research
∙
08/24/2023
CALM : A Multi-task Benchmark for Comprehensive Assessment of Language Model Bias
As language models (LMs) become increasingly powerful, it is important t...
share
research
∙
08/17/2023
Semantic Consistency for Assuring Reliability of Large Language Models
Large Language Models (LLMs) exhibit remarkable fluency and competence a...
research
∙
06/13/2023
Survey on Sociodemographic Bias in Natural Language Processing
Deep neural networks often learn unintended biases during training, whic...
research
∙
03/10/2023
Do we need entire training data for adversarial training?
Deep Neural Networks (DNNs) are being used to solve a wide range of prob...
research
∙
04/05/2022
SwapMix: Diagnosing and Regularizing the Over-Reliance on Visual Context in Visual Question Answering
While Visual Question Answering (VQA) has progressed rapidly, previous w...
research
∙
05/16/2021
LocalNewton: Reducing Communication Bottleneck for Distributed Learning
To address the communication bottleneck problem in distributed optimizat...
research
∙
10/26/2020
BEAR: Sketching BFGS Algorithm for Ultra-High Dimensional Feature Selection in Sublinear Memory
We consider feature selection for applications in machine learning where...
research
∙
10/18/2020
Fast Distributed Training of Deep Neural Networks: Dynamic Communication Thresholding for Model and Data Parallelism
Data Parallelism (DP) and Model Parallelism (MP) are two common paradigm...
research
∙
08/18/2020
Utility-based Resource Allocation and Pricing for Serverless Computing
Serverless computing platforms currently rely on basic pricing schemes t...
research
∙
01/21/2020
Serverless Straggler Mitigation using Local Error-Correcting Codes
Inexpensive cloud services, such as serverless computing, are often vuln...
research
∙
01/07/2020
Stochastic Weight Averaging in Parallel: Large-Batch Training that Generalizes Well
We propose Stochastic Weight Averaging in Parallel (SWAP), an algorithm ...
research
∙
03/21/2019
OverSketched Newton: Fast Convex Optimization for Serverless Systems
Motivated by recent developments in serverless systems for large-scale m...
research
∙
11/06/2018
OverSketch: Approximate Matrix Multiplication for the Cloud
We propose OverSketch, an approximate algorithm for distributed matrix m...
research
∙
10/24/2017