data. Classical approaches discover such structure…
RankMap: A Platform-Aware Framework for Distributed Learning from Dense Datasets
Azalia Mirhoseini, Eva L. Dyer, Ebrahim. M. Songhori +2
This paper introduces RankMap, a platform-aware end-to-end framework for efficient execution of a broad class of iterative learning algorithms for massive and dense datasets. Our f…
Greedy Feature Selection for Subspace Clustering
Eva L. Dyer, Aswin C. Sankaranarayanan, Richard G. Baraniuk
Unions of subspaces provide a powerful generalization to linear subspace models for collections of high-dimensional data. To learn a union of subspaces from a collection of data, s…