research
∙
02/12/2023
Flag Aggregator: Scalable Distributed Training under Failures and Augmented Losses using Convex Optimization
Modern ML applications increasingly rely on complex deep learning models...
share
research
∙
02/11/2023
Differentiable Outlier Detection Enable Robust Deep Multimodal Analysis
Often, deep network models are purely inductive during training and whil...
research
∙
02/05/2023
Using Intermediate Forward Iterates for Intermediate Generator Optimization
Score-based models have recently been introduced as a richer framework t...
research
∙
04/15/2022
Deep Unlearning via Randomized Conditionally Independent Hessians
Recent legislation has led to interest in machine unlearning, i.e., remo...
research
∙
03/29/2022
Equivariance Allows Handling Multiple Nuisance Variables When Analyzing Pooled Neuroimaging Datasets
Pooling multiple neuroimaging datasets across institutions often enables...
research
∙
02/18/2022
Mixed Effects Neural ODE: A Variational Approximation for Analyzing the Dynamics of Panel Data
Panel data involving longitudinal measurements of the same set of partic...
research
∙
11/18/2021
You Only Sample (Almost) Once: Linear Cost Self-Attention Via Bernoulli Sampling
Transformer-based models are widely used in natural language processing ...
research
∙
08/19/2021
Neural TMDlayer: Modeling Instantaneous flow of features via SDE Generators
We study how stochastic differential equation (SDE) based ideas can insp...
research
∙
02/16/2021
Learning Invariant Representations using Inverse Contrastive Loss
Learning invariant representations is a critical first step in a number ...
research
∙
04/30/2020
Physarum Powered Differentiable Linear Programming Layers and Applications
Consider a learning algorithm, which involves an internal call to an opt...
research
∙
04/03/2020
FairALM: Augmented Lagrangian Method for Training Fair Models with Little Regret
Algorithmic decision making based on computer vision and machine learnin...
research
∙
09/26/2019
Optimizing Nondecomposable Data Dependent Regularizers via Lagrangian Reparameterization offers Significant Performance and Efficiency Gains
Data dependent regularization is known to benefit a wide variety of prob...
research
∙
03/21/2018
Robust Blind Deconvolution via Mirror Descent
We revisit the Blind Deconvolution problem with a focus on understanding...
research
∙
03/17/2018
Constrained Deep Learning using Conditional Gradient and Applications in Computer Vision
A number of results have recently demonstrated the benefits of incorpora...
research
∙
08/22/2017
A Deterministic Nonsmooth Frank Wolfe Algorithm with Coreset Guarantees
We present a new Frank-Wolfe (FW) type algorithm that is applicable to m...
research
∙
02/28/2017
On architectural choices in deep learning: From network structure to gradient convergence and parameter estimation
We study mechanisms to characterize how the asymptotic convergence of ba...
research
∙
11/17/2015